Water quality evaluation method based on continuous time neurodynamic network

An evaluation method and dynamic technology, applied in the direction of biological neural network model, constraint-based CAD, neural architecture, etc., to achieve the effect of expanding applicability

Inactive Publication Date: 2021-09-03
HEBEI UNIV OF ENG +1
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no authoritative literature for detailed research and elaboration on the general fuzzy chance-constrained optimization problem of problem (1).

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Water quality evaluation method based on continuous time neurodynamic network
  • Water quality evaluation method based on continuous time neurodynamic network
  • Water quality evaluation method based on continuous time neurodynamic network

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0066] Example 1, solving the fuzzy linear chance constrained programming problem with fuzzy parameters (5):

[0067]

[0068] in,

[0069] The optimal solution to problem (5) obtained by network (4) is x * =(61.2,38.8) T . figure 2 The state trajectory of the network (4) is shown, with 10 random initial points generated from a uniform distribution on [0,100].

[0070] from figure 2 It can be seen that different initial points converge to a unique optimal solution. This fact shows that the method proposed by the present invention is effective in solving linear chance constrained programming problems with fuzzy parameters.

example 2

[0071] Example 2. Solve the following quadratic fuzzy chance-constrained programming problem:

[0072]

[0073] Among them: a=(a i )=(1,2,3,4,5) T ,b=(b i )=(1,1,1,1,1) T ,

[0074] The optimal solution to problem (6) obtained by network (4) is x * =(0.5,1,1.5,2,2.5) T . image 3 State trajectories for the network (4) with 10 random initial points are shown. from image 3 It can be found that different initial points converge to a unique optimal solution. This shows that the network (4) proposed by the present invention is effective for this type of quadratic fuzzy chance constrained programming problem.

example 3

[0075] Example 3. Application in water quality evaluation of Fuyang River (Handan section).

[0076] For evaluation of Fuyang River (Handan section, see Figure 4 ) water quality, set 84 sampling points A i ,i=1,2,...,84, 10 measurements were made for each sampling point x ij ,j=1,2,...,10, the average value of these 10 measurements as the measured value of the sampling point. In this way, 84 water quality evaluation grades belonging to 6 different levels (I "clean", II "relatively clean", III "slightly polluted", IV "moderately polluted", V "heavy polluted", VI "severely polluted" were obtained. Pollution") Sampling measurements per measurement Contains 10 features Such as PH, DO, etc. DO is obtained by iodometric measurement, DO, NH 4 -N, N, NO 3 , NO 2 、PO 4 The units of , TP and CODmn are "mg / L". For the obtained water quality data, a 10-fold cross-validation method was used.

[0077] For this reason, the steps of the CTNDN method proposed by the present i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a water quality evaluation method based on a continuous time neurodynamics network, and the method comprises the following steps: 1, determining an objective function and constraint conditions of a fuzzy opportunity constraint programming problem through combining a water quality evaluation problem with a given confidence level, and constructing the fuzzy opportunity constraint programming problem; 2, determining an equivalent optimization problem of the fuzzy opportunity constraint programming problem; 3, constructing a neurodynamic network with continuous time for solving the equivalent optimization problem; and 4, giving an initial state of a variable, operating a circuit according to the constructed neurodynamics network, operating the circuit to a balance state to obtain an optimal solution of an original problem, namely obtaining an optimal hyperplane equation for water quality evaluation, finally substituting test data, and outputting a water quality evaluation result according to the hyperplane equation. The water quality evaluation method based on the neurodynamics network has the continuous time characteristic and can meet the requirement for real-time solving of the water quality evaluation problem in practice.

Description

technical field [0001] The invention relates to a water quality evaluation method, in particular to a water quality evaluation method based on a continuous time neural dynamic network. Background technique [0002] Since there is no clear grade boundary in water quality evaluation, in the comprehensive evaluation of water environment quality (referred to as water quality evaluation), water quality samples are often represented by vector value data, and the grades of water quality evaluation are commonly used in language (such as good, lightly polluted , heavy pollution, heavy pollution, serious pollution) qualitatively describe. However, in practical applications, most of the water quality evaluation methods are hard to divide the boundaries of grades, so that samples with very close water quality grades are divided into two distinct grades, resulting in a large deviation in the evaluation results. [0003] For this reason, some scholars use fuzzy sets to describe the level...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06N3/04G06F111/04G06F111/06G06F113/08
CPCG06F30/27G06N3/049G06F2111/04G06F2111/06G06F2113/08G06N3/043
Inventor 马丽涛陈继强谭代敏张丽娜张峰付俊丰万杰
Owner HEBEI UNIV OF ENG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap