CN107192802B - Shared direct drinking on-line water quality monitoring method and system - Google Patents
Shared direct drinking on-line water quality monitoring method and system Download PDFInfo
- Publication number
- CN107192802B CN107192802B CN201710500789.0A CN201710500789A CN107192802B CN 107192802 B CN107192802 B CN 107192802B CN 201710500789 A CN201710500789 A CN 201710500789A CN 107192802 B CN107192802 B CN 107192802B
- Authority
- CN
- China
- Prior art keywords
- water quality
- sample
- water
- water tank
- grnn
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
Abstract
The invention discloses a kind of shared direct drinking on-line water quality monitoring method, comprise the following steps:S110 establishes neutral net input sample collection according to the control parameter that water quality is influenceed in constant water tank;S120 establishes neutral net output sample set according to water quality index in the constant water tank measured in real time;Input sample collection and output sample set are normalized S130, obtain normalization sample set;S140 is according to the normalization sample set structure GRNN network models;S150 obtains network spreading factor according to the GRNN network models;S160 realizes real-time estimate to the influence factor of water quality in the constant water tank of real-time change;According to constant roof tank water quality real-time estimate, the adaptive dynamic self study on-line monitoring of shared direct drinking water quality is realized.The present invention provide the user it is a kind of it is quick, healthy, easily share direct-drinking device and system, can not only ensure conveniently to drink drinking water, and be truly realized healthy, efficient and convenient drinking-water, it is final to realize the adaptive dynamic learning on-line detecting system of shared direct drinking.
Description
Technical field
The present invention relates to mobile internet service field, more particularly to a kind of shared direct drinking on-line water quality monitoring method and
System.
Background technology
With the improvement of living standards, economic rapid development, the life idea of high-quality health increasingly obtains people's
Favor.Health, convenience particular for daily drunk water require more and more higher, and the current drinking water mode of in the market includes straight
Drinking-water and barreled mineral water, wherein barreled mineral water quality, capacity, price is uneven, under existing economic system, barreled
The quality of water can not obtain safe and healthy guarantee, and in the market has the phenomenon of a large amount of barreled mineral waters " adulterating ", not only deposited
In excessive huge profit and underproof barreled mineral water potential threat can be brought to the health of the people.Simultaneously, in fast pace
City life in, efficient time utilization causes convenience requirement more and more higher of the people to service product.
The content of the invention
In view of this, it is an object of the invention to provide a kind of shared direct drinking on-line water quality monitoring method and system.With
Solution is convenient, healthy, efficiently shares direct drinking drinks problem, ensures the water quality health of drinking water, realizes shared direct drinking water
Matter monitoring in real time realizes shared direct drinking intelligent management with changing in real time.
An object of the present invention is achieved through the following technical solutions, and shares direct drinking monitoring water quality on line side
Method, comprise the following steps:
S110 establishes neutral net input sample collection according to the control parameter that water quality is influenceed in constant water tank;
S120 establishes neutral net output sample set according to water quality index in the constant water tank measured in real time;
Input sample collection and output sample set are normalized S130, obtain normalization sample set;
S140 is according to the normalization sample set structure GRNN network models;
S150 obtains network spreading factor according to the GRNN network models;
S160 realizes real-time estimate to the influence factor of water quality in the constant water tank of real-time change;According to constant roof tank water quality
Real-time estimate, realize the adaptive dynamic self study on-line monitoring of shared direct drinking water quality.
Further, pre-treatment step is also included after the step S120, the pre-treatment step is:By the input sample of structure
This collection carries out pivot extraction, and obtains new samples collection.
Further, the control parameter of water quality is influenceed in the constant water tank to be included, it is determined that influenceing the influence of water quality in water tank
Factor, the influence factor include:Water temperature in the accumulative water consumption of direct drinking fountain filter core performance, regional id number, direct drinking fountain, water tank
Historical temperature real time data, real-time water tank water outlet on off state.
Further, according to water quality index in the constant water tank measured in real time, neutral net output sample set is established, including:
By regular Quality Inspector's inspection, extract drinking water water sample in water tank and carry out water quality index detection and be real-time transmitted to cloud service
Device, that is, obtain neutral net output sample set.
Further, using pivot analysis algorithm to state variable X (water temperature historical temperature real time data, Real-time Water in water tank
Case water outlet on off state) pivot extraction is carried out, build new state variable X '={ xz1,xz2,L,xzm, X ' is m state
Pivot component, the dimension of each state pivot component are identical with the quantity of the sample.
Further, GRNN model equations are as follows:
Wherein,Represent all sample observations YiWeighted average;YiRepresent observation;X network inputs variables;Xi
Represent learning sample corresponding to i-th of neuron;σ represents network spreading factor.
Further, it is modeled using GRNN algorithms, the process for obtaining network spreading factor comprises the following steps:
The first step:Network spreading factor σ span [σ is setmin,σmax], σ value separation delta h is set;
Second step:Take σ0=σmin, using training samples of the sample set A as GRNN models, B utilizes as test sample
The GRNN model prediction test samples B of foundation all estimatesCalculate test sample B predicted value and actual value
Error E1, and make Emin=E1, it is A to make optimum training sample set;
3rd step:Take σ0=σmin, using training samples of the sample set B as GRNN models, A utilizes as test sample
The GRNN model prediction test samples A of foundation all estimatesCalculate test sample A predicted value and actual value
Error E2If E2< E1, then E is mademin=E2, it is B to make optimum training sample set;Otherwise E is mademin=E1, optimum training sample set is
A;
4th step:Take σ1=σ0+ Δ h, second step and three step process are repeated, is less than second step or the 3rd if there is E
E in stepmin, then σ1Better than σ0;Otherwise optimal network spreading factor value is still σ0;
5th step:In [σmin,σmax] in take all over all σ values continuous renewal test sample minimum error values, optimum training
Sample set, minimum spread factor.
The second object of the present invention is achieved through the following technical solutions, and shares direct drinking monitoring water quality on line system
System, including selection of control parameter unit, modeling sample pivot extraction unit, normalization sample collection acquiring unit, GRNN models
Construction unit, GRNN prototype network spreading factor acquiring units and constant water tank water quality prediction unit;The selection of control parameter
Unit, select to influence the control parameter of water quality in constant water tank, establish neutral net input sample collection;Modeling sample pivot is extracted
Unit, input sample collection is extracted with PCA pivots, and obtain new sample set;Sample collection acquiring unit is normalized, by PCA
Parameter after pivot extraction is normalized;
GRNN model construction units, build GRNN network models;GRNN prototype network spreading factor acquiring units, use
GRNN is trained, and obtains network spreading factor;
Constant water tank water quality prediction unit, with the GRNN network models having built up to carrying out constant water tank water quality index
Prediction.
Advantageous effects:
The present invention provide the user it is a kind of it is quick, healthy, easily share direct-drinking device and system, can not only ensure
Drinking water is conveniently drunk, and is truly realized healthy, efficient and convenient drinking-water, it is final to realize that the shared adaptive dynamic learning of direct drinking exists
Line detecting system.
Brief description of the drawings
Fig. 1 shares direct drinking water quality adaptive learning on-line monitoring method schematic flow sheet;
Fig. 2 shares the logical construction schematic diagram of direct drinking water quality adaptive learning on-line monitoring system.
Embodiment
Below with reference to accompanying drawing, the preferred embodiments of the present invention are described in detail;It should be appreciated that preferred embodiment
Only for the explanation present invention, the protection domain being not intended to be limiting of the invention.
As shown in figure 1, shared direct drinking on-line water quality monitoring method provided by the invention comprises the following steps:
S110 establishes neutral net input sample collection according to the control parameter that water quality is influenceed in constant water tank;
S120 establishes neutral net output sample set according to water quality index in the constant water tank measured in real time;
The input sample collection of structure is carried out pivot extraction by S130, and obtains new samples collection;
New samples collection is normalized S140, obtains normalization sample set;
S150 is according to the normalization sample set structure GRNN network models;
S160 obtains network spreading factor according to the GRNN network models;
S170 realizes real-time estimate to the influence factor of water quality in the constant water tank of real-time change;According to constant roof tank water quality
Real-time estimate, realize the adaptive dynamic self study on-line monitoring of shared direct drinking water quality.
Above-mentioned is shared direct drinking on-line water quality monitoring method provided by the invention, in step S110 and step S120,
Water temperature historical temperature real time data, reality in the accumulative water consumption of direct drinking fountain filter core performance, regional id number, direct drinking fountain, water tank
When water outlet of water tank on off state, that is, obtain establish mode input sample;By regular Quality Inspector's inspection, extract in water tank and drink
Water quality index detection (microbiological indicator, toxicological parameters, chemical index, radioactive indicator), and real-time Transmission are carried out with water water sample
To cloud server, that is, obtain model output sample;
Wherein, the control parameter of water quality in constant water tank is influenceed as shown in Table 1 and Table 2:
The parameter of table 1 and symbol table
The parameter of table 2 and symbol table
Wherein, share filter in direct drinking is to the accumulative water consumption of exclusion water in constant water tankIt is accumulative
With the water time
In step s 130, PCA pivots are extracted;Wherein, pivot analysis algorithm carries out pivot extraction, structure to state variable X
Build new state variable X'={ xz1,xz2,L,xzmBe m state pivot component, the dimension of each state pivot component with it is described
The quantity of sample is identical;
In step S140, data prediction.During neural net model establishing, its hidden layer node function is S types
Function, its codomain are [- 1,1];To improve modeling process precision, so the sample of all collections is normalized.
I.e.:The value of consult volume of sample set is mapped in the range of [- 1,1] using linear normalization method, obtains normalized sample set.
In step S150, according to the normalization sample set structure GRNN network models;
GRNN model equations are as follows:
Wherein,Represent all sample observations YiWeighted average;YiRepresent observation;X network inputs variables;Xi
Represent learning sample corresponding to i-th of neuron;σ represents network spreading factor;
In step S160, using the GRNN algorithms to the mass data by being accumulated on cloud server, god is obtained
Through network parameter;The mass data accumulated on cloud server includes, direct drinking fountain filter core performance, regional id number, direct drinking
Machine adds up water consumption, water temperature historical temperature real time data, real-time water tank water outlet on off state in water tank, that is, obtains and establish mould
Type input sample;By regular Quality Inspector's inspection, extracting drinking water water sample progress water quality index detection in water tank, (microorganism refers to
Mark, toxicological parameters, chemical index, radioactive indicator), and be real-time transmitted to cloud server, that is, obtain model output sample;
The mass data stored using GRNN algorithms to cloud server is modeled, and obtains neural network parameter process
In,
The first step:Span [the σ of network spreading factor is setmin,σmax], σ value separation delta h is set;
Second step:Take σ0=σmin, GRNN models are built as training sample using sample set A, B is as test sample, profit
With the GRNN model prediction sampling sets B of foundation all estimatesCalculate test set B predicted value and the mistake of actual value
Poor E1, and make Emin=E1, it is A to make optimum training sample set;
3rd step:Take σ0=σmin, using training samples of the sample set B as GRNN models, A utilizes as test sample
The GRNN model prediction sampling sets A of foundation all estimatesCalculate test set A predicted value and the error of actual value
E2If E2< E1, then and E is mademin=E2, it is B to make optimum training sample set;Otherwise Emin=E1, optimum training sample set is still A;
4th step:Take σ1=σmin+ Δ h, second step and three step process are repeated, be less than second step or the if there is E
E in three stepsmin, then σ1Better than σ0;Otherwise optimal network spreading factor value is still σ0;
5th step:In [σmin,σmax] in take all over all σ values continuous renewal test sample minimum error values, optimum training
Sample set, minimum spread factor.
In step S170, on the basis of known models, influence for water quality in the constant water tank of real-time change because
Element realizes constant roof tank water quality real-time estimate;
Corresponding with the above method, the shared direct drinking monitoring water quality on line system of the present invention and device, Fig. 2 show basis
The embodiment of the present invention shares direct drinking monitoring water quality on line system and device logical construction.
As shown in Fig. 2 shared direct drinking monitoring water quality on line system, including selection of control parameter unit 210, modeling sample
Pivot extraction unit 220, normalization sample collection acquiring unit 230, GRNN model constructions unit 240, GRNN prototype networks expand
Open up factor acquirement unit 250 and constant water tank water quality prediction unit 260;The selection of control parameter unit, selects constant water tank
The interior control parameter for influenceing water quality, establishes neutral net input sample collection;Modeling sample pivot extraction unit, to input sample collection
Extracted with PCA pivots, and obtain new sample set;Sample collection acquiring unit is normalized, the parameter after PCA pivots are extracted is entered
Row normalized;
GRNN model construction units, build GRNN network models;GRNN prototype network spreading factor acquiring units, use
GRNN is trained, and obtains network spreading factor;
Constant water tank water quality prediction unit, with the GRNN network models having built up to carrying out constant water tank water quality index
Wherein according to the selection of control parameter unit 210 of the influence of water quality in constant water tank, parameter includes for prediction:Direct drinking fountain filter core
Energy, regional id number, direct drinking fountain add up water consumption, water temperature historical temperature real time data, real-time water tank water outlet in water tank
On off state, that is, obtain and establish mode input sample;By regular Quality Inspector's inspection, extract drinking water water sample in water tank and enter water-filling
Matter Indexs measure (microbiological indicator, toxicological parameters, chemical index, radioactive indicator), and be real-time transmitted to cloud server, i.e.,
Obtain model output sample;
Wherein, in an embodiment of the present invention, GRNN model constructions unit 240,
GRNN model equations are as follows:
Wherein,Represent all sample observations YiWeighted average;YiRepresent observation;X network inputs variables;Xi
Represent learning sample corresponding to i-th of neuron;σ represents network spreading factor;
The mass data stored using GRNN algorithms to cloud server is modeled, and obtains network spreading factor process
In,
The first step:Span [the σ of network spreading factor is setmin,σmax], σ value separation delta h is set;
Second step:Take σ0=σmin, GRNN models are built as training sample using sample set A, B is as test sample, profit
With the GRNN model prediction sampling sets B of foundation all estimatesCalculate test set B predicted value and the mistake of actual value
Poor E1, and make Emin=E1, it is A to make optimum training sample set;
3rd step:Take σ0=σmin, using training samples of the sample set B as GRNN models, A utilizes as test sample
The GRNN model prediction sampling sets A of foundation all estimatesCalculate test set A predicted value and the error of actual value
E2If E2< E1, then and E is mademin=E2, it is B to make optimum training sample set;Otherwise Emin=E1, optimum training sample set is still A;
4th step:Take σ1=σmin+ Δ h, second step and three step process are repeated, be less than second step or the if there is E
E in three stepsmin, then σ1Better than σ0;Otherwise optimal network spreading factor value is still σ0;
5th step:In [σmin,σmax] in take all over all σ values continuous renewal test sample minimum error values, optimum training
Sample set, minimum spread factor;It is optimal σ values and training to take the σ values under test sample error minimum, training sample set
Sample set.
It was found from technical scheme above, shared direct drinking monitoring water quality on line system and method provided by the invention,
The control parameter that the mass data selection of cloud server accumulation influences water quality in constant water tank is information carrier, utilizes GRNN side
Method excavates input sample, and (direct drinking fountain filter core performance, regional id number, direct drinking fountain add up water consumption, water temperature history in water tank
Temperature real time data, real-time water tank water outlet on off state) and output sample (pass through regular Quality Inspector's inspection, extract water tank
Interior drinking water water sample carries out water quality index detection microbiological indicator, toxicological parameters, chemical index, radioactive indicator) between relation;
Realize the adaptive real-time water quality prediction of dynamic self study of water quality in constant water tank.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, it is clear that those skilled in the art
Member can carry out various changes and modification without departing from the spirit and scope of the present invention to the present invention.So, if the present invention
These modifications and variations belong within the scope of the claims in the present invention and its equivalent technologies, then the present invention is also intended to include these
Including change and modification.
Claims (7)
1. shared direct drinking on-line water quality monitoring method, it is characterised in that:Comprise the following steps:
S110 establishes neutral net input sample collection according to the control parameter that water quality is influenceed in constant water tank;The constant water tank
The interior control parameter for influenceing water quality includes, it is determined that influenceing the influence factor of water quality in water tank, the influence factor includes:Direct drinking fountain
Water temperature historical temperature real time data, real-time water tank go out in the accumulative water consumption of filter core performance, regional id number, direct drinking fountain, water tank
On off state at the mouth of a river;
S120 establishes neutral net output sample set according to water quality index in the constant water tank measured in real time;
Input sample collection and output sample set are normalized S130, obtain normalization sample set;
S140 is according to the normalization sample set structure GRNN network models;
S150 obtains network spreading factor according to the GRNN network models;
S160 realizes real-time estimate to the influence factor of water quality in the constant water tank of real-time change;It is real-time according to constant roof tank water quality
Prediction, realize the adaptive dynamic self study on-line monitoring of shared direct drinking water quality.
2. shared direct drinking on-line water quality monitoring method according to claim 1, it is characterised in that:After the step S120
Also include pre-treatment step, the pre-treatment step is:The input sample collection of structure is subjected to pivot extraction, and obtains new samples
Collection.
3. shared direct drinking on-line water quality monitoring method according to claim 1, it is characterised in that:According to what is measured in real time
Water quality index in constant water tank, neutral net output sample set is established, including:By regular Quality Inspector's inspection, extract in water tank
Drinking water water sample carries out water quality index detection and is real-time transmitted to cloud server, that is, obtains neutral net output sample set.
4. shared direct drinking on-line water quality monitoring method according to claim 2, it is characterised in that:Calculated using pivot analysis
Method carries out pivot extraction to state variable X, builds new state variable X '={ Xz1, Xz2, L, Xzm }, X ' is m state pivot
Component, the dimension of each state pivot component are identical with the quantity of the training sample in input sample.
5. shared direct drinking on-line water quality monitoring method according to claim 1, it is characterised in that:GRNN model equations are such as
Under:
Wherein,Represent all sample observations YiWeighted average;YiRepresent observation;X network inputs variables;XiRepresent
Learning sample corresponding to i-th of neuron;σ represents network spreading factor, NARepresent the number of input sample.
6. shared direct drinking on-line water quality monitoring method according to claim 1, it is characterised in that:Entered using GRNN algorithms
Row modeling, the process for obtaining network spreading factor comprise the following steps:
The first step:Network spreading factor σ span [σ min, σ max] is set, σ value separation delta h is set;
Second step:Take σ0=σmin, using training samples of the sample set A as GRNN models, B utilizes foundation as test sample
GRNN model prediction test samples B all estimatesCalculate test sample B predicted value and the error of actual value
E1, and make Emin=E1, it is A to make optimum training sample set;Wherein σ 0 represents initial network spreading factor, and sample set A is input sample
The 80% of this quantity, test sample B are the 20% of input sample quantity;
3rd step:Take σ0=σmin, using training samples of the sample set B as GRNN models, A utilizes foundation as test sample
GRNN model prediction test samples A all estimatesCalculate test sample A predicted value and the error of actual value
E2If E2< E1, then E is mademin=E2, it is B to make optimum training sample set;Otherwise E is mademin=E1, optimum training sample set is A;
4th step:Take σ1=σ0+ Δ h, second step and three step process are repeated, be less than if there is E in second step or the 3rd step
Emin, then σ1Better than σ0;Otherwise optimal network spreading factor value is still σ0;
5th step:In [σmin,σmax] in take all over all σ values continuous renewal test sample minimum error values, optimum training sample
Collection, minimum spread factor.
7. shared direct drinking monitoring water quality on line system, it is characterised in that:Including selection of control parameter unit (210), modeling sample
This pivot extraction unit (220), normalization sample collection acquiring unit (230), GRNN model constructions unit (240), GRNN moulds
Type network spreading factor acquiring unit (250) and constant water tank water quality prediction unit (260);
The selection of control parameter unit, select to influence the control parameter of water quality in constant water tank, establish neutral net input sample
This collection;
The control parameter of water quality is influenceed in the constant water tank to be included, it is determined that influenceing the influence factor of water quality in water tank, the influence
Factor includes:Water temperature historical temperature is real in the accumulative water consumption of direct drinking fountain filter core performance, regional id number, direct drinking fountain, water tank
When data, real-time water tank water outlet on off state;
Modeling sample pivot extraction unit, input sample collection is extracted with PCA pivots, and obtain new sample set;
Sample collection acquiring unit is normalized, the parameter after PCA pivots are extracted is normalized;
GRNN model construction units, build GRNN network models;
GRNN prototype network spreading factor acquiring units, are trained using GRNN, obtain network spreading factor;
Constant water tank water quality prediction unit, it is pre- to carrying out constant water tank water quality index with the GRNN network models having built up
Survey.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710500789.0A CN107192802B (en) | 2017-06-27 | 2017-06-27 | Shared direct drinking on-line water quality monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710500789.0A CN107192802B (en) | 2017-06-27 | 2017-06-27 | Shared direct drinking on-line water quality monitoring method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107192802A CN107192802A (en) | 2017-09-22 |
CN107192802B true CN107192802B (en) | 2018-03-27 |
Family
ID=59880051
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710500789.0A Active CN107192802B (en) | 2017-06-27 | 2017-06-27 | Shared direct drinking on-line water quality monitoring method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107192802B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109655594A (en) * | 2018-12-30 | 2019-04-19 | 杭州铭展网络科技有限公司 | A kind of water quality acquisition methods |
CN109828089B (en) * | 2019-02-13 | 2022-01-18 | 仲恺农业工程学院 | DBN-BP-based water quality parameter nitrous acid nitrogen online prediction method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001023966A1 (en) * | 1999-09-29 | 2001-04-05 | The University Of Iowa Research Foundation | System and method for controlling effluents in treatment systems |
CN104063577A (en) * | 2014-05-12 | 2014-09-24 | 吉林省电力科学研究院有限公司 | Method for forecasting characteristic gas development tendency in transformer oil based on generalized recurrent neural network |
-
2017
- 2017-06-27 CN CN201710500789.0A patent/CN107192802B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001023966A1 (en) * | 1999-09-29 | 2001-04-05 | The University Of Iowa Research Foundation | System and method for controlling effluents in treatment systems |
CN104063577A (en) * | 2014-05-12 | 2014-09-24 | 吉林省电力科学研究院有限公司 | Method for forecasting characteristic gas development tendency in transformer oil based on generalized recurrent neural network |
Non-Patent Citations (3)
Title |
---|
应用 GRNN 模型对给水管网水质的综合评价;王晓光 等;《沈阳理工大学学报》;20110831;第30卷(第4期);第63-66页 * |
水环境评价及系统仿真研究;孙少华;《中国优秀硕士学位论文全文数据库(电子期刊) 工程科技Ⅰ辑》;20060415(第4期);第34-48页 * |
生活污水处理监控系统的设计与实现;曹波;《中国优秀硕士论文全文数据库(电子期刊)工程科技Ⅰ辑》;20130115(第1期);第51-54页 * |
Also Published As
Publication number | Publication date |
---|---|
CN107192802A (en) | 2017-09-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | A multidimension cloud model-based approach for water quality assessment | |
CN107229970B (en) | The adaptive dynamic self study on-line monitoring system of shared direct drinking water quality | |
CN104155423B (en) | A kind of landscape water quality method for early warning of changeable weight combination | |
CN108376318A (en) | A kind of drainage pipeline networks, which becomes a mandarin, infiltrates appraisal procedure and system | |
McMinn et al. | Classification and assessment of water bodies as adaptive structural measures for flood risk management planning | |
Mediero et al. | Probabilistic calibration of a distributed hydrological model for flood forecasting | |
CN111310976B (en) | Quick water quality forecasting and early warning method and system based on distributed computing | |
CN107192802B (en) | Shared direct drinking on-line water quality monitoring method and system | |
Doglioni et al. | Inferring groundwater system dynamics from hydrological time-series data | |
Yang et al. | Shallow groundwater quality assessment: use of the improved Nemerow pollution index, wavelet transform and neural networks | |
CN101963607A (en) | Watershed wetland water environment state and public satisfaction degree evaluation method | |
CN105445431A (en) | Urban surface water quality analysis method | |
Dorchies et al. | Climate change impacts on multi-objective reservoir management: case study on the Seine River basin, France | |
CN104270773A (en) | Drainage basin sensor coverage net optimizing method based on genetic algorithm multi-objective optimization | |
CN107300855B (en) | A kind of shared direct drinking fountain water quality ensures management control method and system | |
Singh et al. | Review on Data Mining Techniques for Prediction of Water Quality. | |
Heidarzadeh | A practical low-cost model for prediction of the groundwater quality using artificial neural networks | |
Reaver et al. | Reinterpreting the Budyko framework | |
Li et al. | Groundwater depth prediction in a shallow aquifer in north China by a quantile regression model | |
CN106447077A (en) | Resource evaluation method and resource evaluation system | |
Dhumvad et al. | Water pollution monitoring and decision support system | |
Bertone et al. | Data-driven recursive input–output multivariate statistical forecasting model: case of DO concentration prediction in Advancetown Lake, Australia | |
Hou | Spatial assessment for groundwater quality based on GIS and improved fuzzy comprehensive assessment with entropy weights | |
Peters et al. | ZeroFlow: A PUB (Prediction in Ungauged Basins) workshop on temporary streams Summary of workshop discussions and future directions | |
CN114049031A (en) | Method for optimizing site selection of rainwater storage tank |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210609 Address after: 401331 room a010, 2 / F, Zhongchuang building, No. 20, East Road, University Town, Shapingba District, Chongqing Patentee after: Chongqing Yuji Technology Co.,Ltd. Address before: No. 20, East Road, University City, Chongqing, Shapingba District, Chongqing Patentee before: Chongqing University of Science & Technology |
|
TR01 | Transfer of patent right |