Method and system for evaluating pollution state of karst groundwater
By applying the gray wolf optimization algorithm in karst groundwater systems and creating an evaluation parameter optimization model, the problem of low applicability of traditional evaluation methods in karst systems is solved, and more efficient and accurate pollution status assessment is achieved.
Patent Information
- Application Number
- CN202411861797.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2025-05-09
AI Technical Summary
Traditional water pollution assessment methods are low in applicability in karst groundwater systems and cannot accurately reflect the pollution status, mainly due to the complexity of the karst system and the rapid spread of pollutants.
The gray wolf optimization algorithm is used to create an evaluation parameter optimization model, and the optimal evaluation parameters are obtained through iteratively to conduct a comprehensive assessment of karst groundwater pollution status.
It improves evaluation efficiency and accuracy, can more accurately reflect the state of karst groundwater pollution, and is suitable for complex karst groundwater systems.
Smart Images
Figure CN119962809A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of groundwater pollution assessment, and in particular to a karst groundwater pollution status assessment method and system. Background Art
[0002] Karst groundwater refers to groundwater that exists in karst terrain. Karst terrain is a landform formed by the dissolution of soluble rocks (such as limestone, dolomite, gypsum and salt rock) under the action of groundwater. The karst groundwater system has unique hydrogeological characteristics. Due to the development of fissures and caves in karst areas, groundwater flows rapidly and has high permeability. Pollutants can easily spread rapidly through these channels, increasing the risk of pollution and causing increasingly serious groundwater pollution problems.
[0003] Traditional water pollution assessment methods include physical and chemical analysis, which assesses the risk of water pollution by measuring the physical and chemical properties of various pollutants in water, such as concentration and dissolved oxygen. Biological analysis, which assesses the risk of water pollution by measuring biological indicators in water, such as biological species, quantity, biomass, etc. Comprehensive analysis, which comprehensively considers various pollutants in water and their interactions, as well as their impact on water quality and aquatic ecosystems, to comprehensively assess the risk of water pollution.
[0004] Affected by the complex karst system, such as the development of fractures in karst areas, the complexity of fracture networks, the complexity of groundwater flow paths, infiltration conditions, water dissolution and chemical reactions, adsorption and desorption of pollutants, etc., as well as the connection between groundwater and surface water, the same evaluation indicators cannot accurately reflect the pollution status, making traditional water pollution assessment methods less applicable in different karst groundwater systems. Summary of the invention
[0005] The present invention aims to provide a karst groundwater pollution status assessment method and system, so as to create an assessment parameter optimization model through the Grey Wolf Optimization Algorithm to iteratively obtain the optimal assessment parameters, and to conduct karst groundwater pollution status assessment based on the optimal assessment parameters, thereby improving the assessment efficiency and accuracy.
[0006] In order to achieve the above object, the present invention adopts the following technical scheme:
[0007] Karst groundwater pollution status assessment methods, including:
[0008] An assessment target acquisition step is to acquire assessment targets of karst groundwater pollution, wherein the assessment targets include health, economy, society, water supply system, and ecological environment;
[0009] Data acquisition step: comprehensively acquire the parameters for karst groundwater pollution status assessment based on the assessment objectives;
[0010] The model creation and update step is based on the evaluation target, using the Gray Wolf Optimization Algorithm to take the evaluation parameters as the optimization target, creating an evaluation parameter optimization model, and iterating based on the evaluation parameter optimization model to obtain the optimal evaluation parameters;
[0011] The steps of karst groundwater pollution status assessment are comprehensively evaluated based on the optimal assessment parameters.
[0012] The principles and advantages of this solution are as follows: in actual application, different assessment targets have different focuses. By obtaining the assessment targets, it is easier to prepare for the assessment more accurately. By comprehensively obtaining pollutant data, pollution paths and karst groundwater data, the influencing factors involved in karst groundwater pollution can be covered to improve data integrity. Due to the huge amount of karst groundwater pollution status assessment parameter data, it is difficult to screen the assessment parameters to combine the assessment of the pollution status more accurately and closer to the target. Therefore, based on the assessment target of karst groundwater pollution, the Grey Wolf Optimization Algorithm is used to take the assessment parameters as the optimization target, and an assessment parameter optimization model is created. The optimal evaluation parameters are obtained by iteratively performing the optimization model; the gray wolf algorithm simulates the social hierarchy and predation behavior of gray wolves, including three basic behaviors: searching for prey, surrounding prey, and attacking prey. In the algorithm, the position of the gray wolf individual represents a feasible solution in the solution space. The three gray wolves occupying the best position in the group correspond to the wolf king α and his left and right guards β and δ wolves, respectively. α, β, and δ wolves lead the wolf pack towards the prey (optimal solution). Through this algorithm, the optimization of the evaluation parameters has strong convergence performance, simple structure, few parameters to be adjusted, and easy implementation, which is convenient for quickly and accurately obtaining the optimal evaluation parameters for the evaluation of karst groundwater pollution status.
[0013] Preferably, as an improvement, the data acquisition step includes:
[0014] An evaluation scope acquisition sub-step, acquiring the evaluation scope according to a preset scope mapping rule based on the evaluation target;
[0015] In the data acquisition layout sub-step, based on the assessment objectives, the key influencing positions are obtained, and starting from the key influencing positions, the data acquisition positions are determined by increasing the analysis in sequence according to the radiation distance ratio.
[0016] Technical effect: It is easy to improve the accuracy of data acquisition and improve the overall efficiency.
[0017] Preferably, as an improvement, the data acquisition step further includes:
[0018] The data preprocessing sub-step is to clean and standardize the collected data;
[0019] The feature extraction sub-step converts the preprocessed data into assessment data of the karst groundwater pollution status.
[0020] Technical effect: Facilitates improving data availability.
[0021] Preferably, as an improvement, the model creation and updating steps include:
[0022] Initialization substep, initializing the position of the gray wolf population as a combination vector of evaluation parameters;
[0023] The fitness function determination sub-step determines the fitness function expression according to the evaluation target benefit;
[0024] The model iterative update submodule calculates the individual fitness of all gray wolves, and takes the top three gray wolves in fitness as α, β and δ wolves in turn, and the rest of the gray wolves as ω wolves. The wolf pack updates its position according to α, β and δ wolves. After the maximum number of iterations, the final α wolf position is obtained, and the final α wolf position is used as the optimal evaluation parameter vector combination.
[0025] Technical effect: It is easy to simulate the leadership hierarchy and hunting mechanism of gray wolves in nature to accurately obtain optimization results.
[0026] Preferably, as an improvement, the fitness function expression is:
[0027]
[0028] Among them, τ is the fitness adjustment constant coefficient, θ1, θ2, *θ3 are weight constant coefficients, and v s Get efficiency values for the evaluation parameters, z s To evaluate the accuracy of the parameters, s s is the difficulty value of evaluating parameter fusion.
[0029] Technical effect: It is convenient to evaluate the survival ability of gray wolves in the karst groundwater pollution status assessment environment.
[0030] Preferably, as an improvement, in the grey wolf optimization algorithm, the convergence factor is updated in the following manner:
[0031]
[0032] Among them, t is the current iteration number, t max is the maximum number of iterations.
[0033] Technical effect: The existing Grey Wolf optimization algorithm has the defects of premature convergence, low convergence accuracy when facing complex problems, and slow convergence speed. Through the above formula, nonlinear adjustment of the convergence factor is realized, thereby improving the global search and local development capabilities of the algorithm.
[0034] Preferably, as an improvement, the rule for location updating is:
[0035] If |X2|>|X3|>|X1| or |X3|>|X2|>|X1| or |X3|>|X1|>|X2|, then
[0036]
[0037] If |X1|>|X2|>|X3| or |X1|>|X3|>|X2| or |X2|>|X1|>|X3|, then
[0038]
[0039] in:
[0040] X1=X α -A1D α ;
[0041] X2=X β -A2D β ;
[0042] X3=X δ -A3D δ ;
[0043] Where A1, A2 and A3 are distance coefficient vectors; D α , D β , D δ represents the distance between the wolf pack and α, β and δ; X α , X β and X δ Represent the positions of α, β and δ wolves respectively.
[0044] Technical effect: Through the above-mentioned update algorithm, the Euclidean distances of the three types of leader wolves are calculated respectively according to the positions of α, β and δ wolves relative to ω wolf, and the position update proportion weight of ω wolf is dynamically adjusted to improve the effectiveness of solving complex and high-dimensional problems.
[0045] Preferably, as an improvement, the data acquisition step further includes a correlation analysis sub-step to perform correlation marking on the data after data conversion.
[0046] Technical effect: The amount of data used for evaluation is large, and through correlation marking, it is convenient to deduce and replace it through relevant data when the optimization result data is difficult to obtain.
[0047] Preferably, as an improvement, the karst groundwater pollution status assessment step includes:
[0048] The weight acquisition sub-step is to obtain the weights of the optimal evaluation parameters through the hierarchical analysis method;
[0049] The optimal evaluation parameter replacement submodule replaces the optimal evaluation parameter according to the correlation tag when the optimal evaluation parameter cannot be obtained or the acquisition cost exceeds the threshold;
[0050] The comprehensive evaluation submodule performs weighted summation based on the weights of the optimal evaluation parameters to obtain the final evaluation result.
[0051] Technical effect: It is easy to improve the efficiency of karst groundwater pollution status assessment.
[0052] It also includes a karst groundwater pollution status assessment system, which uses the karst groundwater pollution status assessment method. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] Figure 1 Schematic diagram of the process of karst groundwater pollution status assessment method. DETAILED DESCRIPTION
[0054] The following is further described in detail through specific implementation methods:
[0055] The embodiment is basically as shown in the attached Figure 1 As shown:
[0056] Karst groundwater pollution status assessment methods, including:
[0057] The step of obtaining the assessment target is to obtain the assessment target of karst groundwater pollution, which includes health, economy, society, water supply system, and ecological environment. Different assessment targets have different focuses. By obtaining the assessment targets, it is easy to accurately obtain data and optimize parameters. For example, when the assessment target is health, attention is paid to pollutant concentrations, exposure pathways, and health effects, such as the concentrations of heavy metals, organic pollutants, pathogenic microorganisms, etc. in groundwater, exposure pathways through drinking water, food chain, skin contact, etc., and the potential effects of pollutants on human health, such as carcinogenicity, teratogenicity, and mutagenicity; when the assessment target is economic, attention is paid to governance costs, economic losses, medical costs, insurance costs, and opportunity costs, such as monitoring, repair, and governance facility construction and operation costs, agricultural production reductions, fishery damage, and tourism declines caused by groundwater pollution, treatment of diseases, health examinations, etc. caused by groundwater pollution, increased insurance costs due to groundwater pollution, and opportunity costs of land and water resources that cannot be fully utilized due to groundwater pollution. When the assessment target is society, attention is paid to social impact, social conflict, social support, etc., such as the impact of groundwater pollution on the quality of life and happiness of community residents, the community residents' cognition and attitude towards groundwater pollution, social conflicts and disputes caused by groundwater pollution, and social support and mutual assistance mechanisms provided within the community; when the assessment target is the water supply system, attention is paid to water supply volume, water quality standards, alternative water sources, etc., such as the reduction in water supply due to pollution, whether the groundwater meets national and local water quality standards, the operation and maintenance of water supply facilities, and whether there are alternative water sources for use, such as surface water, seawater desalination, etc.; when the assessment target is the ecological environment, attention is paid to biodiversity, ecological health, ecological service functions, environmental quality standards, etc.
[0058] The data acquisition step is based on the evaluation target to comprehensively acquire the parameters for evaluating the karst groundwater pollution status; the evaluation parameters include but are not limited to pollutant data, pollution paths and relevant data on karst groundwater data. The data acquisition step includes an evaluation range acquisition sub-step, a data acquisition layout sub-step, a data preprocessing sub-step, and a feature extraction sub-step. The evaluation range acquisition sub-step acquires the evaluation range according to the preset range mapping rules based on the evaluation target; for example, when the evaluation target is health, the preset mapping range is the range of population activities affected by the pollution, and the range mapping rules are adjusted and set according to actual application experience. The data acquisition layout sub-step acquires the key positions of influence based on the evaluation target, and takes the key positions of influence as the starting point, and analyzes and determines the data acquisition position in accordance with the radiation distance ratio. For example, if the evaluation target is health, the key positions of influence are drinking water sources, irrigation water sources, etc., and the radiation step length is 1km. The influence decreases outward from the key position, and the step length increases in sequence. The sparser the data acquisition position is, the more sufficient the data volume of the key position is, while reducing the workload. The data preprocessing sub-step cleans and standardizes the collected data; the feature extraction sub-step converts the preprocessed data into assessment data of the karst groundwater pollution status to improve data availability. The data acquisition step also includes a correlation analysis sub-step to mark the data after data conversion for correlation, so that when the optimization result data is difficult to obtain, it can be derived and replaced by related data.
[0059] The model creation and update step is based on the assessment target of karst groundwater pollution, using the Gray Wolf Optimization Algorithm to take the assessment parameters as the optimization target, creating an assessment parameter optimization model, and iterating the assessment parameter optimization model to obtain the optimal assessment parameters; the model creation and update step includes:
[0060] The initialization substep initializes the position of the gray wolf population as a combination vector of evaluation parameters; it also includes the initialization of the convergence factor a and the synergy coefficient vectors A and C.
[0061] The fitness function determination sub-step determines the fitness function expression according to the evaluation target benefit; in this embodiment, the fitness function expression is:
[0062]
[0063] Among them, τ is the fitness adjustment constant coefficient, θ1, θ2, *θ3 are weight constant coefficients, and v s Get efficiency values for the evaluation parameters, z s To evaluate the accuracy of the parameters, s s The difficulty value is integrated for the evaluation parameters. Based on the fitness function expression, it is convenient to evaluate the survival ability of gray wolves in the karst groundwater pollution status assessment environment.
[0064] The model iterative update submodule calculates the individual fitness of all gray wolves, and takes the top three gray wolves in fitness as α, β and δ wolves in turn, and the rest of the gray wolves as ω wolves. The wolf pack updates its position according to α, β and δ wolves. After the maximum number of iterations, the final α wolf position is obtained, and the final α wolf position is used as the optimal evaluation parameter vector combination.
[0065] The existing gray wolf optimization algorithm has the defects of premature convergence, low convergence accuracy and slow convergence speed when facing complex problems. The exploration and development capabilities of the algorithm depend on the value of A. When |A|>1, the gray wolf group continues to search for prey by expanding the search range, that is, global search; and when |A|<1, the gray wolf group attacks the prey by shrinking the search range, that is, local development. The value of A depends on the change of the convergence factor a. In the gray wolf optimization algorithm described in this embodiment, the update method of the convergence factor is:
[0066]
[0067] Among them, t is the current iteration number, t max is the maximum number of iterations. Through the above formula, the nonlinear adjustment of the convergence factor is realized, thereby improving the global search and local development capabilities of the algorithm.
[0068] In this embodiment, the rule for the gray wolf to update its position is:
[0069] If |X2|>|X3|>|X1| or |X3|>|X2|>|X1| or |X3|>|X1|>|X2|, then
[0070]
[0071] If |X1|>|X2|>|X3| or |X1|>|X3|>|X2| or |X2|>|X1|>|X3|, then
[0072]
[0073] in:
[0074] X1=X α -A1D α ;
[0075] X2=X β -A2D β ;
[0076] X3=X δ -A3D δ ;
[0077] Where A1, A2 and A3 are distance coefficient vectors; D α , D β , Dδ represents the distance between the wolf pack and α, β and δ; X α , X β and X δ Represent the positions of α, β and δ wolves respectively. Through the above-mentioned gray wolf position update rules, the Euclidean distances X1, X2, and X3 of the three types of leader wolves are calculated according to the positions of α, β and δ wolves relative to ω wolf, and the position update ratio weights g1, g2, and g3 of ω wolf are dynamically adjusted, so that in each iteration, the α wolf closest to the ω wolf step length has a larger weight in the next position update process, followed by the β wolf closer to the ω wolf step length, and the δ wolf farther from the ω wolf step length has the lowest weight, so as to improve the effectiveness of solving complex and high-dimensional problems.
[0078] The karst groundwater pollution status assessment step is a comprehensive assessment based on the optimal assessment parameters. The karst groundwater pollution status assessment step includes: a weight acquisition sub-step, which obtains the weight of the optimal assessment parameter through the hierarchical analysis method; an optimal assessment parameter replacement sub-module, which replaces the optimal assessment parameter according to the correlation mark when the optimal assessment parameter cannot be obtained or the acquisition cost exceeds the threshold; a comprehensive assessment sub-module, which performs weighted summation based on the weight of the optimal assessment parameter to obtain the final evaluation result, so as to improve the efficiency of the karst groundwater pollution status assessment.
[0079] It also includes a karst groundwater pollution status assessment system, which uses the karst groundwater pollution status assessment method.
[0080] The above is only an embodiment of the present invention, and the common knowledge such as the known specific technical solutions and / or characteristics in the solution is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical solution of the present invention, several modifications and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.
Claims
1. A method for assessing the contamination status of karst groundwater, characterized in that: include: An assessment target acquisition step is to acquire assessment targets of karst groundwater pollution, wherein the assessment targets include health, economy, society, water supply system, and ecological environment; Data acquisition step: comprehensively acquire the parameters for karst groundwater pollution status assessment based on the assessment objectives; The model creation and update step is based on the evaluation target, using the Gray Wolf Optimization Algorithm to take the evaluation parameters as the optimization target, creating an evaluation parameter optimization model, and iterating based on the evaluation parameter optimization model to obtain the optimal evaluation parameters; The steps of karst groundwater pollution status assessment are comprehensively evaluated based on the optimal assessment parameters.
2. The karst groundwater pollution status assessment method according to claim 1, characterized in that: The data acquisition step comprises: An evaluation scope acquisition sub-step, acquiring the evaluation scope according to a preset scope mapping rule based on the evaluation target; In the data acquisition layout sub-step, based on the assessment objectives, the key influencing positions are obtained, and starting from the key influencing positions, the data acquisition positions are determined by increasing the analysis in sequence according to the radiation distance ratio.
3. The method for assessing karst groundwater pollution status according to claim 1, characterized in that , the data acquisition step also includes: The data preprocessing sub-step is to clean and standardize the collected data; The feature extraction sub-step converts the preprocessed data into assessment data of the karst groundwater pollution status.
4. The method for assessing karst groundwater pollution status according to claim 1, characterized in that: The model creation and updating steps include: Initialization substep, initializing the position of the gray wolf population as a combination vector of evaluation parameters; The fitness function determination sub-step determines the fitness function expression according to the evaluation target benefit; The model iterative update submodule calculates the individual fitness of all gray wolves, and takes the top three gray wolves in fitness as α, β and δ wolves in turn, and the rest of the gray wolves as ω wolves. The wolf pack updates its position according to α, β and δ wolves. After the maximum number of iterations, the final α wolf position is obtained, and the final α wolf position is used as the optimal evaluation parameter vector combination.
5. The method for assessing karst groundwater pollution status according to claim 4, characterized in that: The fitness function expression is: Among them, τ is the fitness adjustment constant coefficient, θ1, θ2, *θ3 are weight constant coefficients, and v s Get efficiency values for evaluation parameters, z s To evaluate the accuracy of the parameters, s s is the difficulty value of evaluation parameter fusion.
6. The method for assessing karst groundwater pollution status according to claim 1, characterized in that: In the gray wolf optimization algorithm, the convergence factor is updated as follows: Among them, t is the current iteration number, t max is the maximum number of iterations.
7. The method for assessing karst groundwater pollution status according to claim 4, characterized in that: The rules for the location update are: If |X2|>|X3|>|X1| or |X3|>|X2|>|X1| or |X3|>|X1|>|X2|, then If |X1|>|X2|>|X3| or |X1|>|X3|>|X2| or |X2|>|X1|>|X3|, then in: X1=X α -A1D α ; X2=X β -A2D β ; <h2 style=";text-align:left;direction:ltr">X3=X<h2 style=";text-align:left;direction:ltr"> δ <h2 style=";text-align:left;direction:ltr"> -A3D<h2 style=";text-align:left;direction:ltr"> δ <h2 style=";text-align:left;direction:ltr"> ; Where A1, A2 and A3 are distance coefficient vectors; D α , D β , D δ represents the distance between the wolf pack and α, β and δ; X α , X β and X δ Represent the positions of α, β and δ wolves respectively.
8. The method for assessing karst groundwater pollution status according to claim 3, characterized in that: The data acquisition step also includes a correlation analysis sub-step of marking the correlation of the data after the data conversion.
9. The method for assessing karst groundwater pollution status according to claim 8, characterized in that: The karst groundwater pollution status assessment steps include: The weight acquisition sub-step is to obtain the weights of the optimal evaluation parameters through the hierarchical analysis method; The optimal evaluation parameter replacement submodule replaces the optimal evaluation parameter according to the correlation tag when the optimal evaluation parameter cannot be obtained or the acquisition cost exceeds the threshold; The comprehensive evaluation submodule performs weighted summation based on the weights of the optimal evaluation parameters to obtain the final evaluation result.
10. Karst groundwater pollution status assessment system, characterized by: The karst groundwater pollution status assessment method as described in any one of claims 1 to 9 is used.