CN112651179A - River bottom mud pollution control method - Google Patents
River bottom mud pollution control method Download PDFInfo
- Publication number
- CN112651179A CN112651179A CN202011607283.8A CN202011607283A CN112651179A CN 112651179 A CN112651179 A CN 112651179A CN 202011607283 A CN202011607283 A CN 202011607283A CN 112651179 A CN112651179 A CN 112651179A
- Authority
- CN
- China
- Prior art keywords
- pollution
- sediment
- river
- data
- section
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
A river sediment pollution control method solves the problems that the weight of river sediment pollution cannot be quantified quickly and a sediment pollution engineering strategy cannot be formulated at present, and belongs to the technical field of environmental engineering. The invention comprises the following steps: s1, constructing and training a gray scale neural network model, wherein the input of the gray scale neural network model is cross section overburden water data, sediment pollution data and river hydraulic data, and the output is sediment pollution release rate; s2, inputting the current section data to be predicted into the gray neural network model; s3, obtaining the contribution rate eta of the sediment release to the river water pollution, if eta is smaller than the set value of the contribution rate, switching to S2 to predict the next section, otherwise, switching to S4; s4, obtaining the weight omega of each pollution factor released by the sediment by using an entropy weight methodj(ii) a S5, if omegajIf the weight is larger than the weight set value, corresponding to the pollution factor released by the sediment as a control point, and selecting a corresponding control technology decision scheme; and S6, integrating control points of all sections and corresponding control technology decision schemes.
Description
Technical Field
The invention relates to a river sediment pollution control method based on a gray neural network fusion entropy weight method, and belongs to the cross field of municipal engineering, environmental system simulation and prediction technology and computer technology.
Background
The river water body is an important component of the human living environment, has a plurality of ecological and social functions such as ecological inhabitation, water resource accommodation, shipping traffic and the like, and is closely related to human activities. However, with the rapid development of economy and the acceleration of urbanization process in China, river pollution events caused by water eutrophication and heavy metal exceeding standards occur, and river pollution treatment becomes one of important ecological construction tasks in the urban development process.
Researches show that the sources of river pollution mainly comprise exogenous pollution such as upstream incoming water, branch afflux, point source discharge, rural non-point source pollution, urban non-point source pollution and the like, and endogenous pollution released by bottom mud and the like, and the river pollution has the characteristics of diversity and complexity. Therefore, the source contribution and composition of the river pollutants are determined, and the method is a key technology for realizing the targeted treatment of the river pollutants. At present, a river water quality model represented by an environmental hydrodynamics EFDC model and a QUAL-II comprehensive water quality model is utilized, qualitative and quantitative calculation analysis of exogenous pollution can be realized, but the release amount of endogenous pollution of bottom sediment still needs to be calculated and determined through a release experiment and a formula method, the process is long in time consumption and high in manual operation error, and rapid and accurate analysis of contribution of endogenous pollution of the bottom sediment is not facilitated. Therefore, a solution for rapidly quantifying the river sediment pollution weight and making a sediment pollution engineering strategy is needed in the field of river treatment.
Disclosure of Invention
Aiming at the problems that the prior art can not rapidly quantify the pollution weight of the river bottom mud and formulate a bottom mud pollution engineering strategy, the invention provides a river bottom mud pollution control method.
The invention discloses a river sediment pollution control method, which comprises the following steps:
s1, constructing and training a gray scale neural network model, wherein the input of the gray scale neural network model is the cross section overburden water data, sediment pollution data and river hydraulic data, and the output is the sediment pollution release rate of the overburden water cross section water quality data;
s2, inputting the current water quality data of the section to be predicted, the sediment pollution data and the river hydraulic data into the trained gray scale neural network model, predicting the sediment pollution release rate of the current water quality data of the section, and obtaining the sediment pollution release amount according to the sediment pollution release rate;
s3, obtaining contribution rate eta of the sediment release to the river water pollution according to the sediment pollution release amount and the data of the river pollution source, if eta is smaller than a set value of the contribution rate, switching to S2 to predict the sediment pollution release amount of the next section, and otherwise, switching to S4;
s4, calculating the weight tau of each pollution factor in the current section river data by using an entropy weight methodjAnd according to ωj＝τj·μjObtaining the weight omega of each pollution factor released by the bottom mud of the current sectionj，μjRepresenting the weight of each pollution factor corresponding to the neuron in the gray scale neural network model, wherein j represents the label of the pollution factor released by the sediment;
s5, releasing the bottom mud of the current section into each pollution factor weight omegajComparing with the weight set value, taking the bottom sediment release pollution factor larger than the weight set value as a control point, and selecting a corresponding control technology decision scheme;
and S6, judging whether the prediction of all sections of the river is finished, if not, switching to S2 to predict the bottom mud pollution release amount of the next section, and if so, integrating control points of all sections and corresponding control technology decision schemes to obtain a river mud pollution control scheme.
Preferably, the water covering data on the cross section comprises the contents of ammonia nitrogen, total phosphorus and heavy metal in the water covering on each cross section;
the sediment pollution data comprises the contents of ammonia nitrogen, total phosphorus and heavy metals in the sediment; the river hydraulic data comprises pH value, temperature, flow velocity and sediment thickness of each section of the river.
Preferably, in S1, the gray neural network model includes 1 input layer, 2 intermediate layers, and 1 output layer, and total 60 neurons are obtained, and a gray weakening buffer operator is introduced to find a change law between different input variables, so as to implement the construction of the gray neural network model, where the gray weakening buffer operator is:
x(k)·D＝[x(k)+x(k+1)+…+x(n)]/(n-k+1) k＝1,2,…,n；
wherein x () represents a monotone sequence or an oscillation sequence, D is a sequence operator, and n represents the number of data sequences.
Preferably, in S3, the method for obtaining the contribution rate η of the sediment discharge to the river water pollution comprises:
wherein i represents the source index of the pollutants in the river, PiThe method comprises the release amount of pollutants in upstream incoming water, the release amount of pollutants in branch afflux, the release amount of pollutants in point source discharge, the release amount of rural non-point source pollutants, the release amount of urban non-point source pollutants and the release amount of sediment pollution, wherein P is5Indicating the pollution release amount of the sediment.
Preferably, the contribution ratio set value is 35%.
Preferably, the weight setting value is 20%.
Preferably, in S5, when the control point is the flow rate, a control technical decision scheme is adopted for implementing flow rate control by slope bank restoration and dam construction; when the control point is the sediment thickness, a control technology decision scheme for realizing thickness control by adopting in-situ or ex-situ sediment desilting is adopted; when the control point is water quality, a control technical decision scheme for realizing water quality control by adopting ecological plant in-situ water quality purification or artificial wetland is adopted; and when the control point is bottom sediment pollution, adopting an in-situ or ex-situ biological method to carry out a control technology decision scheme for improving the bottom sediment pollution.
The invention has the beneficial effects that: the method constructs a gray neural network which takes river flow velocity, overlying water quality, bottom sediment thickness, bottom sediment pollutants and the like as input and takes the bottom sediment pollution release rate as output, and realizes the rapid prediction of the river bottom sediment pollution release amount through simulation training and iterative optimization. On the basis, the contribution weight analysis is carried out on the input factors based on the neural network weight and the entropy weight method weight, the key factors influencing the release of the sediment pollutants are determined, and the sediment pollution control method is provided, so that the intelligent analysis and diagnosis from the pollution release amount to the control strategy are realized. The invention is mainly embodied in the following 4 points:
(1) providing a gray neural network model driven by river sediment data, and realizing accurate simulation of more than 90% of the pollution release rate of the river sediment;
(2) the comprehensive flow method for the intelligent decision of the river sediment pollution strategy is provided, so that the intelligent proposal of the engineering strategy based on the contribution weight analysis result of the sediment pollution is realized, and the comprehensive and scientific decision of a city manager on the river sediment pollution treatment is facilitated;
(3) the application case of the invention solves the defects of large workload and long time consumption in the traditional sediment release experimental method for determining the sediment release characteristics, obviously improves the working efficiency, and improves the efficiency by more than 40 times;
the invention is data-driven, the applicability is strong, the modeling method and process are widely suitable for various streams, urban inland rivers, outflowing rivers and the like, the influence of the types and the regional distribution of the rivers is avoided, the simulation result accords with the characteristics of the rivers, and a concrete and feasible bottom mud pollution control proposal which accords with the bottom mud characteristics of the local rivers can be provided according to the requirement that one river corresponds to one strategy.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
As shown in fig. 1, the method for controlling pollution to river sediment based on the gray neural network fusion entropy weight method according to the present embodiment includes:
the method comprises the steps of firstly, constructing and training a gray level neural network model, wherein the input of the gray level neural network model is cross section overburden water data, sediment pollution data and river hydraulic data, the river hydraulic data is corresponding cross section parameters, and the river hydraulic data comprises the temperature, the flow speed, the sediment thickness and the pH value of each cross section; the overlying water data corresponds to water quality parameters; the sediment contamination data corresponds to sediment parameters. The water quality parameters are not obtained through sediment data, and are obtained through experimental measurement in a laboratory by means of sediment collection.
Outputting the bottom sediment pollution release rate of the water quality data of the overlying water section; inputting the current section water quality data to be predicted, sediment pollution data and river hydraulic data into the trained gray scale neural network model, predicting the sediment pollution release rate of the current section water quality data, and obtaining the sediment pollution release amount according to the sediment pollution release rate;
step three, obtaining the contribution rate eta of the bottom sediment release to the river water pollution according to the bottom sediment pollution release amount and the data of a river pollution source, if the eta is smaller than the set value of the contribution rate, switching to step two to predict the bottom sediment pollution release amount of the next section, and otherwise, switching to step four;
fourthly, calculating the weight tau of each pollution factor in the current section river data by utilizing an entropy weight methodjAnd according to ωj＝τj·μjObtaining the weight omega of each pollution factor released by the bottom mud of the current sectionj，μjRepresenting the weight of each pollution factor corresponding to the neuron in the gray scale neural network model, wherein j represents the label of the pollution factor released by the sediment;
fifthly, releasing the bottom mud of the current section into each pollution factor weight omegajComparing the bottom sediment pollution control solution with the weight set value, taking the bottom sediment release pollution factor larger than the weight set value as a control point, and selecting a corresponding bottom sediment pollution control technical decision scheme from a bottom sediment pollution control case reasoning technical library;
and step six, judging whether the prediction of all the sections of the river is finished, if not, transferring to the step two to predict the bottom mud pollution release amount of the next section, and if so, integrating the control points of all the sections and the corresponding control technology decision scheme to obtain a river mud pollution control scheme.
According to the embodiment, the rapid prediction of the pollution release amount of the river sediment is realized through the training and the iterative optimization of the gray scale neural network model. On the basis, the contribution weight analysis is carried out on the input factors based on the neural network weight and the entropy weight method weight, the key factors influencing the release of the sediment pollutants are determined, and the sediment pollution control method is provided, so that the intelligent analysis and diagnosis from the pollution release amount to the control strategy are realized.
The grey neural network is a novel neural network algorithm organically combining a grey system and the neural network, and has strong applicability to the prediction problem under the condition of uncertain factors such as the sediment pollution release rate; the entropy weight method realizes weighting of entropy values of all factors by calculating the discrete degree of all the influencing factors, so as to correct the weight of the neural network, and has important practical significance. The fusion application of the two technologies in the embodiment provides a brand-new realization idea for the analysis of contribution weight of the sediment endogenous pollution.
Step one of the embodiment is to construct and train a gray level neural network model:
the input data of the gray neural network model comprises overlying water data (ammonia nitrogen, total phosphorus and heavy metal), sediment pollution data (ammonia nitrogen, total phosphorus and heavy metal) and river hydraulic data (temperature, flow rate and pH), and the model output data is the release rate of the ammonia nitrogen, the total phosphorus and the heavy metal, namely: the rate of bottom mud contamination release;
the gray scale neural network model is designed into a structure with an input layer 1, a middle layer 2 and an output layer 1, 60 neurons are counted, a gray attenuation buffer operator is introduced to search the change rule among different input variables, the construction of the gray scale neural network model is realized, the formula of the buffer operator is as follows,
x(k)·D＝[x(k)+x(k+1)+…+x(n)]/(n-k+1) k＝1,2,…,n
wherein x () represents a monotone sequence or an oscillation sequence, D represents a sequence operator, x (k) · D represents a sequence obtained by the action of the sequence operator D, and n represents the number of data sequences.
All data of the gray level neural network training are divided into a training set and a testing set, a mean square error function is adopted to control a training process, and the model prediction accuracy is determined by adopting a cross-Validation method (cross-Validation).
In the second step of the embodiment, the method for obtaining the release amount of the sediment pollution according to the release rate of the sediment pollution comprises the following steps:
the release rate of the bottom sediment pollution comprises the average release rate v of total nitrogen, total phosphorus and heavy metal in the bottom sediments(unit mg/(m)2D)) and the annual release Qs(unit kg/a). The specific calculation formula is as follows:
vsi＝f(x1,x2,…xn)
where f () is the gray scale neural network model, xnFor each input parameter, n represents the number of inputs;
wherein m is the number of cross sections, and A is the river flow area/m of each cross section interval2，vsiThe bottom mud pollution release rate of the section is/mg/(m)2·d)；
In the third step of the embodiment, the sediment pollution release amount can be obtained through the sediment pollution release rate predicted by the gray neural network model, and the data of the river pollution sources such as upstream incoming water and branch inflow, point source discharge, rural non-point source pollution, urban non-point source pollution and the like are imported through the river model data interface. Defining the contribution rate of the bottom sediment release to the river water quality pollution as eta, if the eta is less than 35%, determining that the pollution degree of the bottom sediment of the section is small, not performing special treatment, skipping the calculated section to the next section, and repeating the operation of the second step; if eta is more than or equal to 35 percent, considering that the pollution degree of the bottom sediment of the section is higher, the bottom sediment has larger influence on the water quality pollution of the river, executing the operation of the fourth step, and further calculating the weight of each pollution factor released by the bottom sediment. The method for calculating the contribution rate eta of the sediment release to the river water quality pollution comprises
Wherein i represents the source index of the pollutants in the river, PiThe method comprises the release amount of pollutants in upstream incoming water, the release amount of pollutants in branch afflux, the release amount of pollutants in point source discharge, the release amount of rural non-point source pollutants, the release amount of urban non-point source pollutants and the release amount of sediment pollution, wherein P is5Indicating the pollution release amount of the sediment.
And step four of the embodiment is based on the weight calculation of each pollution factor released by the sediment by fusing an entropy weight method, and the weight of each pollution factor released by the sediment is calculated by fusing a gray scale neural network model with the entropy weight method. The weight tau of each pollution factor in the newly input river data can be calculated by utilizing an entropy weight methodjEach neuron in the gray scale neural network model after data training is also endowed with different weights mujCalculating the weight omega of each pollution factor released by the bottom mudjThe specific calculation method comprises the following steps:
ωj＝τj·μj
wherein j represents the number of pollution factors released by the bottom mud; step five of the present embodiment is based on ωjSelecting a technical decision scheme for controlling the bottom sediment pollution, which specifically comprises the following steps:
the weight omega of each pollution factor released by the bottom mud is obtained through calculation in the fourth stepjAnd taking the maximum sediment release influence factor with the weight reaching more than 20 percent as a control point. Setting principles of technical measures corresponding to the influence factors:
flow rate influence type: the flow rate control is suggested to be realized by adopting slope bank restoration and dam construction;
sediment thickness influence type: in-situ or ex-situ sediment desilting is adopted to realize thickness control;
water quality influence type: the ecological plant in-situ water purification or artificial wetland is adopted to realize the water quality control;
bottom sludge pollution influence type: in-situ or ex-situ biological methods are suggested for improving the bottom sediment pollution.
The specific embodiment is as follows: the method is applied to river sediment pollution weight analysis and river sediment pollution treatment work in a certain city, and the specific implementation process is as follows:
(1) program implementation for intelligent automation of models
The embodiment utilizes a distributed cloud computing architecture to realize programming of the invention, input data comprise river section water quality, river flow rate, temperature and bottom sediment pollution, output results are output in a csv form and comprise bottom sediment release rate of each section, contribution rate of bottom sediment pollution of each section to river water quality pollution, suggested treatment technical means of bottom sediment pollution of each section and suggested treatment technical strategies of bottom sediment pollution of the river, and a specific traversal computing process is carried out on the background.
(2) Gray scale neural network model training
Based on years of research results and engineering experience of the research team, river water quality data, bottom sediment data and bottom sediment release experimental data of 50 sampling sections are collected and collated. All data are divided into a training set and a test set, the model prediction accuracy is determined by adopting a cross-Validation method (cross-Validation), and a termination condition is set to be that the prediction accuracy is more than 90%.
(3) Bottom sludge Release Rate calculation
The model system automatically inputs 37 section data into the neural network model line by line for calculation, and in a specific embodiment, section number 19 is taken as an example for introduction of subsequent operations.
According to the calculation result of the neural network model, the sediment release rate of eight heavy metal indexes of the No. 19 section is nearly zero, and the total sediment nitrogen release rate is 332.43 mg/(m)2D), total phosphorus release rate of the sediment 57.59 mg/(m)2D). The surface area of the sediment is approximately equal to the surface area of the river, the river surface data is imported from a river water quality simulation and prediction model through a connector, and the surface area of the sediment on the No. 19 section is about 5419m2So as to calculate the annual total nitrogen release amount of the bottom sediment of the No. 19 section to be 657.52kgThe total phosphorus release was 113.91 kg.
River pollution source data such as upstream incoming water and branch inflow, point source discharge, rural area source pollution, urban area source pollution and the like are imported from a river water quality simulation prediction model through an interface, the bottom mud pollution release amount is calculated through a neural network algorithm, and the pollution contribution rate of the No. 19 section is analyzed to be that the point source discharge accounts for 11.06%, the upstream incoming water and branch inflow accounts for 17.53%, the urban area source pollution accounts for 26.85%, the rural area source pollution accounts for 7.42%, and the bottom mud release accounts for 37.14%. As the contribution rate of the bottom sediment release of the 19 # section to the river pollution is more than 35%, the weight of each pollution factor released by the bottom sediment needs to be further calculated and a corresponding section bottom sediment pollution treatment technical means needs to be provided.
(4) Calculating the weight of each pollution factor released by the sediment
The weight of each pollution factor released by the bottom sediment of the No. 19 section is calculated by utilizing an entropy weight-neural network algorithm, and the calculated weight of the thickness of the bottom sediment is the highest and is 25.98% in the pollution factors of the No. 19 section, and the rest pollution factors with the weight of more than 10% comprise the total nitrogen concentration of water quality of 17.66%, the total phosphorus concentration of water quality of 13.41% and the flow rate of 11.02%.
(5) Technical means for determining section bottom mud pollution treatment suggestion
Weighting the pollution factor omega of the bottom mud of the No. 19 sectionjAs input, three effective treatment technical means with the highest similarity to the section are obtained based on the weight factor-bottom sediment pollution control strategy corresponding principle, namely ex-situ treatment-land utilization-landscaping, ex-situ treatment-land utilization-farmland utilization, ex-situ treatment-building material utilization-brick and tile doping.
(6) Technical strategy for determining river sediment pollution treatment suggestion
And after all the sections participate in calculation, comprehensively integrating and analyzing the bottom mud pollution treatment technical means suggested by each section, and proposing a bottom mud pollution treatment suggestion technical strategy of the river to be researched. In this example, the river to be studied has 37 sections, wherein the contribution rate of sediment release to the river pollution of 8 sections is more than 35%: the pollution factors with the highest 4 section weights are the thickness of the bottom sediment, the pollution factors with the highest 2 section weights are the total nitrogen concentration of the bottom sediment, the pollution factors with the highest 1 section weights are the total phosphorus concentration of the bottom sediment, and the pollution factors with the highest 1 section weights are the flow rate.
The bottom sediment pollution treatment technical proposal scheme of each section is subjected to overall analysis, the river adopts a dredging and in-situ phytoremediation comprehensive treatment scheme in the aspect of bottom sediment treatment, and the total length of bottom sediment treatment accounts for 17.22 percent of the river. The influence interval of the thickness of the bottom sediment is about 2.2km, and the measures are suggested to be taken for dredging the bottom sediment, and the sludge generated by dredging realizes landscaping and farmland utilization; the bottom sediment pollution influence interval is about 3.5km, and the method proposes to adopt measures as an aquatic plant in-situ restoration technology; the hydraulic flow velocity influence interval is about 1.8km, and an in-situ bottom slope finishing technology is adopted to improve the hydrodynamic circulation.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that features described in different dependent claims and herein may be combined in ways different from those described in the original claims. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.
Claims (7)
1. A method for controlling pollution of river bottom mud, the method comprising:
s1, constructing and training a gray scale neural network model, wherein the input of the gray scale neural network model is the cross section overburden water data, sediment pollution data and river hydraulic data, and the output is the sediment pollution release rate of the overburden water cross section water quality data;
s2, inputting the current water quality data of the section to be predicted, the sediment pollution data and the river hydraulic data into the trained gray scale neural network model, predicting the sediment pollution release rate of the current water quality data of the section, and obtaining the sediment pollution release amount according to the sediment pollution release rate;
s3, obtaining contribution rate eta of the sediment release to the river water pollution according to the sediment pollution release amount and the data of the river pollution source, if eta is smaller than a set value of the contribution rate, switching to S2 to predict the sediment pollution release amount of the next section, and otherwise, switching to S4;
s4, calculating the weight tau of each pollution factor in the current section river data by using an entropy weight methodjAnd according to ωj＝τj·μjObtaining the weight omega of each pollution factor released by the bottom mud of the current sectionj，μjRepresenting the weight of each pollution factor corresponding to the neuron in the gray scale neural network model, wherein j represents the label of the pollution factor released by the sediment;
s5, releasing the bottom mud of the current section into each pollution factor weight omegajComparing with the weight set value, taking the bottom sediment release pollution factor larger than the weight set value as a control point, and selecting a corresponding control technology decision scheme;
and S6, judging whether the prediction of all sections of the river is finished, if not, switching to S2 to predict the bottom mud pollution release amount of the next section, and if so, integrating control points of all sections and corresponding control technology decision schemes to obtain a river mud pollution control scheme.
2. The method for controlling pollution of river sediment according to claim 1, wherein the cross section overburden water data comprises the contents of ammonia nitrogen, total phosphorus and heavy metals in the overburden water of each cross section;
the sediment pollution data comprises the contents of ammonia nitrogen, total phosphorus and heavy metals in the sediment; the river hydraulic data comprises pH value, temperature, flow velocity and sediment thickness of each section of the river.
3. The method for controlling pollution of river sediment according to claim 1, wherein in S1, the gray neural network model comprises 1 input layer, 2 intermediate layers and 1 output layer, the total number of neurons is 60, and a gray attenuation buffer operator is introduced to find a change law between different input variables to realize construction of the gray neural network model, and the gray attenuation buffer operator is:
x(k)·D＝[x(k)+x(k+1)+…+x(n)]/(n-k+1)k＝1,2,…,n；
wherein x () represents a monotone sequence or an oscillation sequence, D is a sequence operator, and n represents the number of data sequences.
4. The method for controlling pollution of river sediment according to claim 1, wherein in S3, the method for obtaining the contribution rate η of sediment release to water pollution of river is as follows:
wherein i represents the source index of the pollutants in the river, PiThe method comprises the release amount of pollutants in upstream incoming water, the release amount of pollutants in branch afflux, the release amount of pollutants in point source discharge, the release amount of rural non-point source pollutants, the release amount of urban non-point source pollutants and the release amount of sediment pollution, wherein P is5Indicating the pollution release amount of the sediment.
5. The method of controlling pollution of bottom mud from river as claimed in claim 4, wherein said contribution rate set value is 35%.
6. The method for controlling pollution of bottom mud of a river as claimed in claim 5, wherein the weight set value is 20%.
7. The method for controlling pollution of river sediment according to claim 1, wherein in the step S5, when the control point is the flow rate, a control technology decision scheme for realizing flow rate control by slope bank restoration and dam construction is adopted; when the control point is the sediment thickness, a control technology decision scheme for realizing thickness control by adopting in-situ or ex-situ sediment desilting is adopted; when the control point is water quality, a control technical decision scheme for realizing water quality control by adopting ecological plant in-situ water quality purification or artificial wetland is adopted; and when the control point is bottom sediment pollution, adopting an in-situ or ex-situ biological method to carry out a control technology decision scheme for improving the bottom sediment pollution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011607283.8A CN112651179B (en) | 2020-12-29 | 2020-12-29 | River bottom mud pollution control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011607283.8A CN112651179B (en) | 2020-12-29 | 2020-12-29 | River bottom mud pollution control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112651179A true CN112651179A (en) | 2021-04-13 |
| CN112651179B CN112651179B (en) | 2021-08-10 |
Family
ID=75364321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011607283.8A Active CN112651179B (en) | 2020-12-29 | 2020-12-29 | River bottom mud pollution control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112651179B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12106027B2 (en) * | 2021-05-07 | 2024-10-01 | Dalian University Of Technology | Method and system of sudden water pollutant source detection by forward-inverse coupling |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987477A (en) * | 2006-12-28 | 2007-06-27 | 天津大学 | Interlinked fitting method for heavy metals in river channel sediment |
| CN101962961A (en) * | 2010-09-20 | 2011-02-02 | 中国科学院南京地理与湖泊研究所 | Method for determining ecological dredging range of water body pollution bottom sediment |
| CN102831297A (en) * | 2012-07-27 | 2012-12-19 | 中国环境科学研究院 | Integration method for cause diagnosis of lake pollution |
| CN109101781A (en) * | 2018-07-25 | 2018-12-28 | 水利部交通运输部国家能源局南京水利科学研究院 | The calculation method of pollution sources contribution proportion in a kind of Complex River |
| CN109657942A (en) * | 2018-12-05 | 2019-04-19 | 北京师范大学 | A kind of method of river sound development trend under Prediction of Climate Change |
| CN111598754A (en) * | 2020-04-23 | 2020-08-28 | 中国地质大学（武汉） | Water quality model-based river network area water quality section pollution contribution rate accounting method |
-
2020
- 2020-12-29 CN CN202011607283.8A patent/CN112651179B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987477A (en) * | 2006-12-28 | 2007-06-27 | 天津大学 | Interlinked fitting method for heavy metals in river channel sediment |
| CN101962961A (en) * | 2010-09-20 | 2011-02-02 | 中国科学院南京地理与湖泊研究所 | Method for determining ecological dredging range of water body pollution bottom sediment |
| CN102831297A (en) * | 2012-07-27 | 2012-12-19 | 中国环境科学研究院 | Integration method for cause diagnosis of lake pollution |
| CN109101781A (en) * | 2018-07-25 | 2018-12-28 | 水利部交通运输部国家能源局南京水利科学研究院 | The calculation method of pollution sources contribution proportion in a kind of Complex River |
| CN109657942A (en) * | 2018-12-05 | 2019-04-19 | 北京师范大学 | A kind of method of river sound development trend under Prediction of Climate Change |
| CN111598754A (en) * | 2020-04-23 | 2020-08-28 | 中国地质大学（武汉） | Water quality model-based river network area water quality section pollution contribution rate accounting method |
Non-Patent Citations (2)
| Title |
|---|
| FORIO, MARIE ANNE EURIE等: "Bayesian belief network models to analyse and predict ecological water quality in rivers", 《ECOLOGICAL MODELLING》 * |
| 王娜: "玉门河水环境评价及排放总量控制研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12106027B2 (en) * | 2021-05-07 | 2024-10-01 | Dalian University Of Technology | Method and system of sudden water pollutant source detection by forward-inverse coupling |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112651179B (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102854296B (en) | Sewage-disposal soft measurement method on basis of integrated neural network | |
| Qaderi et al. | Prediction of the groundwater remediation costs for drinking use based on quality of water resource, using artificial neural network | |
| Baxter et al. | Drinking water quality and treatment: the use of artificial neural networks | |
| CN107358021A (en) | DO prediction model establishment method based on BP neural network optimization | |
| CN107045785B (en) | A method of the short-term traffic flow forecast based on grey ELM neural network | |
| CN113156074B (en) | Effluent total nitrogen prediction method based on fuzzy migration | |
| CN107402586A (en) | Dissolved Oxygen concentration Control method and system based on deep neural network | |
| Song et al. | Study on turbidity prediction method of reservoirs based on long short term memory neural network | |
| Elhatip et al. | Evaluation of water quality parameters for the Mamasin dam in Aksaray City in the central Anatolian part of Turkey by means of artificial neural networks | |
| CN112651179B (en) | River bottom mud pollution control method | |
| CN109871638A (en) | A kind of lake and marshland Evaluation of Eutrophication model building method | |
| CN113343601A (en) | Dynamic simulation method for water level and pollutant migration of complex water system lake | |
| CN113850516A (en) | Water quality evaluation method based on T-S fuzzy neural network | |
| CN115906626A (en) | Underground water organic pollution mutual-feedback inversion tracing method based on artificial intelligence | |
| CN109408896B (en) | Multi-element intelligent real-time monitoring method for anaerobic sewage treatment gas production | |
| CN105930685A (en) | Rare earth ore district underground water ammonia nitrogen concentration prediction method with Gauss artificial swarm optimization | |
| Damian | A critical review on artificial intelligence models in hydrological forecasting how reliable are artificial intelligence models | |
| Thaha et al. | Advancing Environmental Sustainability through Implementation of Artificial Neural Networks for Wastewater Treatment Model Prediction and Remediation | |
| Zhang et al. | Prediction and Analysis of MBR Membrane Flux Based on Wavelet Neural Network Optimized by Shuffled Frog-Leaping Algorithm | |
| Blumensaat et al. | An adaptive framework to differentiate receiving water quality impacts on a multi-scale level | |
| Aparna et al. | Enhancing Wastewater Treatment Plant Efficiency: Constraint Optimization and Regression Analysis Approach | |
| Nourani et al. | A hybrid goal programming method and adaptive neural-fuzzy inference system for optimal operation of a multi-objective two-reservoir system | |
| Chu et al. | A PSO-RRBF neural network for BOD prediction in sewage treatment | |
| Luolong et al. | Predicting wastewater sludge recycle performance based on fuzzy neural network | |
| Rai et al. | Prediction of STP Operational Parameters Using ANN |
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 |