Water network system replenishment method and system

Abstract

The present invention discloses a method and system for replenishing a water network system. The method comprises the following steps: classifying and combining subnetworks, calculating the comprehensive evaluation value of each subnetwork and the characteristic value of each subnetwork combination, constructing an optimal projection direction optimization model, calculating the projection value of each subnetwork combination, and extracting the subnetwork combination that needs to be replenished; collecting a set of non-engineering measures and inputting a pre-constructed subnetwork combination non-engineering measures multi-objective optimization model, screening out the optimal non-engineering measures to optimize each subnetwork combination; constructing a combination scheme set of engineering measures, positions of constructible engineering measures, and construction scales and inputting them into a subnetwork combination system dynamics model, obtaining the scheme implementation effect, screening out the optimal scheme to replenish each subnetwork combination; collecting a set of non-engineering measures and inputting them into a subnetwork combination non-engineering measures multi-objective optimization model, screening out the optimal non-engineering measures to optimize each subnetwork combination. The present invention can effectively regulate the supply and demand relationship of water resources, improve resource utilization efficiency, and promote sustainable utilization of water resources.

Description

Technical Field

[0001] The invention relates to a water network system repair 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 water network system is connected to the network, there may still be local areas where the coordinated balance of water resources, ecological environment, economy and society cannot be achieved. At this time, it is necessary to further supplement the water network while it is connected to the network to make the water network denser. In the process of supplementing the network, how to locate the areas that need to be supplemented, how to quantify the demand for supplementation, and how to determine the optimal supplementation plan are all questions that cannot be answered or solved by existing technologies.

[0004] The present invention proposes a water network system replenishment method and system, locates water network gaps, identifies network replenishment needs, and proposes a gradually optimized network replenishment method that nests non-engineering-engineering-non-engineering measures, further improving the systematicity, comprehensiveness, and resilience of the water network. Summary of the invention

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

[0006] Technical solution: A water network system replenishment method, comprising the following steps:

[0007] Step S1, collect the data of each subnet in the study area, classify and combine the subnets based on the subnet requirements, obtain four types of subnet combinations, calculate the comprehensive evaluation value of each subnet and the characteristic value of each subnet combination, build the best projection direction optimization model, use a variety of intelligent algorithms to solve the model, obtain the projection value of each subnet combination, that is, the comprehensive evaluation result of the subnet combination, and extract the subnet combination that needs to be supplemented;

[0008] Step S2: Based on the requirements of each subnet combination, a set of non-engineering measures is collected and input into a pre-built subnet non-engineering measures multi-objective optimization model, the optimal non-engineering measures are selected to optimize each subnet combination, and the optimized subnet combination requirements are calculated;

[0009] Step S3, collect the engineering measure set and construct the correlation between the optimized subnet combination demand and the engineering measure, obtain the measure set corresponding to the demand, identify the combination scheme set of engineering measures, the location of the buildable engineering measure and the construction scale, input it into the subnet combination system dynamics model, obtain the scheme implementation effect, and select the optimal scheme to supplement each subnet combination;

[0010] Step S4: Based on the requirements of each subnet combination after the engineering measures are optimized, a non-engineering measures set is collected and input into the subnet combination non-engineering measures multi-objective optimization model, and the optimal non-engineering measures are selected to optimize each subnet combination.

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

[0012] Step S11, collect data of each subnet in the study area, including the characteristic values ​​of water resources supply, water disaster security, water ecological health and the needs of the subnet;

[0013] Step S12: based on the needs of each subnet, the subnets are divided into three categories: flood control group, water supply group and ecological group. The subnets in the three groups are combined in pairs and in triplets to obtain four subnet combinations, including flood control and water supply combination, flood control and ecological combination, water supply and ecological combination and flood control, water supply, ecological combination;

[0014] Step S13, extracting the characteristic values ​​of a water resource supply, b water disaster security and c water ecological health of each subnet, taking the characteristic value of a+b+c of each subnet in the subnet combination as the coordinate of the subnet in the a+b+c dimensional space, obtaining the a+b+c dimensional space composed of each subnet point in the subnet combination, calculating the coordinate of the center of gravity of the a+b+c dimensional space as the a+b+c characteristic value of the subnet combination, where a, b and c are all positive integers;

[0015] Step S14, extracting the weights of the water network comprehensive evaluation indicators of the four types of subnetwork combinations, and calculating the comprehensive evaluation value of each subnetwork combination based on the characteristic value of a+b+c of each subnetwork combination and the corresponding water network comprehensive evaluation indicator weight;

[0016] Step S15: input the characteristic value of a+b+c of each subnet combination into the pre-constructed optimal projection direction optimization model in turn, obtain the projection value as the comprehensive evaluation value of each subnet combination, determine whether the subnet combination meets the water balance based on the comprehensive evaluation value of each subnet combination, and extract the subnet combination that does not meet the water balance.

[0017] According to one aspect of the present application, step S15 is further:

[0018] Step S15a, constructing an optimal projection direction optimization model, wherein the objective function is to minimize the total deviation between the comprehensive characteristic value obtained by projection and the comprehensive evaluation value;

[0019] Step S15b, using a variety of intelligent algorithms to solve the best projection direction optimization model, and obtain the projection directions of the four types of subnet combinations;

[0020] Step S15c, input the characteristic value of a+b+c of the subnet combination into the best projection direction optimization model, project it according to the best projection direction of the subnet combination category to which it belongs, and obtain the projection value as the comprehensive evaluation value of the subnet combination;

[0021] Step S15d: determine whether each subnet combination satisfies the water balance based on the comprehensive evaluation value of the subnet combination, and extract the subnet combinations that do not satisfy the water balance.

[0022] According to one aspect of the present application, step S2 further comprises:

[0023] Step S21, constructing a subnet combination system dynamics model and an optimization scheduling model respectively, and coupling to obtain a subnet combination non-engineering measures multi-objective optimization model;

[0024] Step S22, based on the combined needs of each subnet, a set of non-engineering measures is collected and input into a multi-objective optimization model of the subnet combined non-engineering measures, and a plurality of multi-objective algorithms are used to solve the model to obtain a non-inferior solution set;

[0025] Step S23, using the ideal point method, fuzzy optimization method, and fuzzy matter-element method to jointly decide on the non-inferior solution set, and select the optimal solution of the subnet combination non-engineering measures multi-objective optimization model;

[0026] Step S24: Optimize each subnet combination by using the best non-engineering measures and calculate the optimized subnet combination requirements.

[0027] According to one aspect of the present application, step S3 further comprises:

[0028] Step S31: using an improved meta-analysis method to collect engineering measure sets and input them into a subnet combination system dynamics model to obtain a subnet combination state, and based on the subnet combination state corresponding to each engineering measure, construct an association relationship between the optimized subnet combination demand and the engineering measure to obtain a measure set corresponding to the demand;

[0029] Step S32, identify the combination scheme set of engineering measures, locations of constructible engineering measures and construction scale, and input it into the subnet combination system dynamics model to obtain the scheme implementation effect, that is, the subnet combination state after the scheme is implemented;

[0030] Step S33: Filter out the best solution to supplement each subnet combination.

[0031] According to one aspect of the present application, step S31 is further:

[0032] Step S31a, using subgroup analysis and sensitivity analysis to determine the source of heterogeneity;

[0033] Step S31b, setting a threshold for grey literature to include unpublished research and grey literature;

[0034] Step S31c, combining case studies and interviews to obtain comprehensive background information and implementation details of engineering measures;

[0035] Step S31d: regularly update meta-analysis and collect the latest research results.

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

[0037] Step S32a, classifying the engineering measures based on their effects on different needs into three categories, namely, flood control, water supply and ecology;

[0038] Step S32b, based on different combination modes of subnet combinations, extract corresponding classified engineering measures for combination to obtain a combination scheme set, and identify nodes of each engineering measure in the engineering measure combination that can be constructed by the subnet combination;

[0039] Step S32c: input the measure combination and the subnetwork combination into the subnetwork combination system dynamics model to obtain the subnetwork combination index improvement result, that is, the scheme implementation effect.

[0040] According to one aspect of the present application, step S4 is further:

[0041] Step S41, constructing a non-engineering measure set based on the combined requirements of each subnet after the engineering measure optimization and inputting the subnet combined non-engineering measure multi-objective optimization model to obtain a non-inferior solution set of the subnet combined non-engineering measure multi-objective optimization model;

[0042] Step S42, inputting the non-engineering measures corresponding to the non-inferior solution set of the sub-network combination non-engineering measures multi-objective optimization model into the sub-network combination system dynamics model in sequence to obtain the improvement of the corresponding sub-network combination comprehensive index;

[0043] Step S43: construct a decision model, set an improvement threshold, screen out non-engineering measures whose improvement of the comprehensive index of the subnet combination is greater than the threshold, and optimize the subnet combination.

[0044] According to another aspect of the present application, a water network system replenishment system is provided, comprising:

[0045] at least one processor; and

[0046] a memory communicatively connected to at least one of the processors; wherein,

[0047] 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 replenishment method described in any of the above technical solutions.

[0048] Beneficial effects: The water network system replenishment method is adopted to effectively regulate the supply and demand of water resources, meet different water needs, reduce the risk of water disasters such as floods and droughts, maintain the ecological balance of water bodies, maintain the health of the ecosystem, and maximize the economic benefits of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of the present invention.

[0050] Figure 2 It is a flow chart of step S1 of the present invention.

[0051] Figure 3 It is a flow chart of step S2 of the present invention.

[0052] Figure 4 It is a flow chart of step S3 of the present invention.

[0053] Figure 5 It is a flow chart of step S4 of the present invention. DETAILED DESCRIPTION

[0054] like Figure 1 According to one aspect of the present application, a water network system replenishment method is provided, characterized in that it includes the following steps:

[0055] Step S1, collect the data of each subnet in the study area, classify and combine the subnets based on the subnet requirements, obtain four types of subnet combinations, calculate the comprehensive evaluation value of each subnet and the characteristic value of each subnet combination, build the best projection direction optimization model, use a variety of intelligent algorithms to solve the model, obtain the projection value of each subnet combination, that is, the comprehensive evaluation result of the subnet combination, and extract the subnet combination that needs to be supplemented;

[0056] Step S2: Based on the requirements of each subnet combination, a set of non-engineering measures is collected and input into a pre-built subnet non-engineering measures multi-objective optimization model, the optimal non-engineering measures are selected to optimize each subnet combination, and the optimized subnet combination requirements are calculated;

[0057] Step S3, collect the engineering measure set and construct the correlation between the optimized subnet combination demand and the engineering measure, obtain the measure set corresponding to the demand, identify the combination scheme set of engineering measures, the location of the buildable engineering measure and the construction scale, input it into the subnet combination system dynamics model, obtain the scheme implementation effect, and select the optimal scheme to supplement each subnet combination;

[0058] Step S4: Based on the requirements of each subnet combination after the engineering measures are optimized, a non-engineering measures set is collected and input into the subnet combination non-engineering measures multi-objective optimization model, and the optimal non-engineering measures are selected to optimize each subnet combination.

[0059] Different from the commonly used water network optimization methods, the present invention firstly selects a variety of non-engineering measures to optimize the subnets according to the calculated needs of each subnet, and selects the best solution for final optimization according to the optimization results, and then calculates the needs of the optimized subnets respectively to optimize the next step of engineering measures;

[0060] Since non-engineering measures cannot meet the demand, the next step is to optimize the subnet by building a project. First, establish the relationship between demand and measures, obtain the measure set corresponding to the demand, and then directly call it. When the measures built cannot fully meet the demand, the scale cannot be expanded blindly. It is necessary to calculate the inflection point of benefit-cost, optimize the engineering measures at the inflection point, and calculate the optimized subnet demand to optimize the next step of non-engineering measures.

[0061] After the project is completed, the subnet as a whole is optimized by non-engineering measures to obtain the optimal operation plan under the current status, and the subnet status is evaluated again.

[0062] In this embodiment, an optimization method of nesting non-engineering-engineering-non-engineering measures within the subnet is adopted, which can maximize the optimization of the subnet at the minimum construction cost.

[0063] According to one aspect of the present application, step S1 further comprises:

[0064] Step S11, collect data of each subnet in the study area, including the characteristic values ​​of water resources supply, water disaster security, water ecological health and the needs of the subnet;

[0065] Step S12: based on the needs of each subnet, the subnets are divided into three categories: flood control group, water supply group and ecological group. The subnets in the three groups are combined in pairs and in triplets to obtain four subnet combinations, including flood control and water supply combination, flood control and ecological combination, water supply and ecological combination and flood control, water supply, ecological combination;

[0066] Step S13, extracting the characteristic values ​​of a water resource supply, b water disaster security and c water ecological health of each subnet, taking the characteristic value of a+b+c of each subnet in the subnet combination as the coordinate of the subnet in the a+b+c dimensional space, obtaining the a+b+c dimensional space composed of each subnet point in the subnet combination, calculating the coordinate of the center of gravity of the a+b+c dimensional space as the a+b+c characteristic value of the subnet combination, where a, b and c are all positive integers;

[0067] Step S14, extracting the weights of the water network comprehensive evaluation indicators of the four types of subnetwork combinations, and calculating the comprehensive evaluation value of each subnetwork combination based on the characteristic value of a+b+c of each subnetwork combination and the corresponding water network comprehensive evaluation indicator weight;

[0068] In this embodiment, each river is weighted by the length and flow of each river in each subnet, and characteristic values ​​of a water resource supply, b water disaster security and c water ecological health of each subnet are calculated;

[0069] The status of each subnet combination is calculated based on the a+b+c eigenvalue of each subnet combination and the a+b+c eigenvalue of each subnet, and the weight of each indicator value is obtained. The comprehensive evaluation value of each subnet combination is obtained by calculating the product of each eigenvalue and its weight value and summing them up.

[0070] Step S15: input the characteristic value of a+b+c of each subnet combination into the pre-constructed optimal projection direction optimization model in turn, obtain the projection value as the comprehensive evaluation value of each subnet combination, determine whether the subnet combination meets the water balance based on the comprehensive evaluation value of each subnet combination, and extract the subnet combination that does not meet the water balance.

[0071] According to one aspect of the present application, step S15 is further:

[0072] Step S15a, constructing an optimal projection direction optimization model, wherein the objective function is to minimize the total deviation between the comprehensive characteristic value obtained by projection and the comprehensive evaluation value;

[0073] Step S15b, using a variety of intelligent algorithms to solve the best projection direction optimization model, and obtain the projection directions of the four types of subnet combinations;

[0074] In this embodiment, genetic algorithm, particle swarm optimization algorithm, ant colony algorithm and simulated annealing algorithm are used in turn to solve the best projection direction optimization model, and the projection directions of the four types of subnet combinations corresponding to various algorithms are obtained. The stacking method is used to input the projection directions of the four types of subnet combinations corresponding to the various algorithms into the pre-built source model as a test set, and the model is trained and the comprehensive result is calculated as the final projection direction of the four types of subnet combinations.

[0075] In this embodiment, using multiple intelligent algorithms to solve the model can reduce the risk of overfitting, and at the same time, integrate multiple perspectives to enhance robustness and improve generalization ability. By combining multiple algorithms, the advantages of each algorithm can be fully utilized, the shortcomings can be reduced, and the overall performance and robustness can be improved.

[0076] Step S15c, input the characteristic value of a+b+c of the subnet combination into the best projection direction optimization model, project it according to the best projection direction of the subnet combination category to which it belongs, and obtain the projection value as the comprehensive evaluation value of the subnet combination;

[0077] Step S15d: determine whether each subnet combination satisfies the water balance based on the comprehensive evaluation value of the subnet combination, and extract the subnet combinations that do not satisfy the water balance.

[0078] According to one aspect of the present application, step S2 further comprises:

[0079] Step S21, constructing a subnet combination system dynamics model and an optimization scheduling model respectively, and coupling to obtain a subnet combination non-engineering measures multi-objective optimization model;

[0080] Step S22, based on the combined needs of each subnet, a set of non-engineering measures is collected and input into a multi-objective optimization model of the subnet combined non-engineering measures, and a plurality of multi-objective algorithms are used to solve the model to obtain a non-inferior solution set;

[0081] Step S23, using the ideal point method, fuzzy optimization method, and fuzzy matter-element method to jointly decide on the non-inferior solution set, and select the optimal solution of the subnet combination non-engineering measures multi-objective optimization model;

[0082] Step S24: Optimize each subnet combination by using the best non-engineering measures and calculate the optimized subnet combination requirements.

[0083] After comprehensive demand collection for each subnet combination, a series of feasible non-engineering measures are identified. Through pre-constructed models, these non-engineering measures are preliminarily evaluated. Based on the screened non-engineering measures, a multi-objective optimization model is constructed. Through a variety of multi-objective optimization algorithms, non-engineering measures that can take into account the needs of each subnet and have the highest comprehensive benefits are screened out. Through structured demand collection and implementation of multi-level optimization models, it is ensured that the needs of each subnet are fully met and blind decision-making is avoided. The combination of multiple non-engineering measures can exert synergistic effects, enhance the overall optimization effect, and create greater comprehensive value.

[0084] According to one aspect of the present application, step S3 further comprises:

[0085] Step S31: using an improved meta-analysis method to collect engineering measure sets and input them into a subnet combination system dynamics model to obtain a subnet combination state, and based on the subnet combination state corresponding to each engineering measure, construct an association relationship between the optimized subnet combination demand and the engineering measure to obtain a measure set corresponding to the demand;

[0086] Step S32, identify the combination scheme set of engineering measures, locations of constructible engineering measures and construction scale, and input it into the subnet combination system dynamics model to obtain the scheme implementation effect, that is, the subnet combination state after the scheme is implemented;

[0087] Step S33: Filter out the best solution to supplement each subnet combination.

[0088] According to one aspect of the present application, step S31 is further:

[0089] Step S31a, using subgroup analysis and sensitivity analysis to determine the source of heterogeneity;

[0090] Step S31b, setting a threshold for grey literature to include unpublished research and grey literature;

[0091] Step S31c, combining case studies and interviews to obtain comprehensive background information and implementation details of engineering measures;

[0092] Step S31d, regularly update the meta-analysis and collect the latest research results. In this embodiment, an improved meta-analysis method is used to obtain relevant engineering measures from existing studies. Compared with the standard meta-analysis method, since there may be significant heterogeneity between different studies that will affect the results of the meta-analysis, such as research design, sample characteristics and intervention measures, the improved meta-analysis method uses subgroup analysis and sensitivity analysis to explore the source of heterogeneity when performing meta-analysis to ensure the robustness of the results;

[0093] Because studies with only positive results are more likely to be published, resulting in meta-analysis that may overestimate the effectiveness of measures, in this example, in addition to published studies, unpublished studies and gray literature were included as much as possible by setting a certain threshold of gray literature to reduce the impact of publication bias;

[0094] At the same time, strict inclusion criteria are established to ensure that only high-quality studies are included in the meta-analysis. On the basis of the meta-analysis, qualitative research is combined to obtain more comprehensive background information and implementation details. The meta-analysis is updated regularly to incorporate the latest research results to ensure the timeliness and relevance of the results.

[0095] According to one aspect of the present application, step S32 is further:

[0096] Step S32a, classifying the engineering measures based on their effects on different needs into three categories, namely, flood control, water supply and ecology;

[0097] Step S32b, based on different combination modes of subnet combinations, extract corresponding classified engineering measures for combination to obtain a combination scheme set, and identify nodes of each engineering measure in the engineering measure combination that can be constructed by the subnet combination;

[0098] Step S32c: input the measure combination and the subnetwork combination into the subnetwork combination system dynamics model to obtain the subnetwork combination index improvement result, that is, the scheme implementation effect.

[0099] In this embodiment, engineering measures are first classified according to the needs they solve and correspond to subnet sets, and recommended measures are provided based on certain aspects. Then, the relationship between engineering measures and specific indicators in one or several aspects is established, and measures are recommended for various aspects. The nodes in the subnet combination where these measures can be built are identified. The subnet combination is optimized based on the selected measures and the system dynamics model is used to calculate the values ​​of each indicator. By comparing with the original indicator values, the improvement of the subnet combination by the measures is obtained.

[0100] According to one aspect of the present application, step S4 is further:

[0101] Step S41, constructing a non-engineering measure set based on the combined requirements of each subnet after the engineering measure optimization and inputting the subnet combined non-engineering measure multi-objective optimization model to obtain a non-inferior solution set of the subnet combined non-engineering measure multi-objective optimization model;

[0102] Step S42, inputting the non-engineering measures corresponding to the non-inferior solution set of the sub-network combination non-engineering measures multi-objective optimization model into the sub-network combination system dynamics model in sequence to obtain the improvement of the corresponding sub-network combination comprehensive index;

[0103] Step S43: construct a decision model, set an improvement threshold, screen out non-engineering measures whose improvement of the comprehensive index of the subnet combination is greater than the threshold, and optimize the subnet combination.

[0104] The present invention classifies and combines subnets based on subnet requirements to obtain various types of subnet combinations, screens out subnet combinations that need to be improved by calculating comprehensive evaluations of each subnet combination, obtains subnet combination requirements, and then supplements the water network system through a step-by-step optimization method in which non-engineering-engineering-non-engineering measures are nested.

[0105] First, non-engineering measures are collected based on the requirements of each subnet combination, and appropriate non-engineering measures are selected to optimize each subnet combination. At the same time, the comprehensive evaluation of the optimized subnet combination is calculated again to find out the subnet combination that has not met all the requirements for further optimization;

[0106] Then, the subnet combinations that still have gaps after the non-engineering measures are optimized are optimized with engineering measures, and are classified according to the needs that the engineering measures solve, and matched with the subnet combination categories in step S1, and the association between engineering measures and one or more indicators is constructed. For subnet combinations with different needs, corresponding engineering measures combinations are found to optimize them, and the nodes in the subnet combinations that can construct these engineering measures are identified. Then, these engineering measures combinations are used to optimize the subnet combinations and the improvements in various aspects and indicators of each subnet after optimization are calculated. Each optimization plan is screened by building a decision model to obtain the optimal plan;

[0107] In the case that there are still gaps in each subnet after optimization using engineering measures, non-engineering measures are used to optimize it again and the final subnet demand is calculated.

[0108] According to another aspect of the present application, a water network system replenishment system is provided, characterized in that it includes:

[0109] at least one processor; and

[0110] a memory communicatively connected to at least one of the processors; wherein,

[0111] 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 water network system replenishment methods described above.

[0112] 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 repair method, characterized in that: The steps include: Step S1, collect the data of each subnet in the study area, classify and combine the subnets based on the subnet requirements, obtain four types of subnet combinations, calculate the comprehensive evaluation value of each subnet and the characteristic value of each subnet combination, build the best projection direction optimization model, use a variety of intelligent algorithms to solve the model, obtain the projection value of each subnet combination, that is, the comprehensive evaluation result of the subnet combination, and extract the subnet combination that needs to be supplemented; Step S2: based on the needs of each subnet combination, a set of non-engineering measures is collected and input into a pre-built multi-objective optimization model of non-engineering measures for subnet combination, the optimal non-engineering measures are selected to optimize each subnet combination, and the optimized subnet combination needs are calculated; Step S3, collect the engineering measure set and construct the correlation between the optimized subnet combination demand and the engineering measure, obtain the measure set corresponding to the demand, identify the combination scheme set of engineering measures, the location of the buildable engineering measure and the construction scale, input it into the subnet combination system dynamics model, obtain the scheme implementation effect, and select the optimal scheme to supplement each subnet combination; Step S4: based on the requirements of each subnet combination after the engineering measures are optimized, a non-engineering measures set is collected and input into a multi-objective optimization model of the subnet combination non-engineering measures, and the optimal non-engineering measures are selected to optimize each subnet combination; The step S1 is further as follows: Step S11, collect data of each subnet in the study area, including the characteristic values ​​of water resources supply, water disaster security, water ecological health and the needs of the subnet; Step S12: based on the needs of each subnet, the subnets are divided into three categories: flood control set, water supply set and ecological set. The subnets in the three sets are combined in pairs and in triplets to obtain four subnet combinations, including flood control and water supply combination, flood control and ecological combination, water supply and ecological combination and flood control, water supply, ecological combination; Step S13, extracting the characteristic values ​​of a water resource supply, b water disaster security and c water ecological health of each subnet, taking the characteristic value of a+b+c of each subnet in the subnet combination as the coordinate of the subnet in the a+b+c dimensional space, obtaining the a+b+c dimensional space composed of each subnet point in the subnet combination, calculating the coordinate of the center of gravity of the a+b+c dimensional space as the a+b+c characteristic value of the subnet combination, where a, b and c are all positive integers; Step S14, extracting the weights of the water network comprehensive evaluation indicators of the four types of subnetwork combinations, and calculating the comprehensive evaluation value of each subnetwork combination based on the characteristic value of a+b+c of each subnetwork combination and the corresponding water network comprehensive evaluation indicator weight; Step S15, input the characteristic value of a+b+c of each subnet combination into the pre-constructed optimal projection direction optimization model in turn, obtain the projection value as the comprehensive evaluation value of each subnet combination, determine whether the subnet combination meets the water balance based on the comprehensive evaluation value of each subnet combination, and extract the subnet combination that does not meet the water balance; The step S15 is further as follows: Step S15a, constructing an optimal projection direction optimization model, wherein the objective function is to minimize the total deviation between the comprehensive characteristic value obtained by projection and the comprehensive evaluation value; Step S15b, using a variety of intelligent algorithms to solve the best projection direction optimization model, and obtain the projection directions of the four types of subnet combinations; Step S15c, input the characteristic value of a+b+c of the subnet combination into the best projection direction optimization model, project it according to the best projection direction of the subnet combination category to which it belongs, and obtain the projection value as the comprehensive evaluation value of the subnet combination; Step S15d, determining whether each subnet combination satisfies the water balance based on the comprehensive evaluation value of the subnet combination, and extracting the subnet combinations that do not satisfy the water balance; The step S2 is further as follows: Step S21, constructing a subnet combination system dynamics model and an optimization scheduling model respectively, and coupling to obtain a subnet combination non-engineering measures multi-objective optimization model; Step S22, based on the combined needs of each subnet, a set of non-engineering measures is collected and input into a multi-objective optimization model of the subnet combined non-engineering measures, and a plurality of multi-objective algorithms are used to solve the model to obtain a non-inferior solution set; Step S23, using the ideal point method, fuzzy optimization method, and fuzzy matter-element method to jointly decide on the non-inferior solution set, and select the optimal solution of the subnet combination non-engineering measures multi-objective optimization model; Step S24, optimizing each subnet combination by using the best non-engineering measures and calculating the optimized subnet combination requirements; The step S3 is further as follows: Step S31: using an improved meta-analysis method to collect engineering measure sets and input them into a subnet combination system dynamics model to obtain a subnet combination state, and based on the subnet combination state corresponding to each engineering measure, construct an association relationship between the optimized subnet combination demand and the engineering measure to obtain a measure set corresponding to the demand; Step S32, identify the combination scheme set of engineering measures, locations of constructible engineering measures and construction scale, and input it into the subnet combination system dynamics model to obtain the scheme implementation effect, that is, the subnet combination state after the scheme is implemented; Step S33, select the best solution to supplement each subnet combination; The step S31 is further as follows: Step S31a, using subgroup analysis and sensitivity analysis to determine the source of heterogeneity; Step S31b, setting a threshold for grey literature to include unpublished research and grey literature; Step S31c, combining case studies and interviews to obtain comprehensive background information and implementation details of engineering measures; Step S31d, regularly update meta-analysis and collect the latest research results; The step S32 is further as follows: Step S32a, classifying the engineering measures based on their effects on different needs into three categories, namely, flood control, water supply and ecology; Step S32b, based on different combination modes of subnet combinations, extract corresponding classified engineering measures for combination to obtain a combination scheme set, and identify nodes of each engineering measure in the engineering measure combination that can be constructed by the subnet combination; Step S32c, inputting the measure combination and the subnetwork combination into the subnetwork combination system dynamics model to obtain the subnetwork combination index improvement result, that is, the scheme implementation effect; Step S41, constructing a non-engineering measure set based on the combined requirements of each subnet after the engineering measure optimization and inputting the subnet combined non-engineering measure multi-objective optimization model to obtain a non-inferior solution set of the subnet combined non-engineering measure multi-objective optimization model; Step S42, inputting the non-engineering measures corresponding to the non-inferior solution set of the sub-network combination non-engineering measures multi-objective optimization model into the sub-network combination system dynamics model in sequence to obtain the improvement of the corresponding sub-network combination comprehensive index; Step S43: construct a decision model, set an improvement threshold, screen out non-engineering measures whose improvement of the comprehensive index of the subnet combination is greater than the threshold, and optimize the subnet combination.

2. A water network system replenishment system, 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 replenishment method described in claim 1.

Images