CN114580266A - Land-source pollutant intelligent comprehensive evaluation method and system - Google Patents

Land-source pollutant intelligent comprehensive evaluation method and system Download PDF

Info

Publication number
CN114580266A
CN114580266A CN202210047231.2A CN202210047231A CN114580266A CN 114580266 A CN114580266 A CN 114580266A CN 202210047231 A CN202210047231 A CN 202210047231A CN 114580266 A CN114580266 A CN 114580266A
Authority
CN
China
Prior art keywords
pollutant
pollution
factor index
calculating
comprehensive
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.)
Pending
Application number
CN202210047231.2A
Other languages
Chinese (zh)
Inventor
牟林
董亚康
王道胜
牛茜如
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Cudi Ocean Guangzhou Research Institute Of Science And Technology Co ltd
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Original Assignee
Cudi Ocean Guangzhou Research Institute Of Science And Technology Co ltd
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Cudi Ocean Guangzhou Research Institute Of Science And Technology Co ltd, Southern Marine Science and Engineering Guangdong Laboratory Guangzhou filed Critical Cudi Ocean Guangzhou Research Institute Of Science And Technology Co ltd
Priority to CN202210047231.2A priority Critical patent/CN114580266A/en
Publication of CN114580266A publication Critical patent/CN114580266A/en
Pending legal-status Critical Current

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00—Water conservation; Efficient water supply; Efficient water use
    • Y02A20/152—Water filtration

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Mathematical Analysis (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Geometry (AREA)
  • Algebra (AREA)
  • Computer Hardware Design (AREA)
  • Databases & Information Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of river mouth area pollutant monitoring, and provides a land source pollutant intelligent comprehensive evaluation method and system, which comprises the following steps: s1: acquiring a pollutant data set and a river flow data set, acquiring the pollution source type of each pollutant through the correlation coefficient of each pollutant data and the river flow data, and calculating to obtain the flux of each pollutant; s2: calculating to obtain pollution factor indexes corresponding to the pollutant data, obtaining the weight of each pollution factor index through an analytic hierarchy process, and calculating to obtain a comprehensive pollution evaluation level according to the weight of each pollution factor index; s3: and (3) taking the pollution factor index and the pollutant flux corresponding to each pollutant data as input, taking the comprehensive pollution evaluation level as output, training an artificial neural network, and applying the trained artificial neural network to the comprehensive pollution evaluation of the terrestrial pollutants. The method improves the accuracy and the reliability of comprehensive evaluation and provides an auxiliary decision in future river management.

Description

Land-source pollutant intelligent comprehensive evaluation method and system
Technical Field
The invention relates to the field of river mouth area pollutant monitoring, in particular to a land source pollutant intelligent comprehensive evaluation method and system.
Background
In recent years, with the development of economy of China, the advance of urbanization and the improvement of the living standard of people, wastewater, waste liquid, domestic sewage and the like generated by industry and agriculture are continuously discharged into rivers, so that the pollution problem of the water environment is continuously aggravated, the ecological environment quality of river water is reduced, and the adverse effect on the water quality is caused.
The water quality factors of the river need to be evaluated quantitatively or qualitatively, and scientific basis is provided for subsequent treatment and protection work. The currently adopted water quality evaluation methods mainly comprise a single-factor evaluation method, a comprehensive pollution index method, an analytic hierarchy process, fuzzy comprehensive evaluation and the like. Due to the complexity and the dynamic property of multiple pollution factors of the water environment and the characteristics of ambiguity and uncertainty, the actually measured concentration of the pollutants is compared with the set standard item by item only according to a single-factor evaluation method, and the category of the worst evaluation item is used as the category of water quality evaluation, so that the requirements cannot be met. The single factor evaluation method only considers the influence of the most serious factor of the pollution condition, exaggerates the decisive action of the factor on the result and ignores the action of other factors; the comprehensive pollution index method has no determined analysis standard, the pollution index changes along with the number of the evaluation factors, and the comparability is poor; the fuzzy evaluation method emphasizes that the extreme value has too strong effect, and the value-taking algorithm is easy to cause data information loss, so that the evaluation result is not ideal.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent comprehensive evaluation method for land-source pollutants, which comprises the following steps:
s1: acquiring a pollutant data set and a river flow data set, acquiring the pollution source type of each pollutant through the correlation coefficient of each pollutant data and the river flow data, and calculating to obtain the flux of each pollutant;
s2: calculating to obtain pollution factor indexes corresponding to the pollutant data, obtaining the weight of each pollution factor index through an analytic hierarchy process, and calculating to obtain a comprehensive pollution evaluation level according to the weight of each pollution factor index;
s3: and taking the pollution factor index and the pollutant flux corresponding to each pollutant data as input, taking the comprehensive pollution evaluation level as output, training an artificial neural network, and applying the trained artificial neural network to the comprehensive pollution evaluation of the terrestrial pollutants.
Preferably, step S1 specifically includes:
s11: obtaining a correlation coefficient r of the pollutant data and the river flow data through T-test, wherein if r is less than 0, the type of a pollution source of the pollutant data is point source pollution, otherwise, the pollution source is non-point source pollution;
s12: flux of contaminant W of the point source contamination over an estimated time period1The calculation formula of (a) is as follows:
Figure BDA0003472457160000021
wherein K is a conversion coefficient in the estimation time period; n is the total number of samples in the estimation time period; i is the number of sampling times; c. CiThe instantaneous concentration value of the ith sampling; qiIs the instantaneous flow value of the ith sampling;
s13: flux of contaminant W of the non-point source contaminant in an estimation period2The calculation formula of (a) is as follows:
Figure BDA0003472457160000022
wherein the content of the first and second substances,
Figure BDA0003472457160000023
is the average of the instantaneous flow values of the n samples.
Preferably, step S2 specifically includes:
s21: the calculation formula of the pollution factor index is as follows:
Figure BDA0003472457160000024
j is the number of the pollutant type in the pollutant data; pjThe pollution factor index of the j pollutant; mjThe measured content of the j-th pollutant; sjThe evaluation standard value of the j-type pollutant is obtained;
s22: if Pj>1 indicates that the water environment quality is in a polluted state, and if P isjIf 1, the water environment quality is in a critical state, if PjIf the water environment quality is less than 1, the water environment quality is in a clean state;
s23: calculating to obtain the weight of the feature vector of each pollution factor index;
s24: calculating to obtain a consistency check coefficient of each pollution factor index, and adjusting the consistency check coefficient of each pollution factor index to be smaller than a preset value;
s25: the weight of each pollution factor index is obtained through normalization processing calculation, and the calculation formula is as follows:
Figure BDA0003472457160000025
wherein, WjWeight of contamination factor index, v, for class j contaminantsjThe weight value corresponding to j pollutants in the feature vector is shown, and m is the total number of the pollutant types;
s26: and calculating to obtain the comprehensive pollution evaluation level P, wherein the calculation formula is as follows:
P＝∑Wj×Pj。
preferably, step S23 specifically includes:
s231: constructing a decision matrix
Figure BDA0003472457160000031
Wherein m is the total number of contaminant species, adjIs a comparison of the importance of contaminant d to contaminant j, i.e. adjScale of (d); d and j are serial numbers of pollutant types in the pollutant data;
s232: solving the equation:
Figure BDA0003472457160000032
lambda to be obtainedjMaximum eigenvalue λ as a class j contaminantjmaxWherein I is an identity matrix;
s233: by solving the equation: (lambda. alpha.jmaxI-ajj) x is 0, and the obtained x is taken as the weight v corresponding to the j pollutant in the feature vectorj。
Preferably, step S24 specifically includes:
s241: and calculating to obtain a consistency index of the pollution factor index, wherein a calculation formula is as follows:
Figure BDA0003472457160000033
wherein, CIjIs a measure of the consistency of class j contaminants, λjmaxThe maximum characteristic value of the j-th pollutant, and m is the total number of pollutant types;
s242: calculating to obtain the random consistency index of the pollution factor index, wherein the calculation formula is as follows:
Figure BDA0003472457160000034
wherein, RIjThe random consistency index of the j-th pollutant;
s243: and calculating a consistency check coefficient of the pollution factor index, wherein a calculation formula is as follows:
Figure BDA0003472457160000035
wherein, CRjThe consistency checking coefficient of the j-th pollutant is obtained;
will CRjIs set to g, the consistency check coefficient CR is setjCorrecting the pollution factor index of not less than g to make the consistency check coefficient CRj＜g。
An intelligent comprehensive evaluation system for land-source pollutants, comprising:
the pollutant flux acquisition module is used for acquiring a pollutant data set and a river flow data set, acquiring the pollution source type of each pollutant through the correlation coefficient of each pollutant data and the river flow data, and calculating to obtain each pollutant flux;
the comprehensive pollution evaluation level acquisition module is used for calculating and acquiring pollution factor indexes corresponding to the pollutant data, acquiring the weight of each pollution factor index through an analytic hierarchy process, and calculating and acquiring a comprehensive pollution evaluation level according to the weight of each pollution factor index;
and the land-source pollutant comprehensive pollution evaluation acquisition module is used for taking the pollution factor index and the pollutant flux corresponding to each pollutant data as input, taking the comprehensive pollution evaluation level as output, training an artificial neural network, and applying the trained artificial neural network to the land-source pollutant comprehensive pollution evaluation.
The invention has the following beneficial effects:
the method takes the pollution factor index of each evaluation element as an influence factor of the subsequent grading of the analytic hierarchy process, trains the artificial neural network on the basis, can be used for prediction, improves the accuracy and the reliability of the comprehensive evaluation of the land-source pollutants, and provides an auxiliary decision in the future river treatment.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
FIG. 2 is a topology of an ANN model;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the invention provides an intelligent comprehensive evaluation method for a land-source pollutant, comprising the following steps:
s1: acquiring a pollutant data set and a river flow data set, acquiring the pollution source type of each pollutant through the correlation coefficient of each pollutant data and the river flow data, and calculating to obtain the flux of each pollutant;
s2: calculating to obtain pollution factor indexes corresponding to the pollutant data, obtaining the weight of each pollution factor index through an analytic hierarchy process, and calculating to obtain a comprehensive pollution evaluation level according to the weight of each pollution factor index;
s3: and taking the pollution factor index and the pollutant flux corresponding to each pollutant data as input, taking the comprehensive pollution evaluation level as output, training an artificial neural network, and applying the trained artificial neural network to the comprehensive pollution evaluation of the terrestrial pollutants.
In this embodiment, step S1 specifically includes:
s11: obtaining a correlation coefficient r of the pollutant data and the river flow data through T-test, wherein if r is less than 0, the type of a pollution source of the pollutant data is point source pollution, otherwise, the pollution source is non-point source pollution;
specifically, firstly, the pollutant types of the main pollutant data of the river are determined, and the pollutant types are found by an intersection method, wherein the method comprises the following steps: total phosphorus (mg/L), ammonia nitrogen (mg/L), COD (mg/L), dissolved oxygen (mg/L) and total nitrogen (mg/L);
s12: flux of contaminant W of the point source contamination over an estimated time period1The calculation formula of (a) is as follows:
Figure BDA0003472457160000051
where K is the conversion factor in the estimation period (preferably K isSet to 1); n is the total number of samples in the estimation time period; i is the number of sampling times; c. CiThe instantaneous concentration value of the ith sampling; qiIs the instantaneous flow value of the ith sample; the method neglects the influence of the uniform change when the runoff is changed, but highlights the point source pollution;
s13: the flux W of the non-point source pollution in the estimation time period2The calculation formula of (a) is as follows:
Figure BDA0003472457160000052
wherein the content of the first and second substances,
Figure BDA0003472457160000053
is the average of the instantaneous flow values of the n samples.
In this embodiment, step S2 specifically includes:
s21: the calculation formula of the pollution factor index is as follows:
Figure BDA0003472457160000054
wherein j is the serial number of the pollutant type in the pollutant data; pjThe pollution factor index of the j pollutant; mjThe measured content of the j-type pollutant; sjThe evaluation standard value of the j-type pollutant is obtained;
specifically, the pollution factor index adopts a III-class water quality standard in the national surface water environment quality standard (GB3838-2002) as a standard value, and refers to Table 1;
TABLE 1 Standard values of pollution factors (quality Standard of Water Environment on Earth's surface of China; GB3838-2002)
Figure BDA0003472457160000055
TP: total phosphorus; TN: total nitrogen; NH 4: ammonia nitrogen; COD: chemical oxygen demand; DO: dissolving oxygen;
taking the calculation of the pollution factor index of DO as an example:
calculation of the contamination factor index for DO the exponential formula for naphtholuro (n.l. nemerow) was used:
Figure BDA0003472457160000061
wherein, PDOA pollution factor index for DO; DOfThe saturated dissolved oxygen concentration (mg/L) under certain water temperature and air pressure conditions is related to the temperature and salinity of the seawater; DO is the measured value of dissolved oxygen (mg/L); DOsEvaluation standard limit value (mg/L) of dissolved oxygen;
DOf＝14.161-0.3943T+0.007714T2-0.0000646T3
-Q(0.0841-0.00256T+0.0000374T2)
wherein T is water temperature (unit: Kelvin), and Q is seawater salinity;
s22: if Pj>1, the water environment quality is in a polluted state, and if P is in a polluted statejThe water environment quality is in a critical state if 1, and if PjIf the water environment quality is less than 1, the water environment quality is in a clean state;
specifically, the relationship between the water environment quality and the water quality evaluation standard can be judged by using a single pollution factor index evaluation method, generally speaking, if P isj>1, indicating that the water environment quality can not meet the requirement of evaluation standard; if Pj1, indicating that the water environment quality is in a critical state; if Pj<1, the water environment quality meets the requirement of an evaluation standard, and the evaluation grade division standard of a single pollution factor index is shown in a table 2;
TABLE 2
Figure BDA0003472457160000062
S23: calculating to obtain the weight of the feature vector of each pollution factor index;
s24: calculating to obtain a consistency check coefficient of each pollution factor index, and adjusting the consistency check coefficient of each pollution factor index to be smaller than a preset value;
s25: the weight of each pollution factor index is obtained through normalization processing calculation, and the calculation formula is as follows:
Figure BDA0003472457160000063
wherein, WjWeight of contamination factor index, v, for class j contaminantsjThe weight value corresponding to j pollutants in the feature vector is shown, and m is the total number of the pollutant types;
s26: and calculating to obtain the comprehensive pollution evaluation level P, wherein the calculation formula is as follows:
P＝∑Wj×Pj；
specifically, according to the quality standard of surface water environment of the national environmental protection administration: GB3838-2002 obtains standard values of each level of each pollutant type, substitutes parameters corresponding to each pollutant type into the formula to obtain a single factor representing the classification critical value of the pollutant pollution degree, adds the single factors of the same level to obtain the classification critical value of the comprehensive pollution evaluation level, and divides the pollution level (I-V level) of the river according to the classification critical value.
In this embodiment, step S23 specifically includes:
s231: constructing a decision matrix
Figure BDA0003472457160000071
Wherein m is the total number of contaminant species, adjIs a comparison of the importance of contaminant d to contaminant j, i.e. adjScale of (d); d and j are serial numbers of pollutant types in the pollutant data;
specifically, the construction of the judgment matrix A refers to the technical specification of Water ecological health evaluation of the Water administration in Beijing, according to the hydrology and biochemical characteristics of the drainage basin: DB 11/T1722-: the judgment matrix of dissolved oxygen, COD, total phosphorus and ammonia nitrogen is shown in Table 3;
table 3 analytic hierarchy process decision matrix
Figure BDA0003472457160000072
DO: dissolving oxygen; COD: chemical oxygen demand; TP: total phosphorus; NH 4: ammonia nitrogen
S232: solving the equation:
Figure BDA0003472457160000073
will find lambdajMaximum eigenvalue λ as a class j contaminantjmaxWherein I is an identity matrix;
s233: by solving the equation: (lambdajmaxI-ajj) x is 0, and the obtained x is taken as the weight v corresponding to the j pollutant in the feature vectorj。
In this embodiment, step S24 specifically includes:
s241: and calculating to obtain a consistency index of the pollution factor index, wherein a calculation formula is as follows:
Figure BDA0003472457160000081
wherein, CIjIs a measure of the consistency of class j contaminants, λjmaxThe maximum characteristic value of the j-th pollutant, and m is the total number of pollutant types;
s242: calculating to obtain the random consistency index of the pollution factor index, wherein the calculation formula is as follows:
Figure BDA0003472457160000082
wherein, RIjThe random consistency index of the j-th pollutant;
in particular, the random consistency index RIjAnd the order of the judgment matrix is related, generally, the larger the order of the matrix is, the higher the probability of occurrence of consistent random deviation is, and the random consistency index is obtained through a lookup table 4:
TABLE 4 random consistency index lookup table
Figure BDA0003472457160000083
S243: and calculating a consistency check coefficient of the pollution factor index, wherein a calculation formula is as follows:
Figure BDA0003472457160000084
wherein, CRjThe consistency checking coefficient of the j-th pollutant is obtained;
will CRjIs set to g, the consistency check coefficient CR is setjCorrecting the pollution factor index of not less than g to make the consistency check coefficient CRj< g; the value of g is preferably set to 0.1;
specifically, after consistency is adjusted, a total hierarchical index ranking is established, and weights of all influence factors of the lowest layer (factor layer) on relative importance of the highest layer (total target) are calculated and are called as the total hierarchical index ranking; the process is carried out from the highest level to the lowest level according to the constructed hierarchical structure model, and the calculation method is to multiply the weight vector of the middle layer by the weight matrix of the low layer.
In this embodiment, step S3 specifically includes:
referring to fig. 2, an ANN model is constructed, and the pollution factor index and the pollutant flux corresponding to each pollutant data are used as a training set for training a network, where an input layer includes a weighted average of monitoring indexes and fluxes of 4 pollutants, and the number of nodes of the input layer is 4; the number of neurons in the hidden layer is obtained according to an empirical formula;
Figure BDA0003472457160000085
v and b are the number of nodes of an input layer and an output layer respectively, a belongs to (1, 10), the number of neurons is increased in sequence, and the number of neurons is determined according to the mean square error and the training step length; the output layer is 5 pollution levels of the comprehensive pollution evaluation level, so that 5 neurons are selected as the output layer; sigmoid is selected as an activation function, so that the input layer is subjected to normalization processing, and the output layer is represented by a matrix of 5 multiplied by 1;
in the training optimization of the artificial neural network, a plurality of groups of data samples with random land-source pollutant comprehensive classification standard values are trained until the training error sum E is less than or equal to 0.00001, the training is stopped, and the maximum training frequency is set to 25000. And finally, applying the trained ANN model to the comprehensive pollution evaluation of the land-source pollutants.
The invention provides an intelligent comprehensive evaluation system for land-source pollutants, which comprises:
the pollutant flux acquisition module is used for acquiring a pollutant data set and a river flow data set, acquiring the pollution source type of each pollutant through the correlation coefficient of each pollutant data and the river flow data, and calculating to obtain each pollutant flux;
the comprehensive pollution evaluation level acquisition module is used for calculating and acquiring pollution factor indexes corresponding to the pollutant data, acquiring the weight of each pollution factor index through an analytic hierarchy process, and calculating and acquiring a comprehensive pollution evaluation level according to the weight of each pollution factor index;
and the land-source pollutant comprehensive pollution evaluation acquisition module is used for taking the pollution factor index and the pollutant flux corresponding to each pollutant data as input, taking the comprehensive pollution evaluation level as output, training an artificial neural network, and applying the trained artificial neural network to the land-source pollutant comprehensive pollution evaluation.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third and the like do not denote any order, but rather the words first, second and the like may be interpreted as indicating any order.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.

Claims (6)

1. An intelligent comprehensive evaluation method for land-source pollutants is characterized by comprising the following steps:
s1: acquiring a pollutant data set and a river flow data set, acquiring the pollution source type of each pollutant through the correlation coefficient of each pollutant data and the river flow data, and calculating to obtain the flux of each pollutant;
s2: calculating to obtain pollution factor indexes corresponding to the pollutant data, obtaining the weight of each pollution factor index through an analytic hierarchy process, and calculating to obtain a comprehensive pollution evaluation level according to the weight of each pollution factor index;
s3: and taking the pollution factor index and the pollutant flux corresponding to each pollutant data as input, taking the comprehensive pollution evaluation level as output, training an artificial neural network, and applying the trained artificial neural network to the comprehensive pollution evaluation of the terrestrial pollutants.
2. The land-source pollutant intelligent comprehensive evaluation method according to claim 1, wherein the step S1 is specifically as follows:
s11: obtaining a correlation coefficient r of the pollutant data and the river flow data through T-test, wherein if r is less than 0, the type of a pollution source of the pollutant data is point source pollution, otherwise, the pollution source is non-point source pollution;
s12: flux of contaminant W of the point source contamination over an estimated time period1The calculation formula of (a) is as follows:
Figure FDA0003472457150000011
wherein K is a conversion coefficient in the estimation time period; n is the total number of samples in the estimation time period; i is the number of sampling times; c. CiThe instantaneous concentration value of the ith sampling; qiIs the instantaneous flow value of the ith sample;
s13: flux of contaminant W of the non-point source contaminant in an estimation period2The calculation formula of (a) is as follows:
Figure FDA0003472457150000012
wherein the content of the first and second substances,
Figure FDA0003472457150000013
is the average of the instantaneous flow values of the n samples.
3. The land-source pollutant intelligent comprehensive evaluation method according to claim 1, wherein the step S2 is specifically as follows:
s21: the calculation formula of the pollution factor index is as follows:
Figure FDA0003472457150000014
wherein j is the serial number of the pollutant type in the pollutant data; p isjIs the pollution factor index of the j-th pollutant; mjThe measured content of the j-type pollutant; sjThe evaluation standard value is the j-type pollutant;
s22: if Pj>1 indicates that the water environment quality is in quiltState of contamination if PjThe water environment quality is in a critical state if 1, and if PjIf the water environment quality is less than 1, the water environment quality is in a clean state;
s23: calculating to obtain the weight of the feature vector of each pollution factor index;
s24: calculating to obtain a consistency check coefficient of each pollution factor index, and adjusting the consistency check coefficient of each pollution factor index to be smaller than a preset value;
s25: the weight of each pollution factor index is obtained through normalization processing calculation, and the calculation formula is as follows:
Figure FDA0003472457150000021
wherein, WjWeight of contamination factor index, v, for class j contaminantsjThe weight value corresponding to the pollutant j in the characteristic vector is obtained, and m is the total number of the pollutant types;
s26: and calculating to obtain the comprehensive pollution evaluation level P, wherein the calculation formula is as follows:
P＝∑Wj×Pj。
4. the land-source pollutant intelligent comprehensive evaluation method according to claim 3, wherein the step S23 is specifically as follows:
s231: constructing a decision matrix
Figure FDA0003472457150000022
Wherein m is the total number of contaminant species, adjIs a comparison of the importance of contaminant d to contaminant j, i.e. adjScale of (d); d and j are serial numbers of pollutant types in the pollutant data;
s232: solving the equation:
Figure FDA0003472457150000023
lambda to be obtainedjMaximum eigenvalue λ as a class j contaminantjmaxWherein I is an identity matrix;
s233: by solving the equation: (lambdajmaxI-ajj) x is 0, and the obtained x is taken as the weight v corresponding to the j pollutant in the feature vectorj。
5. The land-source pollutant intelligent comprehensive evaluation method according to claim 3, wherein the step S24 is specifically as follows:
s241: and calculating to obtain a consistency index of the pollution factor index, wherein a calculation formula is as follows:
Figure FDA0003472457150000031
wherein, CIjIs a measure of the consistency of class j contaminants, λjmaxThe maximum characteristic value of the j-th pollutant, and m is the total number of pollutant types;
s242: calculating to obtain the random consistency index of the pollution factor index, wherein the calculation formula is as follows:
Figure FDA0003472457150000032
wherein, RIjThe random consistency index of the j-th pollutant;
s243: and calculating a consistency check coefficient of the pollution factor index, wherein a calculation formula is as follows:
Figure FDA0003472457150000033
wherein, CRjThe consistency checking coefficient of the j-th pollutant is obtained;
will CRjIs set to g, the consistency check coefficient CR is setjCorrecting the pollution factor index of not less than g to make the consistency check coefficient CRj＜g。
6. An intelligent comprehensive evaluation system for land-source pollutants, comprising:
the pollutant flux acquisition module is used for acquiring a pollutant data set and a river flow data set, acquiring the pollution source type of each pollutant through the correlation coefficient of each pollutant data and the river flow data, and calculating to obtain each pollutant flux;
the comprehensive pollution evaluation level acquisition module is used for calculating and acquiring pollution factor indexes corresponding to the pollutant data, acquiring the weight of each pollution factor index through an analytic hierarchy process, and calculating and acquiring a comprehensive pollution evaluation level according to the weight of each pollution factor index;
and the land-source pollutant comprehensive pollution evaluation acquisition module is used for taking the pollution factor index and the pollutant flux corresponding to each pollutant data as input, taking the comprehensive pollution evaluation level as output, training an artificial neural network, and applying the trained artificial neural network to the land-source pollutant comprehensive pollution evaluation.
CN202210047231.2A 2022-01-17 2022-01-17 Land-source pollutant intelligent comprehensive evaluation method and system Pending CN114580266A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210047231.2A CN114580266A (en) 2022-01-17 2022-01-17 Land-source pollutant intelligent comprehensive evaluation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210047231.2A CN114580266A (en) 2022-01-17 2022-01-17 Land-source pollutant intelligent comprehensive evaluation method and system

Publications (1)

Publication Number Publication Date
CN114580266A true CN114580266A (en) 2022-06-03

Family

ID=81769056

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210047231.2A Pending CN114580266A (en) 2022-01-17 2022-01-17 Land-source pollutant intelligent comprehensive evaluation method and system

Country Status (1)

Country Link
CN (1) CN114580266A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115409318A (en) * 2022-07-22 2022-11-29 南方海洋科学与工程广东省实验室(广州) Natural-based water purification scheme optimization method integrating fuzzy AHP and MDS
CN117434227A (en) * 2023-12-20 2024-01-23 河北金隅鼎鑫水泥有限公司 Method and system for monitoring waste gas components of cement manufacturing plant

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115409318A (en) * 2022-07-22 2022-11-29 南方海洋科学与工程广东省实验室(广州) Natural-based water purification scheme optimization method integrating fuzzy AHP and MDS
CN115409318B (en) * 2022-07-22 2024-03-19 南方海洋科学与工程广东省实验室(广州) Natural-based water purification scheme optimization method integrating fuzzy AHP and MDS
CN117434227A (en) * 2023-12-20 2024-01-23 河北金隅鼎鑫水泥有限公司 Method and system for monitoring waste gas components of cement manufacturing plant
CN117434227B (en) * 2023-12-20 2024-04-30 河北金隅鼎鑫水泥有限公司 Method and system for monitoring waste gas components of cement manufacturing plant

Similar Documents

Publication Publication Date Title
Gaya et al. Estimation of water quality index using artificial intelligence approaches and multi-linear regression
Elkiran et al. Artificial intelligence-based approaches for multi-station modelling of dissolve oxygen in river
Sahoo et al. Forecasting stream water temperature using regression analysis, artificial neural network, and chaotic non-linear dynamic models
Dogan et al. Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique
Partal et al. Prediction of daily precipitation using wavelet—neural networks
CN114580266A (en) Land-source pollutant intelligent comprehensive evaluation method and system
Yang et al. Prediction of effluent quality in a wastewater treatment plant by dynamic neural network modeling
US20180029900A1 (en) A Method for Effluent Total Nitrogen-based on a Recurrent Self-organizing RBF Neural Network
Brion et al. Artificial neural network modelling: a summary of successful applications relative to microbial water quality
Hamada et al. Application of artificial neural networks for the prediction of Gaza wastewater treatment plant performance-Gaza strip
Ruben et al. Application and sensitivity analysis of artificial neural network for prediction of chemical oxygen demand
CN102854296A (en) Sewage-disposal soft measurement method on basis of integrated neural network
CN108562709A (en) A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine
CN103606006A (en) Sludge volume index (SVI) soft measuring method based on self-organized T-S fuzzy nerve network
CN109190865B (en) Water quality index evaluation method, prediction method and water area water quality grade evaluation method
CN109657790B (en) PSO-based recursive RBF neural network effluent BOD prediction method
CN107247888B (en) Method for soft measurement of total phosphorus TP (thermal transfer profile) in sewage treatment effluent based on storage pool network
CN110969346A (en) Drainage basin water ecological function regional treatment demand evaluation method based on index screening
Boyacioglu et al. Application of factor analysis in the assessment of surface water quality in Buyuk Menderes River Basin
Abba et al. Modelling of uncertain system: a comparison study of linear and non-linear approaches
Areerachakul et al. Integration of unsupervised and supervised neural networks to predict dissolved oxygen concentration in canals
CN103793604A (en) Sewage treatment soft measuring method based on RVM
Neelakantan et al. Neural network modelling of Cryptosporidium and Giardia concentrations in the Delaware River, USA
CN115713448A (en) Catchment unit-based method for quickly tracing conventional factors of basin water pollution
Areerachakul et al. Prediction of dissolved oxygen using artificial neural network

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