AU2021106280A4 - A Method of Water Environment Risk Assessment Based on Fuzzy Integral Model - Google Patents
A Method of Water Environment Risk Assessment Based on Fuzzy Integral Model Download PDFInfo
- Publication number
- AU2021106280A4 AU2021106280A4 AU2021106280A AU2021106280A AU2021106280A4 AU 2021106280 A4 AU2021106280 A4 AU 2021106280A4 AU 2021106280 A AU2021106280 A AU 2021106280A AU 2021106280 A AU2021106280 A AU 2021106280A AU 2021106280 A4 AU2021106280 A4 AU 2021106280A4
- Authority
- AU
- Australia
- Prior art keywords
- standard
- over
- points
- water environment
- evaluation
- 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.)
- Ceased
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title abstract description 50
- 238000000034 method Methods 0.000 title abstract description 22
- 238000012502 risk assessment Methods 0.000 title abstract description 16
- 238000012544 monitoring process Methods 0.000 abstract description 34
- 238000013528 artificial neural network Methods 0.000 abstract description 18
- 238000011156 evaluation Methods 0.000 abstract description 18
- 238000012706 support-vector machine Methods 0.000 abstract description 15
- 102100025142 Beta-microseminoprotein Human genes 0.000 abstract description 7
- 101000576812 Homo sapiens Beta-microseminoprotein Proteins 0.000 abstract description 7
- 238000012549 training Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000003912 environmental pollution Methods 0.000 description 3
- 238000010183 spectrum analysis Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000013316 zoning Methods 0.000 description 1
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
- G06Q10/06—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
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/0275—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using fuzzy logic only
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/05—Programmable logic controllers, e.g. simulating logic interconnections of signals according to ladder diagrams or function charts
- G05B19/058—Safety, monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Automation & Control Theory (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Fuzzy Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a water environment risk assessment method based on a fuzzy
integral model, establishing a support vector machine neural network; training the
support vector machine neural network; inputting PRPS map features into the support
vector machine neural network, and identifying the network topology structure before
and after exceeding the standard differences, determine the over-standard points;
conduct a preliminary over-standard evaluation; pre-process the preliminary
over-standard evaluation conclusions; form a set of candidate over-standard points,
and form a set of directly related over-standard points of each candidate over-standard
point; determine the weight, based on the monitored water environment topology
information and the evaluation conclusions of each over-standard point, forming a set
of the degree of dependence of the directly related over-standard points on the
alternative over-standard points and the set of the degree of dependence of the
indirectly related over-standard points on the alternative over-standard points;
according to the risk index of the possibility of exceeding the standard set, determine
the over-standard monitoring points. The comprehensive evaluation of the present
invention fully considers the reliability difference of the primary evaluation
conclusions, and effectively improves the accuracy of the evaluation.
1
Description
A Method of Water Environment Risk Assessment Based on Fuzzy
Integral Model
The invention belongs to the technical field of environmental monitoring,
and specifically relates to a water environment risk assessment method
based on a fuzzy integral model, and is particularly suitable for risk
monitoring and assessment of water environment risk sources in larger
river basins.
The prevention and control of water environment risks has become one of the important issues that need to be solved urgently in the water environment management ofriver basins, especially in larger river basins.
Unreasonable regional ecological function zoning, inconsistent
implementation standards for upstream and downstream, left and right
banks, and poor communication of environmental information have led to
a large pollution load of regional water environment, unreasonable
allocation of environmental resources, and greater water environmental
risks than other regions. The water environment risk assessment is one of
the important contents of river basin monitoring. At present, there is no specific water environment risk assessment method. Therefore, it is of important practical significance to construct a more practical risk assessment method for the characteristics of various types of water environment risk sources, strong regional sensitivity, and high risk.
The purpose of the present invention is to provide a water environment risk assessment method based on a fuzzy integral model, which is used to assess the level of water environment risk in a river basin and screen key monitoring points. The specific technical solutions are: The water environment risk assessment method based on the fuzzy integral model mainly includes the following steps:
(1) Establish a support vector machine neural network for the monitoring
points of the monitored water environment;
(2) Select appropriate training samples and radial basis function neural
network to train the support vector machine neural network;
(3) Using Fourier analysis method to perform spectrum analysis on the
monitoring signal of the water sample to obtain the PRPS map; input the
PRPS map characteristics into the support vector machine neural network
to identify the difference between the network topology before and after
exceeding the standard, and determine the points of exceeding the
standard;
(4) Based on the support vector machine neural network oriented to the
over-standard point, conduct a preliminary over-standard evaluation;
(5) Use Choquet fuzzy integral model to pre-process the preliminary
over-standard assessment conclusion;
(6) According to the topological information of the monitored water
environment, a set of candidate over-standard points F={fi, f2 ... fN is
formed, where f is the candidate over-standard point;
(7) According to the topological information of the monitored water
environment, form the directly related set of Fi-direct={fm,...fn} and the
indirect related set of Fi-indirect-{fk...fi} of each candidate
over-standard point;
(8) Determine the weight, that is, r--r({xj}), j=, 2,...n, where r is the weight of the j-th information;
(9) Based on the topological information of the monitored water
environment and the evaluation conclusions of each over-standard point,
a set of the degree of dependence of the directly related over-standard
point on the alternative over-standard point is formed of Gi-direct =
{gm...gn} and a set of the degree of dependence of the indirectly related
over-standard point on the alternative over-standard point is formed of
Gi-indirect={gk...gi};
(10) Use the following formula:
A= f g.r= "ggxj) - g(xj) ).r(xj)
Calculate the fuzzy integral value ai, ai is the risk index of the possibility
of exceeding the standard given by the comprehensive assessment, forming a set of possible risk indicators of the alternative over-standard point A={al, a2...aN}; according to the set of possible risk indicators of exceeding the standard, determine the monitoring point for exceeding the standard.
Further, in the step (5), the fuzzy integral model is used to pre-process the
preliminary over-standard assessment conclusion, and the selected
membership degrees are as follows: 0 x < x, z = g(x)= _X_ x < X «X 2 Ix Xz < X
Among them, z is the pre-processed value, x is the data to be
pre-processed, k is the natural constant, h is the threshold, and s is the
weight factor. Preferably, determining the weight in the step (8) includes the following steps:
(8.1) Construct fuzzy measure by weight;
(8.2) Calculate the Choquet fuzzy integral based on the fuzzy measure to
fuse the set of directly related over-standard points and the set of
indirectly related over-standard points;
(8.3) Compare the magnitude of the fuzzy integral value under each
category, and the category corresponding to the largest fuzzy integral
value is the evaluation conclusion of the over-standard point. The advantages of the present invention mainly include: 1. The water environment risk assessment method based on the fuzzy integral model of the present invention adopts neural network for water environment monitoring points and fuzzy integral information fusion technology to evaluate and analyze the monitoring points exceeding the standard, which adapts to the diverse types of water environment risk sources and regional sensitivity Features such as strong sex and high risk;
2. The water environment risk assessment method of the present
invention based on the fuzzy integral model fully takes into account the
reliability difference of the primary assessment conclusions in the
comprehensive assessment, and effectively improves the accuracy of the
assessment.
The present invention will be further described below in conjunction with specific embodiments, but the protection scope of the present invention is not limited to this. First, a complete water environment monitoring system is arranged in the regional water environment. The water environment monitoring system includes multiple environmental pollution indicator monitoring collection modules, wireless information transmission modules, cloud servers, monitoring controlcenters and terminal equipment; The environmental pollution indicator monitoring and collection module is used to collect water quality-related information data of monitoring points in real time and send it to the cloud server through the wireless information transmission module; the cloud server for the water environment is used to receive various environmental pollution indicator monitoring and collection modules. The water quality-related information data of each monitoring point is regularly stored, and the data is analyzed and processed, and the analysis and processing results are sent to the monitoring controlcenter for real-time monitoring; The cloud server includes a cloud database and a data processing analysis module, the cloud database is used to store water quality related information data of each monitoring point; the data processing analysis module is used to implement a water environment risk assessment method based on a fuzzy integral model The fast analysis and evaluation of fuzzy clustering of water quality-related information data of each monitoring point can identify normal water quality monitoring points and monitoring points exceeding standard water quality. The monitoring control center is used to receive the analysis and processing results sent by the cloud server, and perform real-time monitoring, evaluation, early warning and management; The wireless information transmission module is used to realize the wireless data transmission between the above-mentioned modules. Based on the above monitoring system, the water environment risk assessment method based on the fuzzy integral model mainly includes the following steps: (1) Establish a support vector machine neural network for the monitoring points of the monitored water environment; (2) Select appropriate training samples and radial basis function neural network to train the support vector machine neural network; (3) Using Fourier analysis method to perform spectrum analysis on the monitoring signal of the water sample to obtain the PRPS map; input the PRPS map characteristics into the support vector machine neural network to identify the difference between the network topology before and after exceeding the standard, and determine the point of exceeding the standard; (4) Based on the support vector machine neural network oriented to the over-standard point, conduct a preliminary over-standard evaluation; (5) Use Choquet fuzzy integral model to pre-process the preliminary over-standard assessment conclusion; In the step (5), the fuzzy integral model is used to pre-process the preliminary over-standard assessment conclusion, and the selected membership degree is as follows:
0 x z = g(x) = 1 + k-(x-h)/s x 1 <X x2
xXX2 < X
Among them, z is the pre-processed value, x is the data to be pre-processed, k is the natural constant, h is the threshold, and s is the weighting factor. (6) According to the topological information of the monitored water environment, a set of candidate over-standard points F={fl, f2...fN} is formed, where f is the candidate over-standard point; (7) According to the topological information of the monitored water environment, form the directly related set of excess punctuation Fi-direct={fm...fn} and the set of indirect related excess punctuation Fi-indirect-{fk...fi} of each candidate excess punctuation mark; (8) Determine the weight, that is, r-r({xj}), j=l,2,...n, where r is the weight of the j-th information; Determining the weight includes the following steps: (8.1) Construct fuzzy measure by weight; (8.2) Calculate the Choquet fuzzy integral based on the fuzzy measure to fuse the set of directly related over-standard points and the set ofindirectly related over-standard points; (8.3) Compare the magnitude of the fuzzy integral value under each category, and the category corresponding to the largest fuzzy integral value is the evaluation conclusion of the over-standard point. (9) Based on the topological information of the monitored water environment and the evaluation conclusions of each over-standard point, a set of the degree of dependence of the directly related over-standard point on the alternative over-standard point is formed Gi-direct = {gm...gn} and the indirectly correlated over-standard point pair The set Gi-indirect-{gk...gi} of the degree of dependence of the candidate excess punctuation points; (10) Use the following formula: n
A= fg.r= (g(xj) - g(xj) ).r(xj) j=1
Calculate the fuzzy integral value ai, ai is the risk index of the possibility
of exceeding the standard given by the comprehensive evaluation,
forming the possible risk index set A of the candidate exceeding the
standard monitoring point A={al, a2...aN}; according to the risk index
set of the possibility of exceeding the standard , Determine the
monitoring point for exceeding the standard.
1. The water environment risk assessment method based on the fuzzy integral model is characterized in that it mainly includes the following steps: (1) Establish a support vector machine neural network for the monitoring points of the monitored water environment; (2) Select appropriate training samples and radial basis function neural network to train the support vector machine neural network; (3) Using Fourier analysis method to perform spectrum analysis on the monitoring signal of the water sample to obtain the PRPS map; input the PRPS map characteristics into the support vector machine neural network to identify the difference between the network topology before and after exceeding the standard, and determine the points of exceeding the standard; (4) Based on the support vector machine neural network oriented to the over-standard point, conduct a preliminary over-standard evaluation; (5) Use Choquet fuzzy integral model to pre-process the preliminary over-standard assessment conclusion; (6) According to the topological information of the monitored water environment, a set of candidate over-standard points F={fi, f2 ... fNj is formed, where f is the candidate over-standard point; (7) According to the topological information of the monitored water environment, form the directly related set of Fi-direct={fm...fn} and the indirect related set of Fi-indirect={fk...fi} ofeach candidate over-standard point; (8) Determine the weight, that is, r--r({xj}), j=1, 2,...n, where r is the weight of the j-th information; (9) Based on the topological information of the monitored water environment and the evaluation conclusions of each over-standard point, a set of the degree of dependence of the directly related over-standard point on the alternative over-standard point is formed of Gi-direct = {gm... gn} and a set of the degree of dependence of the indirectly related over-standard point on the alternative over-standard point is formed of Gi-indirect={gk...gi}; (10) Use the following formula:
A= f g. r = E'I(g(xj)- g(xI) ).r(x)
Calculate the fuzzy integral value ai, ai is the risk index of the possibility of exceeding the standard given by the comprehensive assessment, forming a set of possible risk indicators of the alternative over-standard point A={al, a2... aN}; according to the set of possible risk indicators of exceeding the standard, determine the monitoring point for exceeding the standard. 2. The water environment risk assessment method based on the fuzzy integral model according to claim 1, characterized in that, in the step (5), the fuzzy integral model is used to pre-process the preliminary over-standard assessment conclusion, and the selected membership degrees are as follows:
0 x < xIL z = g(x)= _x1 « x « X2 Ix X2 < X Among them, z is the pre-processed value, x is the data to be pre-processed, k is the natural constant, h is the threshold, and s is the weight factor. 3. The water environment risk assessment method based on the fuzzy integral model according to claim 1 or 2, characterized in that, determining the weight in the step (8) includes the following steps: (8.1) Construct fuzzy measure by weight; (8.2) Calculate the Choquet fuzzy integral based on the fuzzy measure to fuse the set of directly related over-standard points and the set of indirectly related over-standard points; (8.3) Compare the magnitude of the fuzzy integral value under each category, and the category corresponding to the largest fuzzy integral value is the evaluation conclusion of the over-standard point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021106280A AU2021106280A4 (en) | 2021-08-21 | 2021-08-21 | A Method of Water Environment Risk Assessment Based on Fuzzy Integral Model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021106280A AU2021106280A4 (en) | 2021-08-21 | 2021-08-21 | A Method of Water Environment Risk Assessment Based on Fuzzy Integral Model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2021106280A4 true AU2021106280A4 (en) | 2021-11-04 |
Family
ID=78488500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2021106280A Ceased AU2021106280A4 (en) | 2021-08-21 | 2021-08-21 | A Method of Water Environment Risk Assessment Based on Fuzzy Integral Model |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2021106280A4 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930393A (en) * | 2023-09-19 | 2023-10-24 | 北京大学 | Ecological risk evaluation method for water body antibiotics comprising parent body and transformation product |
| CN118098442A (en) * | 2024-04-19 | 2024-05-28 | 四川国蓝中天环境科技集团有限公司 | Urban water environment small-scale tracing method based on multilayer perceptron model |
-
2021
- 2021-08-21 AU AU2021106280A patent/AU2021106280A4/en not_active Ceased
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930393A (en) * | 2023-09-19 | 2023-10-24 | 北京大学 | Ecological risk evaluation method for water body antibiotics comprising parent body and transformation product |
| CN116930393B (en) * | 2023-09-19 | 2023-12-26 | 北京大学 | Ecological risk evaluation method for water body antibiotics comprising parent body and transformation product |
| CN118098442A (en) * | 2024-04-19 | 2024-05-28 | 四川国蓝中天环境科技集团有限公司 | Urban water environment small-scale tracing method based on multilayer perceptron model |
| CN118098442B (en) * | 2024-04-19 | 2024-07-02 | 四川国蓝中天环境科技集团有限公司 | Urban water environment small-scale tracing method based on multilayer perceptron model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107436277B (en) | The single index data quality control method differentiated based on similarity distance | |
| CN109583520B (en) | State evaluation method of cloud model and genetic algorithm optimization support vector machine | |
| AU2021106280A4 (en) | A Method of Water Environment Risk Assessment Based on Fuzzy Integral Model | |
| CN106779069A (en) | A kind of abnormal electricity consumption detection method based on neutral net | |
| CN110837866A (en) | XGboost-based electric power secondary equipment defect degree evaluation method | |
| CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
| CN112134871A (en) | Abnormal flow detection device and method for energy internet information support network | |
| CN109389325B (en) | Method for evaluating state of electronic transformer of transformer substation based on wavelet neural network | |
| CN115423009A (en) | Cloud edge coordination-oriented power equipment fault identification method and system | |
| CN103103570B (en) | Based on the aluminium cell condition diagnostic method of pivot similarity measure | |
| CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN114169424A (en) | Discharge capacity prediction method based on k nearest neighbor regression algorithm and electricity utilization data | |
| CN110837532A (en) | Method for detecting electricity stealing behavior of charging pile based on big data platform | |
| CN109886314B (en) | Kitchen waste oil detection method and device based on PNN neural network | |
| CN111861141B (en) | Power distribution network reliability assessment method based on fuzzy fault rate prediction | |
| CN117353315B (en) | Device for controlling power generation voltage based on transient fluctuation of photovoltaic and wind power generation voltage | |
| CN113505980A (en) | Reliability evaluation method, device and system for intelligent traffic management system | |
| CN111667391A (en) | Environment-friendly big data monitoring system | |
| CN111861273B (en) | Water environment risk assessment method based on fuzzy integral model | |
| CN114167837B (en) | Intelligent fault diagnosis method and system for railway signal system | |
| CN113449966B (en) | Gypsum board equipment inspection method and system | |
| CN114693175A (en) | Unit state analysis method and system based on network source network-related test | |
| CN117853270B (en) | Anti-electricity-stealing monitoring system and method based on big data analysis | |
| CN110245872A (en) | The method for determining highway engineering safety in production credit grade using improved grey model Cluster Assessment model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) | ||
| MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |