Water network system chain strengthening method and system

Abstract

The present invention discloses a water network system strong chain method and system, collects research area data, identifies typical years of each subnet in the research area, constructs typical scenarios in the research area, constructs a hydrological and hydrodynamic model to calculate the comprehensive state of the water network system under each typical scenario, and screens out subnets with gaps; calculates the association between each subnet and each water diversion and regulation project; classifies each subnet based on the number of water diversion and regulation projects associated with the subnet, and calculates the demand of each water diversion and regulation project respectively, takes the water diversion and regulation projects that do not meet the demand as checkpoints, and calculates the water diversion and regulation capacity demand of each checkpoint; inputs all checkpoint water diversion and regulation capacity demands into a pre-built expansion optimization model, and solves the model to obtain a water network system strong chain solution. The present invention focuses on analyzing the water diversion and regulation projects in various regions of the water network system in series, and considers more refinement in spatial scale to achieve flood control, water supply, and ecological security in water source areas and receiving areas.

Description

Technical Field

[0001] The invention relates to a water network system chain strengthening method. Background Art

[0002] The water network system is a comprehensive system based on natural rivers and lakes, with diversion and drainage projects as channels, storage projects as nodes, and intelligent regulation as a means. It integrates the functions of optimizing water resources allocation, flood control and disaster reduction in river basins, and protection of water ecosystems. It is an effective measure to solve the uneven spatial distribution of water resources, improve the water resources guarantee rate in the receiving areas, alleviate the contradiction between water supply and demand in water-scarce areas, and achieve rational allocation of water resources. It is an important way to promote economic development and comprehensive development and utilization of water resources in water-scarce areas.

[0003] After the overall structure, networking and network supplementation of the water network system, it is necessary to analyze the outline of the serial water network system in more detail to determine whether there is a bottleneck and strengthen it, that is, to strengthen the chain of the water network system. How to identify the relationship between the subnetwork and the water diversion and regulation project, calculate the water diversion and regulation capacity requirements of the checkpoints, and propose the optimal solution for strengthening the water network chain are key technical issues in strengthening the water network chain. At present, there is no complete technical method to solve the above problems.

[0004] The present invention proposes a water network system chain strengthening method and system, identifies the association between subnetworks and water diversion and regulation projects, calculates the gate requirements, and adopts measures such as channel heightening, river channel deepening and widening, pump station renewal and transformation, pump station capacity expansion, new pump station construction, gate renewal and transformation, and new gate construction according to the type of water diversion and regulation projects, and proposes a water network system chain strengthening plan that takes into account both the gate improvement degree and the gate expansion cost. Summary of the invention

[0005] The purpose of the invention is to provide a water network system strengthening method to solve the above problems existing in the prior art. On the other hand, a water network system strengthening system is provided.

[0006] Technical solution: Water network system strong chain method, including the following steps:

[0007] Step S1, collect data of the study area, identify typical years of each subnet in the study area, construct typical scenarios of the study area, construct a hydrological and hydrodynamic model to calculate the comprehensive status of the water network system under each typical scenario, and screen out subnets with gaps;

[0008] Step S2: using improved Euclidean distance to calculate the association between each subnet and each water diversion project;

[0009] Step S3: Based on the number of water diversion and regulation projects associated with the subnet, each subnet is divided into two categories, namely, a subnet class associated with a single water diversion and regulation project and a subnet class associated with multiple water diversion and regulation projects, and the demand of each water diversion and regulation project is calculated respectively, and the water diversion and regulation projects that do not meet the demand are used as checkpoints to obtain the water diversion and regulation capacity demand of each checkpoint;

[0010] Step S4: input the water diversion capacity requirements of all checkpoints into the pre-built checkpoint expansion optimization model, use multiple artificial intelligence algorithms to solve the model, obtain a non-inferior solution set, make decisions on the non-inferior solution set, and obtain the optimal solution as a water network system strengthening solution.

[0011] According to one aspect of the present application, step S1 further comprises:

[0012] Step S11, collect data of the study area, extract the typical rainfall year type of each subnet, amplify the rainfall of the typical rainfall year type to once in a hundred years, build a rainfall type optimization model, and solve the model to obtain the rainfall type of once in a hundred years in the study area;

[0013] Step S12, obtaining a typical scenario of the study area based on the cross combination of typical years and once-in-a-century rainfall patterns of each subnet in the study area;

[0014] Step S13: Input the typical scenarios of the study area into the pre-constructed hydrological and hydrodynamic model in sequence, calculate the hydrological and hydrodynamic data of the water network system in the study area under various typical scenarios, calculate the water balance state of each subnet based on the hydrological and hydrodynamic data of the water network system, and extract each subnet with a water gap.

[0015] According to one aspect of the present application, the step S11 is further:

[0016] Step S11a, respectively calculating the comprehensive evaluation results of the entire water network system under the typical rainfall year type of each subnet, and setting a threshold, and selecting all years with comprehensive evaluation results below the threshold as the typical rainfall year type of the entire water network;

[0017] Step S11b, fitting rainfall distribution based on historical rainfall and water level data, and calculating the once-in-a-century rainfall;

[0018] Step S11c, constructing a rain pattern optimization model, the objective function is that the rain pattern and the water level process are most similar, and the constraint condition is the rainfall that occurs once in a hundred years;

[0019] Step S11d: Use the improved GA algorithm to solve the rain pattern optimization model and obtain the once-in-a-century rain pattern in the study area.

[0020] According to one aspect of the present application, step S2 further comprises:

[0021] Step S21, collecting water level and flow data of each subnet with water gap and operation data of water diversion and regulation projects related to the subnet;

[0022] Step S22: using improved Euclidean distance to calculate the distance between each subnet and each water diversion project associated with it;

[0023] Step S23, calculate the similarity between each water diversion project and the subnets not related to it in turn, obtain similar subnets and calculate the Euclidean distance from the water diversion project to each similar subnet, and set the maximum value as the threshold.

[0024] According to one aspect of the present application, step S22 is further:

[0025] Step S22a, setting a time lag t and a time series length of the test to T, where t and T are positive numbers;

[0026] Step S22b, constructing a time-delay optimization model, with the objective function being the minimum Euclidean distance and the constraint being that t is between 0 and T / 2;

[0027] Step S22c, using an improved dynamic programming algorithm to solve the model and obtain the minimum Euclidean distance, which is the distance from the subnet to the water diversion project.

[0028] According to one aspect of the present application, step S23 is further:

[0029] Step S23a, using an improved meta-analysis method to construct an indicator system describing the water level process;

[0030] Step S23b: Determine the weights using a weight optimization method, construct a weight optimization model, and obtain an optimal weight combination scheme;

[0031] Step S23c, calculating similar subnets based on the weight combination scheme and calculating the Euclidean distance from the water diversion project to each similar subnet;

[0032] Step S23d: Select the value with the largest Euclidean distance as the threshold.

[0033] According to one aspect of the present application, step S3 further comprises:

[0034] Step S31: for the subnets in the subnet class associated with a single water diversion and regulation project, the subnet gaps are respectively superimposed on the associated water diversion and regulation projects, the demands of each water diversion and regulation project are respectively calculated, and the water diversion and regulation projects that do not meet the demands are used as checkpoints to obtain the water diversion and regulation capacity demands of each checkpoint;

[0035] Step S32: for the subnets in the subnet class associated with multiple water diversion and regulation projects, calculate the demands of each water diversion and regulation project associated with the subnet respectively and input the pre-built multi-objective optimization allocation model, solve the model, and obtain the demands of each checkpoint.

[0036] According to one aspect of the present application, step S32 is further:

[0037] Step S32a, respectively calculating the demand of each water diversion and regulation project;

[0038] Step S32b, constructing a multi-objective optimization allocation model, the objective function is: minimum number of bayonet ports and minimum restricted capacity;

[0039] Step S32c, assigning weights to the minimum number of checkpoints and the minimum restricted capacity based on cost-effectiveness, and weighting the two goals into one goal;

[0040] Step S32d, solving the multi-objective optimization allocation model to obtain the requirements of each checkpoint.

[0041] According to one aspect of the present application, step S4 is further:

[0042] Step S41, constructing a multi-objective optimization model, the objective function of which is: optimal improvement of the card slot and minimum card expansion cost;

[0043] Step S42, coupling the multi-objective optimization model with the water network hydrological and hydrodynamic simulation model to obtain a card expansion optimization model;

[0044] Step S43: Based on different types of water diversion and regulation projects, various engineering measures are taken as constraints of the expansion optimization model, and the engineering measures include: channel heightening, river channel deepening and widening, pump station renewal, transformation, pump station capacity expansion, new pump station construction, gate renewal, transformation, and new gate construction;

[0045] Step S44: Use multiple artificial intelligence algorithms to solve the card expansion optimization model, obtain a non-inferior solution set, make decisions on the non-inferior solution set, and obtain the optimal solution as a water network system chain strengthening solution.

[0046] According to another aspect of the present application, a water network system strong chain system is provided, comprising:

[0047] at least one processor; and

[0048] a memory communicatively connected to at least one of the processors; wherein,

[0049] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the water network system strong link method described in any of the above technical solutions.

[0050] Beneficial effects: The water network system strengthening method can reduce the flood control pressure downstream of the water source area while increasing the water resource supply in the receiving area, thereby achieving flood control, water supply and ecological security in the water source area and the receiving area. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flow chart of the present invention.

[0052] Figure 2 It is a flow chart of step S1 of the present invention.

[0053] Figure 3 It is a flow chart of step S2 of the present invention.

[0054] Figure 4 It is a flow chart of step S3 of the present invention.

[0055] Figure 5 It is a flow chart of step S4 of the present invention. DETAILED DESCRIPTION

[0056] like Figure 1 According to one aspect of the present application, a water network system strengthening method is provided, characterized in that it includes the following steps:

[0057] Step S1, collect data of the study area, identify typical years of each subnet in the study area, construct typical scenarios of the study area, construct a hydrological and hydrodynamic model to calculate the comprehensive status of the water network system under each typical scenario, and screen out subnets with gaps;

[0058] Step S2: using improved Euclidean distance to calculate the association between each subnet and each water diversion project;

[0059] Step S3: Based on the number of water diversion and regulation projects associated with the subnet, each subnet is divided into two categories, namely, a subnet class associated with a single water diversion and regulation project and a subnet class associated with multiple water diversion and regulation projects, and the demand of each water diversion and regulation project is calculated respectively, and the water diversion and regulation projects that do not meet the demand are used as checkpoints to obtain the water diversion and regulation capacity demand of each checkpoint;

[0060] Step S4: input the water diversion capacity requirements of all checkpoints into the pre-built checkpoint expansion optimization model, use multiple artificial intelligence algorithms to solve the model, obtain a non-inferior solution set, make decisions on the non-inferior solution set, and obtain the optimal solution as a water network system strengthening solution.

[0061] The present invention analyzes the state of the water network system after networking and network supplementation, that is, the water supply safety, flood control safety, and ecological safety of the water network system. Aiming at the state of the water network system after networking and network supplementation, the present invention focuses on analyzing the water diversion and regulation projects of various internal areas of the water network system in series. This is mainly because there may be many restrictive factors in newly built water diversion and regulation projects, such as land occupation, immigration, ecology and other restrictive factors, so the present invention analyzes the existing water diversion and regulation projects.

[0062] In this embodiment, the focus is on the water source area and the receiving area, and the time scales include long, medium, short and real-time. The long, medium, short and real-time mainly consider the two factors of water supply security and ecological security. In the short term, there is also a new goal, which is to divert the flood in the water source area to reduce the flood control pressure downstream of the water source area. At the same time, it can also increase the water resource supply in the receiving area, that is, reduce the water supply pressure and ecological pressure. According to the flow capacity of each key section within the water diversion project, the capacity of the water diversion gate and the corresponding projects along the line, it is analyzed whether the existing water diversion project can be used to achieve flood control, water supply and ecological security in the water source area and the receiving area. If it cannot be achieved, it can be considered to expand the local checkpoint, such as making the section wider or higher. If it is a water lifting project, the water lifting capacity of the pump station will be increased.

[0063] For water network systems involving multiple water diversion and regulation projects, analysis is conducted on multiple water diversion and regulation projects based on the analysis of a single water diversion and regulation project to determine whether they have the same water source area based on the three goals of water supply, flood control, and ecology. In this way, flood control pressure in the water source area can be reduced simultaneously in the upstream and downstream areas, or a flood control and dispatching system for the upstream and downstream areas of the water source area can be constructed to achieve coordinated allocation in the upstream and downstream areas. For ecological security, while ensuring the ecological security of the water source area, a coordinated consideration is given to the ecological security of the upstream and downstream areas of the water source area. Alternatively, if there is a regional water system connection project in the receiving area, the water can be transported there by gravity first, and then the water can be diverted to the receiving area through water diversion and regulation projects.

[0064] According to one aspect of the present application, step S1 further comprises:

[0065] Step S11, collect data of the study area, extract the typical rainfall year type of each subnet, amplify the rainfall of the typical rainfall year type to once in a hundred years, build a rainfall type optimization model, and solve the model to obtain the rainfall type of once in a hundred years in the study area;

[0066] Step S12, obtaining a typical scenario of the study area based on the cross combination of typical years and once-in-a-century rainfall patterns of each subnet in the study area;

[0067] Step S13: Input the typical scenarios of the study area into the pre-constructed hydrological and hydrodynamic model in sequence, calculate the hydrological and hydrodynamic data of the water network system in the study area under various typical scenarios, calculate the water balance state of each subnet based on the hydrological and hydrodynamic data of the water network system, and extract each subnet with a water gap.

[0068] The entire water network system covers a vast area, spanning different river basins and different climate zones. Therefore, each boundary condition will have different statistical characteristics. For example, the water network can be divided into three sub-networks: A, B, and C.

[0069] For flood control, the most unfavorable typical rainfall pattern for flood control of each subnet is different. For example, A is the 1990 pattern, B is the 2000 pattern, and C is the 2010 pattern. The rainfall in different 50-year return periods is also different. For example, if a 50-year return period is constructed based on the most unfavorable flood control situation of the entire water network, if the most unfavorable rainfall patterns of the three subnets are spliced ​​separately, it is definitely safe excess, which will lead to the subsequent scheme being uneconomical. Therefore, in this embodiment, the rainfall patterns of different subnets are coordinated and the rainfall pattern of that year is enlarged to 100-year return period;

[0070] For water supply, the water level at the water level station is the main factor, so in this embodiment, the annual type of water supply and flood control are combined and called a typical year.

[0071] According to one aspect of the present application, the step S11 is further:

[0072] Step S11a, respectively calculating the comprehensive evaluation results of the entire water network system under the typical rainfall year type of each subnet, and setting a threshold, and selecting all years with comprehensive evaluation results below the threshold as the typical rainfall year type of the entire water network;

[0073] Step S11b, fitting rainfall distribution based on historical rainfall and water level data, and calculating the once-in-a-century rainfall;

[0074] Step S11c, constructing a rain pattern optimization model, the objective function is that the rain pattern and the water level process are most similar, and the constraint condition is the rainfall that occurs once in a hundred years;

[0075] Step S11d: Use the improved GA algorithm to solve the rain pattern optimization model and obtain the once-in-a-century rain pattern in the study area.

[0076] GA algorithm is an optimization algorithm based on selection and genetics, which is widely used in various fields. However, GA algorithm has the disadvantages of slow convergence, premature convergence, parameter sensitivity, uneven fitness distribution and complex solution encoding. Therefore, in this embodiment, GA algorithm is improved to solve the rain-type optimization model by dynamically adjusting parameters, using multiple selection strategies, introducing local search, increasing population diversity and adopting hierarchical genetic algorithm. Specifically:

[0077] Dynamically adjust GA control parameters through adaptive mechanisms to adapt to different search stages, promote faster convergence and avoid premature convergence;

[0078] Combine different selection mechanisms to enhance the diversity and effectiveness of selection;

[0079] In each generation of GA evolution, a local search algorithm is introduced to fine-tune the optimal individuals to improve the quality of the solution;

[0080] Regularly introduce new individuals to maintain population diversity and avoid premature convergence;

[0081] Divide the population into several groups, allow each sub-group to evolve independently, and regularly exchange information between sub-groups to increase the breadth of the search.

[0082] According to one aspect of the present application, step S2 further comprises:

[0083] Step S21, collecting water level and flow data of each subnet with water gap and operation data of water diversion and regulation projects related to the subnet;

[0084] Step S22: using improved Euclidean distance to calculate the distance between each subnet and each water diversion project associated with it;

[0085] In this embodiment, considering that the water diversion and regulation effect has a time lag, the improved Euclidean distance is used to calculate the lag correlation.

[0086] Step S23, calculate the similarity between each water diversion project and the subnets not related to it in turn, obtain similar subnets and calculate the Euclidean distance from the water diversion project to each similar subnet, and set the maximum value as the threshold.

[0087] According to one aspect of the present application, step S22 is further:

[0088] Step S22a, setting a time lag t and a time series length of the test to T, where t and T are positive numbers;

[0089] Step S22b, constructing a time-delay optimization model, with the objective function being the minimum Euclidean distance and the constraint being that t is between 0 and T / 2;

[0090] Step S22c, using an improved dynamic programming algorithm to solve the model and obtain the minimum Euclidean distance, which is the distance from the subnet to the water diversion project.

[0091] In this embodiment, an improved dynamic programming algorithm is used to find the global optimal solution compared to the commonly used GA and PSO algorithms, specifically:

[0092] For state transitions that only depend on the previous state, use a set of arrays or simple variables to replace the two-bit array to reduce space complexity;

[0093] For recursive dynamic programming, use memoized search to store the results of the calculated subproblems in an array so that the results can be returned directly when called later;

[0094] Build up the solution incrementally, reducing the size of the state space;

[0095] Divide and conquer large problems into smaller parts, solve these parts using dynamic programming and then merge the results;

[0096] Heuristic strategies are added to dynamic programming to effectively prune the state space and reduce unnecessary calculations.

[0097] According to one aspect of the present application, step S23 is further:

[0098] Step S23a, using an improved meta-analysis method to construct an indicator system describing the water level process;

[0099] Meta-analysis is a statistical method used to combine the results of multiple independent studies to obtain a more accurate estimate of the overall effect. The traditional meta-analysis method has defects in heterogeneity, publication bias, data quality and model selection. Therefore, in this embodiment, the validity and reliability of the results are enhanced by improving the meta-analysis method, specifically:

[0100] Heterogeneity was handled through sensitivity analysis, subgroup analysis, and meta-regression analysis;

[0101] Systematic search of all relevant studies, including unpublished studies and grey literature, visual review and analysis of studies to identify publication bias, and adjustments to address publication bias;

[0102] Use consistent tools to assess the quality of included studies to ensure the reliability of the results, and evaluate and compare the methodological quality of each study before inclusion in the meta-analysis;

[0103] Use advanced statistical methods, improve study inclusion criteria, implement prospective registries, and employ machine learning and data mining to improve meta-analysis.

[0104] Step S23b: Determine the weights using a weight optimization method, construct a weight optimization model, and obtain an optimal weight combination scheme;

[0105] Step S23c, calculating similar subnets based on the weight combination scheme and calculating the Euclidean distance from the water diversion project to each similar subnet;

[0106] Step S23d: Select the value with the largest Euclidean distance as the threshold.

[0107] According to one aspect of the present application, step S3 further comprises:

[0108] Step S31: for the subnets in the subnet class associated with a single water diversion and regulation project, the subnet gaps are respectively superimposed on the associated water diversion and regulation projects, the demands of each water diversion and regulation project are respectively calculated, and the water diversion and regulation projects that do not meet the demands are used as checkpoints to obtain the water diversion and regulation capacity demands of each checkpoint;

[0109] Step S32: for the subnets in the subnet class associated with multiple water diversion and regulation projects, calculate the demands of each water diversion and regulation project associated with the subnet respectively and input the pre-built multi-objective optimization allocation model, solve the model, and obtain the demands of each checkpoint.

[0110] According to one aspect of the present application, step S32 is further:

[0111] Step S32a, respectively calculating the demand of each water diversion and regulation project;

[0112] Step S32b, constructing a multi-objective optimization allocation model, the objective function is: minimum number of bayonet ports and minimum restricted capacity;

[0113] Step S32c, assigning weights to the minimum number of checkpoints and the minimum restricted capacity based on cost-effectiveness, and weighting the two goals into one goal;

[0114] In a certain embodiment, there are two projects, A and B, whose capacity can be increased to meet the demand. Project A currently has a surplus capacity of 100, and Project B has reached a bottleneck and needs to build 100.

[0115] When the demand is less than 100, all is counted on A;

[0116] When the demand is 101, or the part greater than 100 is very small, 100 is counted in Project A, and the rest in Project B;

[0117] When the demand is 150, that is, the part greater than 100 is too large, because the marginal benefit is getting smaller and smaller, it is more appropriate for A to build an additional 50 than to expand B by another 50 on the basis of expanding 100.

[0118] Step S32d, solving the multi-objective optimization allocation model to obtain the requirements of each checkpoint.

[0119] According to one aspect of the present application, step S4 is further:

[0120] Step S41, constructing a multi-objective optimization model, the objective function of which is: optimal improvement of the card slot and minimum card expansion cost;

[0121] Step S42, coupling the multi-objective optimization model with the water network hydrological and hydrodynamic simulation model to obtain a card expansion optimization model;

[0122] Step S43: Based on different types of water diversion and regulation projects, various engineering measures are taken as constraints of the expansion optimization model, and the engineering measures include: channel heightening, river channel deepening and widening, pump station renewal, transformation, pump station capacity expansion, new pump station construction, gate renewal, transformation, and new gate construction;

[0123] Step S44: Use multiple artificial intelligence algorithms to solve the card expansion optimization model, obtain a non-inferior solution set, make decisions on the non-inferior solution set, and obtain the optimal solution as a water network system chain strengthening solution.

[0124] The present invention improves the overall resilience and responsiveness of the water network system through scientific model construction and analysis. First, typical years are innovatively identified, and typical scenarios are constructed based on them, so as to intuitively reflect the comprehensive status of the water network system under different hydrological conditions. Then, a hydrological and hydrodynamic model is constructed to calculate in detail the operating status of the water network system under each typical scenario, and then the subnetworks with gaps are screened out. In this process, the correlation between each subnetwork and the water diversion and regulation project is calculated and analyzed, the needs of each water diversion and regulation project are quantitatively calculated to find the checkpoints, and finally, the water diversion and regulation capacity requirements of all checkpoints are calculated by constructing an expansion optimization model to obtain a water network system chain strengthening solution.

[0125] According to another aspect of the present application, a water network system strong chain system is provided, characterized in that it includes:

[0126] at least one processor; and

[0127] a memory communicatively connected to at least one of the processors; wherein,

[0128] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement any of the above-mentioned water network system strengthening methods.

[0129] The preferred embodiments of the present invention are described in detail above; however, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. A water network system strengthening method, It is characterized in that The steps include: Step S1, collect data of the study area, identify typical years of each subnet in the study area, construct typical scenarios of the study area, construct a hydrological and hydrodynamic model to calculate the comprehensive status of the water network system under each typical scenario, and screen out subnets with gaps; Step S2: using improved Euclidean distance to calculate the association between each subnet and each water diversion project; Step S3: Based on the number of water diversion and regulation projects associated with the subnet, each subnet is divided into two categories, namely, a subnet class associated with a single water diversion and regulation project and a subnet class associated with multiple water diversion and regulation projects, and the demand of each water diversion and regulation project is calculated respectively, and the water diversion and regulation projects that do not meet the demand are used as checkpoints to obtain the water diversion and regulation capacity demand of each checkpoint; Step S4: input the water diversion capacity requirements of all checkpoints into the pre-built checkpoint expansion optimization model, use multiple artificial intelligence algorithms to solve the model, obtain a non-inferior solution set, make decisions on the non-inferior solution set, and obtain the optimal solution as a water network system strengthening solution; The step S1 is further as follows: Step S11, collect data of the study area, extract the typical rainfall year type of each subnet, amplify the rainfall of the typical rainfall year type to once in a hundred years, build a rainfall type optimization model, and solve the model to obtain the rainfall type of once in a hundred years in the study area; Step S12, obtaining a typical scenario of the study area based on the cross combination of typical years and once-in-a-century rainfall patterns of each subnet in the study area; Step S13, input the typical scenarios of the study area into the pre-built hydrological and hydrodynamic model in sequence, calculate the hydrological and hydrodynamic data of the water network system in the study area under each typical scenario, calculate the water balance state of each subnet based on the hydrological and hydrodynamic data of the water network system, and extract each subnet with a water gap; The step S2 is further as follows: Step S21, collecting water level and flow data of each subnet with water gap and operation data of water diversion and regulation projects related to the subnet; Step S22: using improved Euclidean distance to calculate the distance between each subnet and each water diversion project associated with it; Step S23, calculate the similarity between each water diversion project and the subnets not related to it in turn, obtain similar subnets and calculate the Euclidean distance from the water diversion project to each similar subnet, and set the maximum value as the threshold.

2. The water network system strengthening method according to claim 1, It is characterized in that The step S11 is further as follows: Step S11a, respectively calculating the comprehensive evaluation results of the entire water network system under the typical rainfall year type of each subnet, and setting a threshold, and selecting all years with comprehensive evaluation results below the threshold as the typical rainfall year type of the entire water network; Step S11b, fitting rainfall distribution based on historical rainfall and water level data, and calculating the once-in-a-century rainfall; Step S11c, constructing a rain pattern optimization model, the objective function is that the rain pattern and the water level process are most similar, and the constraint condition is the rainfall that occurs once in a hundred years; Step S11d: Use the improved GA algorithm to solve the rain pattern optimization model and obtain the once-in-a-century rain pattern in the study area.

3. The water network system strengthening method as claimed in claim 2, It is characterized in that The step S22 is further as follows: Step S22a, setting a time lag t and a time series length of the test to T, where t and T are positive numbers; Step S22b, constructing a time-delay optimization model, with the objective function being the minimum Euclidean distance and the constraint being that t is between 0 and T / 2; Step S22c, using an improved dynamic programming algorithm to solve the model and obtain the minimum Euclidean distance, which is the distance from the subnet to the water diversion project.

4. The water network system strengthening method according to claim 1, It is characterized in that The step S23 is further as follows: Step S23a, using an improved meta-analysis method to construct an indicator system describing the water level process; Step S23b: Determine the weights using a weight optimization method, construct a weight optimization model, and obtain an optimal weight combination scheme; Step S23c, calculating similar subnets based on the weight combination scheme and calculating the Euclidean distance from the water diversion project to each similar subnet; Step S23d: Select the value with the largest Euclidean distance as the threshold.

5. The water network system strengthening method according to claim 1, It is characterized in that The step S3 is further as follows: Step S31: for the subnets in the subnet class associated with a single water diversion and regulation project, the subnet gaps are respectively superimposed on the associated water diversion and regulation projects, the demands of each water diversion and regulation project are respectively calculated, and the water diversion and regulation projects that do not meet the demands are used as checkpoints to obtain the water diversion and regulation capacity demands of each checkpoint; Step S32: for the subnets in the subnet class associated with multiple water diversion and regulation projects, calculate the demands of each water diversion and regulation project associated with the subnet respectively and input the pre-built multi-objective optimization allocation model, solve the model, and obtain the demands of each checkpoint.

6. The water network system strengthening method as claimed in claim 5, It is characterized in that The step S32 is further as follows: Step S32a, respectively calculating the demand of each water diversion and regulation project; Step S32b, constructing a multi-objective optimization allocation model, the objective function is: minimum number of bayonet ports and minimum restricted capacity; Step S32c, assigning weights to the minimum number of checkpoints and the minimum restricted capacity based on cost-effectiveness, and weighting the two goals into one goal; Step S32d, solving the multi-objective optimization allocation model to obtain the requirements of each checkpoint.

7. The water network system strengthening method according to claim 1, It is characterized in that The step S4 is further as follows: Step S41, constructing a multi-objective optimization model, the objective function of which is: optimal improvement of the card slot and minimum card expansion cost; Step S42, coupling the multi-objective optimization model with the water network hydrological and hydrodynamic simulation model to obtain a card expansion optimization model; Step S43: Based on different types of water diversion and regulation projects, various engineering measures are taken as constraints of the expansion optimization model, and the engineering measures include: channel heightening, river channel deepening and widening, pump station renewal, pump station renovation, pump station capacity expansion, new pump station construction, gate renewal, gate renovation and new gate construction; Step S44: Use multiple artificial intelligence algorithms to solve the card expansion optimization model, obtain a non-inferior solution set, make decisions on the non-inferior solution set, and obtain the optimal solution as a water network system chain strengthening solution.

8. A water network system strong chain system, It is characterized in that include: at least one processor; as well as a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the water network system strengthening method described in any one of claims 1 to 7.

Images