CN109271465A - A kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing - Google Patents
A kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing Download PDFInfo
- Publication number
- CN109271465A CN109271465A CN201810964010.5A CN201810964010A CN109271465A CN 109271465 A CN109271465 A CN 109271465A CN 201810964010 A CN201810964010 A CN 201810964010A CN 109271465 A CN109271465 A CN 109271465A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- projection
- water
- value
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing, the relevant mode of its room and time and rule are shown by way of combining space-time data and geographic mapping, pass through data visualization, it can be on the basis of water conservancy big data overall cognitive, show the development trend of dynamic high dimensional data, to which continually changing data are carried out Situation Assessment and be showed, such as visualization emergency response of extreme weather etc..The present invention realizes the visualization of hydrographic data; convenient for grasping water resource and water resources development, utilization and conservation status in detail in time; water resource change feature and rule are accurately held; incorporate a large amount of basic data; good data can be provided for water conservancy decision-maker to support, and there is good data interaction.
Description
Technical field
The invention belongs to hydrologic management technical fields, and in particular to a kind of Hydrological Data Analysis and displaying based on cloud computing
The design of method.
Background technique
Currently, commonly showing to the analysis of hydrographic data, mainly certain section of river/river water quality is analyzed,
Such as the indexs such as ammonia nitrogen, total phosphorus are analyzed, change procedure curve is provided for analysis result, and with histogram, pie chart, column
The various ways display data such as table.Common hydrographic data includes that water level, flow velocity, flow, water temperature, silt content, ice slush and water quality are several
A important factor, data structure very disunity.In the prior art usually based on manual analysis, in addition analytic process is non-
It is structural and uncertain, so be not easy to form fixed analysis process or mode, be difficult to call in data in application system into
Row analysis mining.In magnanimity hydrographic data association analysis, since involved information is more dispersed, by powerful
Visualized data analysis platform, can indirect labor's operation data are associated analysis, and make and completely analyze chart.
Summary of the invention
The purpose of the present invention is to propose to a kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing, by means of cloud meter
It calculates, describes the hierarchical relationship of various hydrographic data nodes by correlation models, intuitively show between various hydrographic datas
Relationship.
The technical solution of the present invention is as follows: a kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing, including following step
It is rapid:
S1, distributed data base HBase is constructed in cloud computing management platform OPENSTACK, and hydrographic data is stored
Into in distributed data base HBase.
S2, data model libraries are constructed in cloud computing management platform OPENSTACK, data normalization model is stored into number
According in model library, and establish the data mapping relations of each data normalization model Yu data Source drive.
S3, in conjunction with WEB front-end visualization technique and Online Map service technology, construct visualization human-computer interaction in terminal
Interface.
S4, according to decision-maker visualization human-computer interaction interface selection, decision-maker is obtained from data model libraries
Required data normalization model, and the details of the data normalization model are shown in visualization human-computer interaction interface.
S5, according to decision-maker visualization human-computer interaction interface selection, call and determine from distributed data base HBase
Hydrographic data needed for plan personnel combines GIS platform as calculating parameter, by calculating parameter in visualization human-computer interaction interface
It is shown on the map of display.
S6, the data normalization model for the calculating parameter input step S4 selection that step S5 is selected is calculated, and will
Calculated result is graphically shown in visualization human-computer interaction interface.
Further, the distributed data base HBase in step S1 is the NoSQL database based on column storage.
Further, the data normalization model in step S2 includes water safety appraisal model, sustainable utilization of water resource
Evaluation model and water resource water environment prediction model.
Further, water safety appraisal model specifically:
Evaluation points are chosen on the basis of analyzing influence water quality factors, establish the projection pursuit analysis mould of water quality assessment
Type, and projection pursuit analysis model is optimized using particle swarm algorithm, by the projection pursuit analysis model application after optimization
In the evaluation and sequence of quality of river water.
Further, the projection pursuit analysis model of water quality assessment is established method particularly includes:
A1, the projection sample data x that water quality assessment is established according to water quality assessment standardijAnd corresponding grade y (i)；Its
Middle i indicates i-th of sample, and j indicates j-th of index, i=1,2 ..., n, j=1,2 ..., p, n be sample size, p is water quality
The index number of evaluation.
A2, according to projection sample data xijIt calculates projection value Z (i):
Wherein ajIndicate the unit length on j-th of index projecting direction.
A3, projection target function is established according to projection value Z (i):
WhereinIndicate the standard deviation of projection value, EZIndicate the mean value of projection value Z (i),Indicate that projection value obtains Local standard deviation, R is local density's windows radius, rikIndicate sample i and sample
The distance between this k projection value, u () indicate unit-step function.
A4, optimization projection target function obtain best projection by solving projection target function greatest problem max (Q (a))
Direction:And best projection value Z is determined according to best projection directionm(i)。
A5, according to best projection value Zm(i) and the distribution of grade y (i) determines water grade evaluation criterion matrix, thus structure
Build the projection pursuit analysis model of water quality assessment.
Further, projection pursuit analysis model is optimized using particle swarm algorithm method particularly includes:
B1, using the water grade evaluation criterion matrix in step A5 as objective function.
B2, building penalty function:
Min F (x, r)=min { f (x)+r*P (x) } (3)
Wherein r is penalty factor, and f (x) is the objective function that penalty term is not added, and P (x) is penalty.
B3, the projection pursuit analysis model according to the penalty function in objective function solution procedure B2, after being optimized.
Further, Evaluation Water Resources Sustainable Utilization model specifically:
C1, according to the projection sample data x in the projection pursuit analysis model of water quality assessmentij, determine i-th of grade jth
The lower limit value a* (i, j) and upper limit value b* (i, j) of a index constant interval.
C2, sample data x is being projectedijMiddle selection njA master sample value x (k, j) simultaneously carries out nondimensionalization processing to it.
C3, the distance D for calculating each master sample x (k, j) and [a* (i, j), b* (i, j)]k,i:
Wherein di,j,kIndicate that x (k, j) is more than the absolute value of [a* (i, j), b* (i, j)], if x (k, j) is in [a* (i, j), b*
(i, j)] in section, then di,j,kIt is 0；I=1,2 ..., ni；J=1,2 ..., nj；K=1,2 ..., nj, niFor evaluation criterion
Number of levels.
wjFor weight coefficient, method is determined are as follows:
The importance of each index is compared two-by-two, establishes Fuzzy Complementary Judgment Matrices A=(ahj), wherein ahjIndicate projection
Index x in sample datahBetter than index xjDegree.
If A has crash consistency, have:
If A does not have crash consistency, amendment A is added, revised B=(b is obtainedhj), wherein bhjAfter indicating amendment
Project index x in sample datahBetter than index xjDegree, and have:
Wherein CIC () indicates coincident indicator function, and solution formula (5) or formula (6) obtain weight coefficient wj。
C4, according to distance Dk,iEach master sample x (k, j) is calculated to the relative defects value of the i-th standard class ideal interval
rk,i:
Wherein q indicates that the inverse of comentropy destination item weight, p are the constant not equal to 1.
C5, according to relative defects value rk,iSustainable utilization of water resource grade point h (k) is calculated:
The sustainable use of water resource is evaluated using sustainable use grade point h (k).
Further, water resource water environment prediction model includes the Runoff Forecast of the feedforward neural network based on TABU search
The River Sediment Carrying Capacity prediction model of model and support vector machines.
The Runoff Predicting Model of feedforward neural network based on TABU search specifically:
D1,3 layers of feedforward neural network for constructing 4 input nodes, 7 hidden nodes and 1 output node, and using taboo
Searching algorithm optimizes feedforward neural network parameter.
D2, the rivers hydrographic data for choosing history N will using the rivers hydrographic data of wherein preceding P as Primary Stage Data
The rivers hydrographic data of N-P is as inspection data after wherein.
D3, the predictive factor input feedforward neural network in Primary Stage Data and inspection data is handled, obtains runoff
Predicted value；The predictive factor includes previous total rainfall per year, the previous year monthly average zonal circulation index, the previous year average radial
Circulation index and the previous year solar radio radiation flow.
The River Sediment Carrying Capacity prediction model of support vector machines specifically:
According to regression support vector machine principle, using flow rate of water flow V, silt-settling velocity w and than dropping J as input vector, by water
Sand holding ability S is flowed as object vector, establishes the River Sediment Carrying Capacity prediction model based on support vector machines, River Sediment Carrying Capacity is carried out
Prediction.
The beneficial effects of the present invention are: the present invention shows it by way of combining space-time data and geographic mapping
The relevant mode of room and time and rule can be opened up by data visualization on the basis of water conservancy big data overall cognitive
Show the development trend of dynamic high dimensional data, so that continually changing data are carried out Situation Assessment and be showed, such as extreme weather
Visualization emergency response etc..The present invention realizes the visualization of hydrographic data, convenient for grasping water resource and water money in detail in time
Source exploitation, utilization and conservation status, have accurately held water resource change feature and rule, have incorporated a large amount of basic data, energy
Good data enough are provided for water conservancy decision-maker to support, and there is good data interaction.
Detailed description of the invention
Fig. 1 show a kind of Hydrological Data Analysis and methods of exhibiting process based on cloud computing provided in an embodiment of the present invention
Figure.
Specific embodiment
Carry out detailed description of the present invention illustrative embodiments with reference to the drawings.It should be appreciated that shown in attached drawing and
The embodiment of description is only exemplary, it is intended that is illustrated the principle and spirit of the invention, and is not limited model of the invention
It encloses.
The embodiment of the invention provides a kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing, as shown in Figure 1, packet
Include following steps S1-S6:
S1, distributed data base HBase is constructed in cloud computing management platform OPENSTACK, and hydrographic data is stored
Into in distributed data base HBase.
In the embodiment of the present invention, cloud computing platform is built using the cloud computing management platform OPENSTACK of open source, is responsible for each
Publication and scheduling of storage, the service of class hydrographic data etc..OPENSTACK is integrated with multiple cores and extension project, Suo Youmo
Service call is realized by standardized API between block sub-project, for efficient storage and analysis magnanimity hydrology time sequence
Column data is built based on bottom cloud platform and new distribution type database HBase (Hadoop Database), and system constructs
The hydrology integrates distributed data base.HBase is the NoSQL database based on column storage, the comprehensive distributed data base of the building hydrology
Be conducive to real-time or quickly handle more places, multi -index decision support issue, and realizes the close of data and data model libraries
In conjunction with, make accurate measurements and using hydrographic data basis.
S2, data model libraries are constructed in cloud computing management platform OPENSTACK, data normalization model is stored into number
According in model library, and establish the data mapping relations of each data normalization model Yu data Source drive.
Various types of data standardized model is to carry out integrated design to each hydrographic data, by providing all kinds of hydrographic datas
The data mapping function of standardized model and data Source drive, so that each come from Hydrology department, water administration authorities, work
All kinds of hydrographic datas of the departments such as industry and relevant industries department, water conservancy environmental protection will effectively integrate together, be conducive to hereafter to sea
Measure the excavation and statistical forecast of hydrographic data.Water conservancy big data analysis generally refers to carry out data using distributed computing cluster
Processing, excavation and visualized operation etc., select Storm to use the processing model of message flow, message is once when doing hydrological analysis
Generation begins to transmit and handle.By to water level, rainfall, work feelings, underground water, water quality, ponding, dam safety, water supply and row
The real-time processing of the data such as water can analyze flood risk, carry out early warning to urban waterlogging, thus anti-for the public
Flood mitigation provides socialized service system.
S3, in conjunction with WEB front-end visualization technique and Online Map service technology, construct visualization human-computer interaction in terminal
Interface.The thematic figure and data mark of river trend and river moisture storage capacity and water level line may be implemented in visualization human-computer interaction interface
The integrated and visual interactive manipulation of standardization model improves data processing by visualized map dynamic configuration model parameter
Efficiency.
S4, according to decision-maker visualization human-computer interaction interface selection, decision-maker is obtained from data model libraries
Required data normalization model, and the details of the data normalization model are shown in visualization human-computer interaction interface.
Decision-maker can be by visualizing human-computer interaction interface dynamic select data normalization model, and system passes through reading
The data of cloud computation data center obtain the model information in data model libraries, then show on terminal interface, so that decision
Personnel can according to need the corresponding data normalization model of selection.After decision-maker selects data normalization model, system
It can be in the specifying information of visualization human-computer interaction interface display model.
S5, according to decision-maker visualization human-computer interaction interface selection, call and determine from distributed data base HBase
Hydrographic data needed for plan personnel combines GIS platform as calculating parameter, by calculating parameter in visualization human-computer interaction interface
It is shown on the map of display.
Decision-maker can dynamic interactive selection participates in the parameter calculated in real time according to the map, will by Map Services
Monitoring point hydrographic data moves towards live thematic maps with river and links together, and shows that monitoring point is joined with the formal intuition of map
Number.Show that monitoring point information, Map Services provide online river fact figure browsing, supports the history in observation point on map
Data statistic analysis shows, while supporting roaming zoom operations, and decision-maker can be by browsing map quickly on map
Monitoring point is selected, the monitoring point on map is clicked and obtains related monitoring parameters, then chosen for data normalization model and calculate ginseng
Number (independent variable and dependent variable).Meanwhile visualization human-computer interaction interface can dynamically show the ginseng that user selected in table
Several or data, the data that real-time display decision-maker wants.
S6, the data normalization model for the calculating parameter input step S4 selection that step S5 is selected is calculated, and will
Calculated result is graphically shown in visualization human-computer interaction interface.
In the embodiment of the present invention, the data normalization model in step S2 includes that water safety appraisal model, water resource can be held
Continuous Utilization assessment model and water resource water environment prediction model.
(1) water safety appraisal model specifically:
On the basis of analyzing influence water quality factors, BOD5 (five-day BOD), CODcr (chemical oxygen demand are chosen
Amount), petroleum-type, the principal elements such as volatile phenol establish the projection pursuit analysis model of water quality assessment as evaluation points, and use
Particle swarm algorithm optimizes projection pursuit analysis model, and the projection pursuit analysis model after optimization is applied to quality of river water
Evaluation and sequence.
In the embodiment of the present invention, the specific method for establishing the projection pursuit analysis model of water quality assessment includes the following steps A1
~A5:
A1, the projection sample data x that water quality assessment is established according to water quality assessment standardijAnd corresponding grade y (i)；Its
Middle i indicates i-th of sample, and j indicates j-th of index, i=1,2 ..., n, j=1,2 ..., p, n be sample size, p is water quality
The index number of evaluation.
A2, according to projection sample data xijIt calculates projection value Z (i):
Wherein ajIndicate the unit length on j-th of index projecting direction.
A3, projection target function is established according to projection value Z (i):
WhereinIndicate the standard deviation of projection value, EZIndicate the mean value of projection value Z (i),Indicate that projection value obtains Local standard deviation, R is local density's windows radius, rikIndicate sample i and sample
The distance between this k projection value, u () indicate unit-step function.
A4, optimization projection target function obtain best projection by solving projection target function greatest problem max (Q (a))
Direction:And best projection value Z is determined according to best projection directionm(i)。
A5, according to best projection value Zm(i) and the distribution of grade y (i) determines water grade evaluation criterion matrix, thus structure
Build the projection pursuit analysis model of water quality assessment.
B1~B3 is included the following steps using the specific method that particle swarm algorithm optimizes projection pursuit analysis model:
B1, using the water grade evaluation criterion matrix in step A5 as objective function.
B2, building penalty function:
Min F (x, r)=min { f (x)+r*P (x) } (3)
Wherein r is penalty factor, and f (x) is the objective function that penalty term is not added, and P (x) is penalty.
B3, the projection pursuit analysis model according to the penalty function in objective function solution procedure B2, after being optimized.
(2) Evaluation Water Resources Sustainable Utilization model has mainly used the water based on entropy and FAHP (Fuzzy AHP)
Resources fuzzy overall evaluation new model (EFAHP.FCEM), specifically includes following steps C1~C5:
C1, according to the projection sample data x in the projection pursuit analysis model of water quality assessmentij, determine i-th of grade jth
The lower limit value a* (i, j) and upper limit value b* (i, j) of a index constant interval.
C2, sample data x is being projectedijMiddle selection njA master sample value x (k, j) simultaneously carries out nondimensionalization processing to it.
C3, the distance D for calculating each master sample x (k, j) and [a* (i, j), b* (i, j)]k,i:
Wherein di,j,kIndicate that x (k, j) is more than the absolute value of [a* (i, j), b* (i, j)], if x (k, j) is in [a* (i, j), b*
(i, j)] in section, then di,j,kIt is 0；I=1,2 ..., ni；J=1,2 ..., nj；K=1,2 ..., nj, niFor evaluation criterion
Number of levels.
wjFor weight coefficient, method is determined are as follows:
The importance of each index is compared two-by-two, establishes Fuzzy Complementary Judgment Matrices A=(ahj), wherein ahjIndicate projection
Index x in sample datahBetter than index xjDegree.
If A has crash consistency, have:
If A does not have crash consistency, amendment A is added, revised B=(b is obtainedhj), wherein bhjAfter indicating amendment
Project index x in sample datahBetter than index xjDegree, and have:
Wherein CIC () indicates coincident indicator function, as long as its value is not more than the 90% of confidence level RIC (n),
The function has consistent satisfaction property, and wherein RIC (n) is with stochastic simulation method respectively to 3~n Random-fuzzy Complementary Judgement Matrix
It acquires.
Solution formula (5) or formula (6) obtain weight coefficient wj。
C4, according to distance Dk,iEach master sample x (k, j) is calculated to the relative defects value of the i-th standard class ideal interval
rk,i:
Wherein q indicates that the inverse of comentropy destination item weight, p are the constant not equal to 1.
C5, according to relative defects value rk,iSustainable utilization of water resource grade point h (k) is calculated:
The sustainable use of water resource is evaluated using sustainable use grade point h (k).
(3) water resource water environment prediction model include the feedforward neural network based on TABU search Runoff Predicting Model and
The River Sediment Carrying Capacity prediction model of support vector machines.
Wherein, the Runoff Predicting Model of the feedforward neural network based on TABU search specifically includes following steps D1~D3:
D1,3 layers of feedforward neural network for constructing 4 input nodes, 7 hidden nodes and 1 output node, and using taboo
Searching algorithm optimizes feedforward neural network parameter.
D2, the rivers hydrographic data for choosing history N will using the rivers hydrographic data of wherein preceding P as Primary Stage Data
The rivers hydrographic data of N-P is as inspection data after wherein.
D3, the predictive factor input feedforward neural network in Primary Stage Data and inspection data is handled, obtains runoff
Predicted value；The predictive factor includes previous total rainfall per year, the previous year monthly average zonal circulation index, the previous year average radial
Circulation index and the previous year solar radio radiation flow.
The River Sediment Carrying Capacity prediction model of support vector machines specifically:
According to regression support vector machine principle, using flow rate of water flow V, silt-settling velocity w and than dropping J as input vector, by water
Sand holding ability S is flowed as object vector, establishes the River Sediment Carrying Capacity prediction model based on support vector machines, River Sediment Carrying Capacity is carried out
Prediction.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field
Those of ordinary skill disclosed the technical disclosures can make according to the present invention and various not depart from the other each of essence of the invention
The specific variations and combinations of kind, these variations and combinations are still within the scope of the present invention.
Claims (9)
1. a kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing, which comprises the following steps:
S1, cloud computing management platform OPENSTACK in construct distributed data base HBase, and by hydrographic data store into point
In cloth database HBase；
S2, data model libraries are constructed in cloud computing management platform OPENSTACK, data normalization model is stored into data mould
In type library, and establish the data mapping relations of each data normalization model Yu data Source drive；
S3, in conjunction with WEB front-end visualization technique and Online Map service technology, construct visualization human-computer interaction circle in terminal
Face；
S4, according to decision-maker visualization human-computer interaction interface selection, from data model libraries obtain decision-maker needed for
Data normalization model, and show the details of the data normalization model in visualization human-computer interaction interface；
S5, according to decision-maker visualization human-computer interaction interface selection, call policymaker from distributed data base HBase
Hydrographic data needed for member combines GIS platform as calculating parameter, and calculating parameter is shown in visualization human-computer interaction interface
Map on be shown；
S6, the data normalization model for the calculating parameter input step S4 selection that step S5 is selected is calculated, and will calculated
As a result it is graphically shown in visualization human-computer interaction interface.
2. Hydrological Data Analysis according to claim 1 and methods of exhibiting, which is characterized in that the distribution in the step S1
Formula database HBase is the NoSQL database based on column storage.
3. Hydrological Data Analysis according to claim 1 and methods of exhibiting, which is characterized in that the data in the step S2
Standardized model includes water safety appraisal model, Evaluation Water Resources Sustainable Utilization model and water resource water environment prediction model.
4. Hydrological Data Analysis according to claim 3 and methods of exhibiting, which is characterized in that the water safety appraisal model
Specifically:
Evaluation points are chosen on the basis of analyzing influence water quality factors, establish the projection pursuit analysis model of water quality assessment, and
The projection pursuit analysis model is optimized using particle swarm algorithm, the projection pursuit analysis model after optimization is applied to
The evaluation and sequence of quality of river water.
5. Hydrological Data Analysis according to claim 4 and methods of exhibiting, which is characterized in that described to establish water quality assessment
Projection pursuit analysis model method particularly includes:
A1, the projection sample data x that water quality assessment is established according to water quality assessment standardijAnd corresponding grade y (i)；Wherein i table
Show i-th of sample, j indicates j-th of index, i=1,2 ..., n, j=1,2 ..., p, n be sample size, p is water quality assessment
Index number；
A2, according to projection sample data xijIt calculates projection value Z (i):
Wherein ajIndicate the unit length on j-th of index projecting direction；
A3, projection target function is established according to projection value Z (i):
WhereinIndicate the standard deviation of projection value, EZIndicate the mean value of projection value Z (i),Indicate that projection value obtains Local standard deviation, R is local density's windows radius, rikIndicate sample i and sample
The distance between this k projection value, u () indicate unit-step function；
A4, optimization projection target function obtain best projection side by solving projection target function greatest problem max (Q (a))
To:And best projection value Z is determined according to best projection directionm(i)；
A5, according to best projection value Zm(i) and the distribution of grade y (i) determines water grade evaluation criterion matrix, to construct water
The projection pursuit analysis model of matter evaluation.
6. Hydrological Data Analysis according to claim 5 and methods of exhibiting, which is characterized in that described to use particle swarm algorithm
The projection pursuit analysis model is optimized method particularly includes:
B1, using the water grade evaluation criterion matrix in step A5 as objective function；
B2, building penalty function:
MinF (x, r)=min { f (x)+r*P (x) } (3)
Wherein r is penalty factor, and f (x) is the objective function that penalty term is not added, and P (x) is penalty；
B3, the projection pursuit analysis model according to the penalty function in objective function solution procedure B2, after being optimized.
7. Hydrological Data Analysis according to claim 4 and methods of exhibiting, which is characterized in that the evaluation points include
BOD5, CODcr, petroleum-type and volatile phenol.
8. Hydrological Data Analysis according to claim 5 and methods of exhibiting, which is characterized in that the sustainable benefit of water resource
With evaluation model specifically:
C1, according to the projection sample data x in the projection pursuit analysis model of water quality assessmentij, determine j-th of i-th of grade finger
Mark the lower limit value a* (i, j) and upper limit value b* (i, j) of constant interval；
C2, sample data x is being projectedijMiddle selection njA master sample value x (k, j) simultaneously carries out nondimensionalization processing to it；
C3, the distance D for calculating each master sample x (k, j) and [a* (i, j), b* (i, j)]k,i:
Wherein di,j,kIndicate x (k, j) be more than [a* (i, j), b* (i, j)] absolute value, if x (k, j) [a* (i, j), b* (i,
J)] in section, then di,j,kIt is 0；I=1,2 ..., ni；J=1,2 ..., nj；K=1,2 ..., nj, niFor evaluation criterion etc.
Number of stages；wjFor weight coefficient, method is determined are as follows:
The importance of each index is compared two-by-two, establishes Fuzzy Complementary Judgment Matrices A=(ahj), wherein ahjIndicate projection sample number
According to middle index xhBetter than index xjDegree；
If A has crash consistency, have:
If A does not have crash consistency, amendment A is added, revised B=(b is obtainedhj), wherein bhjIt is projected after indicating amendment
Index x in sample datahBetter than index xjDegree, and have:
Wherein CIC () indicates coincident indicator function, and solution formula (5) or formula (6) obtain weight coefficient wj；
C4, according to distance Dk,iEach master sample x (k, j) is calculated to the relative defects value r of the i-th standard class ideal intervalk,i:
Wherein q indicates that the inverse of comentropy destination item weight, p are the constant not equal to 1；
C5, according to relative defects value rk,iSustainable utilization of water resource grade point h (k) is calculated:
The sustainable use of water resource is evaluated using sustainable use grade point h (k).
9. Hydrological Data Analysis according to claim 3 and methods of exhibiting, which is characterized in that the water resource water environment is pre-
The River Sediment Carrying Capacity for surveying the Runoff Predicting Model that model includes the feedforward neural network based on TABU search and support vector machines is pre-
Survey model；
The Runoff Predicting Model of the feedforward neural network based on TABU search specifically:
D1,3 layers of feedforward neural network for constructing 4 input nodes, 7 hidden nodes and 1 output node, and use TABU search
Algorithm optimization feedforward neural network parameter；
D2, the rivers hydrographic data for choosing history N will wherein using the rivers hydrographic data of wherein preceding P as Primary Stage Data
The rivers hydrographic data of N-P is as inspection data afterwards；
D3, the predictive factor input feedforward neural network in Primary Stage Data and inspection data is handled, obtains Runoff Forecast
Value；The predictive factor includes previous total rainfall per year, the previous year monthly average zonal circulation index, the previous year mean meridional circulation
Index and the previous year solar radio radiation flow；
The River Sediment Carrying Capacity prediction model of the support vector machines specifically:
Water flow is held under the arm using flow rate of water flow V, silt-settling velocity w and than dropping J as input vector according to regression support vector machine principle
Husky power S establishes the River Sediment Carrying Capacity prediction model based on support vector machines as object vector, carries out to River Sediment Carrying Capacity pre-
It surveys.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810964010.5A CN109271465B (en) | 2018-08-23 | 2018-08-23 | Hydrological data analysis and display method based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810964010.5A CN109271465B (en) | 2018-08-23 | 2018-08-23 | Hydrological data analysis and display method based on cloud computing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109271465A true CN109271465A (en) | 2019-01-25 |
| CN109271465B CN109271465B (en) | 2020-09-29 |
Family
ID=65154101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810964010.5A Expired - Fee Related CN109271465B (en) | 2018-08-23 | 2018-08-23 | Hydrological data analysis and display method based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271465B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135555A (en) * | 2019-03-25 | 2019-08-16 | 东莞理工学院 | A kind of feedforward neural network prediction model of water resource carrying capacity |
| CN110837625A (en) * | 2019-11-07 | 2020-02-25 | 华能曹妃甸港口有限公司 | Port operation control method and device |
| CN111241067A (en) * | 2020-01-14 | 2020-06-05 | 智恒科技股份有限公司 | Water affair big data mining modeling management method, device, equipment and medium |
| CN112019607A (en) * | 2020-08-14 | 2020-12-01 | 华东师范大学 | Intelligent farm comprehensive control method and system based on visual cloud platform |
| CN117648887A (en) * | 2024-01-29 | 2024-03-05 | 航天宏图信息技术股份有限公司 | Hydrologic hydrodynamic processing method, device, equipment and medium based on cloud computing |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831175A (en) * | 2012-07-30 | 2012-12-19 | 河海大学 | Method for establishing water conservancy service Web business library based on cloud platform |
| US20130080484A1 (en) * | 2011-06-06 | 2013-03-28 | International Business Machines Corporation | Rapidly deploying virtual database applications using data model analysis |
| WO2013052237A2 (en) * | 2011-09-08 | 2013-04-11 | Attagene, Inc. | Systems and methods for assay of bio-contaminants in water |
| KR20170127087A (en) * | 2016-05-10 | 2017-11-21 | 주식회사 알엔에이솔루션 | Method for Management of River Facility through River Diagnosis and System thereof |
| CN107463614A (en) * | 2017-06-30 | 2017-12-12 | 中国科学院寒区旱区环境与工程研究所 | Eco-hydrological Model structure and parameter simulation method based on modeling framework |
| CN107564257A (en) * | 2017-08-30 | 2018-01-09 | 商洛学院 | A kind of hydrography data acquisition display systems |
| KR101824330B1 (en) * | 2016-09-21 | 2018-02-01 | 한국수자원공사 | Providing device for water quality information and providing system for water quality of an apartment house using the providing device |
| CN107705084A (en) * | 2016-08-08 | 2018-02-16 | 张永平 | A kind of hydrometric station data management system based on GIS |
-
2018
- 2018-08-23 CN CN201810964010.5A patent/CN109271465B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130080484A1 (en) * | 2011-06-06 | 2013-03-28 | International Business Machines Corporation | Rapidly deploying virtual database applications using data model analysis |
| WO2013052237A2 (en) * | 2011-09-08 | 2013-04-11 | Attagene, Inc. | Systems and methods for assay of bio-contaminants in water |
| CN102831175A (en) * | 2012-07-30 | 2012-12-19 | 河海大学 | Method for establishing water conservancy service Web business library based on cloud platform |
| KR20170127087A (en) * | 2016-05-10 | 2017-11-21 | 주식회사 알엔에이솔루션 | Method for Management of River Facility through River Diagnosis and System thereof |
| CN107705084A (en) * | 2016-08-08 | 2018-02-16 | 张永平 | A kind of hydrometric station data management system based on GIS |
| KR101824330B1 (en) * | 2016-09-21 | 2018-02-01 | 한국수자원공사 | Providing device for water quality information and providing system for water quality of an apartment house using the providing device |
| CN107463614A (en) * | 2017-06-30 | 2017-12-12 | 中国科学院寒区旱区环境与工程研究所 | Eco-hydrological Model structure and parameter simulation method based on modeling framework |
| CN107564257A (en) * | 2017-08-30 | 2018-01-09 | 商洛学院 | A kind of hydrography data acquisition display systems |
Non-Patent Citations (2)
| Title |
|---|
| 刘孙俊等: "基于WEBGIS的气象水文综合服务平台", 《科技传播》 * |
| 吕爱锋等: "基于GIS的分布式水文模型系统开发研究", 《中国科学院研究生院学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135555A (en) * | 2019-03-25 | 2019-08-16 | 东莞理工学院 | A kind of feedforward neural network prediction model of water resource carrying capacity |
| CN110135555B (en) * | 2019-03-25 | 2021-02-26 | 东莞理工学院 | Forward neural network prediction model for water resource bearing capacity |
| CN110837625A (en) * | 2019-11-07 | 2020-02-25 | 华能曹妃甸港口有限公司 | Port operation control method and device |
| CN111241067A (en) * | 2020-01-14 | 2020-06-05 | 智恒科技股份有限公司 | Water affair big data mining modeling management method, device, equipment and medium |
| CN111241067B (en) * | 2020-01-14 | 2022-05-03 | 智恒科技股份有限公司 | Water affair big data mining modeling management method, device, equipment and medium |
| CN112019607A (en) * | 2020-08-14 | 2020-12-01 | 华东师范大学 | Intelligent farm comprehensive control method and system based on visual cloud platform |
| CN117648887A (en) * | 2024-01-29 | 2024-03-05 | 航天宏图信息技术股份有限公司 | Hydrologic hydrodynamic processing method, device, equipment and medium based on cloud computing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109271465B (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271465A (en) | A kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing | |
| Harrison et al. | Foundations for smarter cities | |
| McManamay | Quantifying and generalizing hydrologic responses to dam regulation using a statistical modeling approach | |
| CN107610021A (en) | The comprehensive analysis method of environmental variance spatial and temporal distributions | |
| Park et al. | The structure and knowledge flow of building information modeling based on patent citation network analysis | |
| CN113434565A (en) | Water conservancy flood control drought and waterlogging prevention comprehensive disaster reduction platform system based on CIM platform | |
| KR101341437B1 (en) | Method for multi criteria assessment of flood risk | |
| CN112182234A (en) | Drainage basin flood control planning data knowledge graph construction method | |
| Noori et al. | A reliable GIS-based FAHP-FTOPSIS model to prioritize urban water supply management scenarios: A case study in semi-arid climate | |
| Bruno et al. | Location and GIS | |
| Gourbesville et al. | Decision support system architecture for real-time water management | |
| CN109829607A (en) | A kind of integrated evaluating method of Sustainable Development for Urban Traffic System | |
| CN114492233B (en) | Watershed water simulation method based on webGIS platform and considering comprehensive utilization requirements | |
| CN117236673B (en) | Urban water network multi-scale flood control and drainage combined optimization scheduling method and system | |
| Jalili et al. | Multi-objective Optimization of water resources in real time based on integration of NSGA-II and support vector machines | |
| Majumder et al. | Real-time monitoring of power production in modular hydropower plant: most significant parameter approach | |
| Zhang et al. | Evaluating the socioeconomic value of urban underground space in Kunming, China, Using the entropy method and exponential smoothing prediction | |
| CN104794328A (en) | Hydroelectric development ecological suitability evaluation method with water footprint taken into consideration | |
| Nutkiewicz et al. | Exploring the integration of simulation and deep learning models for urban building energy modeling and retrofit analysis | |
| Kong et al. | Urban building energy modeling (UBEM): a systematic review of challenges and opportunities | |
| Zhu et al. | Rural road network planning based on 5g and traffic big data | |
| Jin et al. | A metadata framework for asset management decision support: a water infrastructure case study | |
| Jin et al. | Optimization of sustainable land use management in water source area using water quality dynamic monitoring model | |
| CN101950324A (en) | River-health intelligent diagnosis method and equipment | |
| Zhang et al. | Urban water resources allocation and shortage risk mapping with support vector machine method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200929 Termination date: 20210823 |