Urban drainage pipe network optimization method and device based on big data

Abstract

The invention discloses an urban drainage pipe network optimization method and device based on big data, and relates to the technical field of data processing, and the method comprises the steps: constructing a plurality of feature rainfall scenes based on historical rainfall event differential clustering, evaluating the flood drainage response standard reaching performance of a drainage pipe network in each scene, screening and generating a target rainfall scene, and carrying out the optimization of the target rainfall scene. The method comprises the following steps: performing adaptive layout adjustment in combination with overground and underground data, establishing a layout adjustment space, performing multi-degree-of-freedom optimization based on a pipe network loss prediction model, forming an optimization strategy, performing state compensation through real-time monitoring data, and finally generating a dynamic adaptive drainage pipe network optimization scheme. The technical problems that an existing urban drainage pipe network lacks systematic evaluation and a multi-dimensional optimization mechanism when coping with a complex rainfall scene, the flood drainage response capability is insufficient, and the operation efficiency is low are solved, and the purposes of multi-scene optimization and real-time monitoring compensation are achieved. And the technical effects of flood drainage response capability and operation efficiency of the drainage pipe network are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an optimization method and device for urban drainage pipe networks based on big data. Background Art

[0002] In the context of the rapid advancement of urbanization, the drainage system, as an important part of urban infrastructure, its planning, design and operation efficiency have a direct impact on the urban flood control and drainage capacity. However, most of the traditional planning methods for drainage pipe networks are based on static historical rainfall data and a single design rainfall intensity formula, lacking a systematic analysis of complex rainfall change patterns and being difficult to cope with the increasingly frequent and intense extreme rainfall events in recent years.

[0003] In addition, the existing drainage systems generally have problems such as lagging design standards, rigid spatial layouts, and slow operation and maintenance responses. Especially when the rainfall intensity is concentrated in a short time or the spatial distribution is uneven, it is easy to cause local waterlogging and even urban waterlogging disasters. Summary of the Invention

[0004] This application provides an optimization method and device for urban drainage pipe networks based on big data, which are used to solve the technical problems that the existing urban drainage pipe networks lack a systematic evaluation and multi-dimensional optimization mechanism when dealing with complex rainfall scenarios, have insufficient flood drainage response capabilities and low operation efficiency.

[0005] In the first aspect of this application, an optimization method for urban drainage pipe networks based on big data is provided. The method includes: performing differential clustering on the historical rainfall event set of the target city to obtain multiple characteristic rainfall scenarios; calculating the flood drainage response compliance of the drainage pipe network of the target city according to the multiple characteristic rainfall scenarios to obtain the flood drainage response compliance coefficients for each scenario; performing compliance inspection on the multiple characteristic rainfall scenarios according to the flood drainage response compliance coefficients for each scenario to generate a target rainfall scenario; obtaining the above-ground and underground data sets of the target city, and adaptively adjusting the layout of the drainage pipe network in combination with the target rainfall scenario to establish a pipe network layout adjustment space; performing multi-degree-of-freedom optimization on the pipe network layout adjustment space according to a pipe network loss prediction model to generate a first pipe network layout optimization strategy; obtaining multi-dimensional data of pipe network monitoring of the drainage pipe network, and compensating and optimizing the pipe network state of the first pipe network layout optimization strategy according to the multi-dimensional data of pipe network monitoring to obtain a second pipe network optimization strategy.

[0006] In a second aspect of the present application, an optimization device for an urban drainage pipe network based on big data is provided. The device includes: a rainfall scenario sorting module for differentially clustering and sorting a historical rainfall event set of a target city to obtain multiple characteristic rainfall scenarios; a flood drainage response compliance calculation module for calculating the flood drainage response compliance of the drainage pipe network of the target city according to the multiple characteristic rainfall scenarios to obtain the flood drainage response compliance coefficients for each scenario; a compliance inspection module for performing compliance inspection on the multiple characteristic rainfall scenarios according to the flood drainage response compliance coefficients for each scenario to generate a target rainfall scenario; a pipe network layout adjustment module for obtaining the above-ground and underground data sets of the target city and adaptively adjusting the layout of the drainage pipe network in combination with the target rainfall scenario to establish a pipe network layout adjustment space; a multi-degree-of-freedom optimization module for performing multi-degree-of-freedom optimization on the pipe network layout adjustment space according to a pipe network loss prediction model to generate a first pipe network layout optimization strategy; and a pipe network state compensation module for obtaining the multi-dimensional pipe network monitoring data of the drainage pipe network and compensating and optimizing the first pipe network layout optimization strategy according to the multi-dimensional pipe network monitoring data to obtain a second pipe network optimization strategy.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages: The optimization method and device for an urban drainage pipe network based on big data provided in the present application relate to the technical field of data processing. By differentially clustering to construct characteristic rainfall scenarios, evaluating the flood drainage response compliance to generate a target scenario, adjusting the pipe network layout in combination with above-ground and underground data, optimizing the scheme based on a loss prediction model, and fusing monitoring data for compensation and correction, a dynamically optimized drainage pipe network strategy is formed, solving the technical problems that the existing urban drainage pipe network lacks a systematic evaluation and multi-dimensional optimization mechanism when dealing with complex rainfall scenarios, has insufficient flood drainage response ability and low operation efficiency, and achieving the technical effect of effectively improving the flood drainage response ability and operation efficiency of the drainage pipe network through multi-scenario optimization and real-time monitoring compensation. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 It is a schematic flow chart of an optimization method for an urban drainage pipe network based on big data provided in an embodiment of the present application; Figure 2 Schematic diagram of the structure of the urban drainage pipe network optimization device based on big data provided by the embodiments of the present application.

[0010] Explanation of reference numerals: rainfall scenario sorting module 11, waterlogging drainage response compliance calculation module 12, compliance inspection module 13, pipe network layout adjustment module 14, multi-degree-of-freedom optimization module 15, pipe network state compensation module 16. Detailed implementation manners

[0011] The present application provides a method and device for optimizing an urban drainage pipe network based on big data, which are used to solve the technical problems that the existing urban drainage pipe network lacks a systematic evaluation and multi-dimensional optimization mechanism when dealing with complex rainfall scenarios, and has insufficient waterlogging drainage response ability and low operation efficiency.

[0012] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0013] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 shown, the present application provides a method for optimizing an urban drainage pipe network based on big data, and the method includes: P10: Perform differential clustering sorting on the historical rainfall event set of the target city to obtain multiple characteristic rainfall scenarios.

[0015] Furthermore, step P10 of the embodiments of the present application further includes: P11: Perform pairwise difference degree evaluation based on the historical rainfall event set to obtain a first differential detection distribution; P12: Classify the historical rainfall event set according to the first differential detection distribution to obtain multiple rainfall event classes; P13: Perform inter-class difference degree evaluation on the multiple rainfall event classes to obtain a second differential detection distribution, and perform inter-class fusion on the multiple rainfall event classes according to the second differential detection distribution to obtain multiple rainfall event regions; P14: Perform rainfall feature recognition fusion for each rainfall event region in the multiple rainfall event regions to generate the multiple characteristic rainfall scenarios. [[ID=I]]

[0016] It should be understood that to achieve the efficient optimization of urban drainage pipe networks under variable climate conditions, it is first necessary to extract the historical rainfall event set of the target city for differential clustering and sorting to obtain multiple characteristic rainfall scenarios that can represent different rainfall patterns.

[0017] Specifically, first perform pairwise difference degree evaluation on all events in the historical rainfall event set to construct a relative heterogeneity quantification index between rainfall events. This difference degree evaluation can be carried out based on multi-dimensional meteorological characteristic parameters, and the selected characteristics include but are not limited to total rainfall, rainfall duration, maximum 1-hour rainfall intensity, rainfall peak time, rainfall center of gravity, and spatial distribution pattern, etc. By constructing a comprehensive difference degree function, such as weighted Euclidean distance or Mahalanobis distance, calculate the difference values between all events, and then obtain a first differential detection distribution. This distribution reflects the similarity and distinguishability between events in the historical rainfall event set.

[0018] After obtaining the first differential detection distribution, use an unsupervised clustering method based on difference degree to classify the historical rainfall events. Exemplarily, optional clustering methods include DBSCAN, spectral clustering, or hierarchical clustering. According to the difference values, the events are divided into several rainfall event classes, and the events within each class are highly similar in terms of rainfall intensity, time characteristics, and spatial features.

[0019] After the initial clustering is completed, continue to perform inter-class evaluation on the differences between these rainfall event classes. By calculating the distance or distribution overlap degree between the average feature vectors of each class, a second differential detection distribution is obtained. The evaluation of inter-class difference degree can also be carried out from multiple dimensions such as rainfall intensity, rainfall duration, and rainfall distribution. For example, calculate the difference in average rainfall intensity and the difference in average rainfall duration between two rainfall event classes. Through the second differential detection distribution, it can be identified which rainfall event classes have significant differences and which classes have small differences, thereby providing a basis for further inter-class fusion. This process is a key step in the differential clustering algorithm, which determines the similarity degree between rainfall event classes. Through reasonable evaluation of inter-class difference degree, over-segmentation or inappropriate merging of rainfall event classes can be avoided, ensuring that the finally obtained rainfall event regions have reasonable representativeness and distinguishability.

[0020] Finally, according to the second differential detection distribution, inter-class fusion is performed on multiple rainfall event classes. Rainfall event classes with small differences are merged into larger rainfall event areas, while rainfall event classes with significant differences are retained as independent rainfall event areas. After forming multiple rainfall event areas, further rainfall feature recognition and fusion are carried out within each rainfall event area. Exemplarily, by analyzing the rainfall events within each rainfall event area, representative rainfall features are extracted, such as average rainfall intensity, typical rainfall duration, main rainfall distribution area, etc. These rainfall features are fused to generate the final characteristic rainfall scenarios. These characteristic rainfall scenarios can comprehensively cover the main features of historical rainfall events in the target city, providing accurate rainfall condition simulations for subsequent drainage network optimization analysis.

[0021] Rainfall feature recognition and fusion is a key link in generating characteristic rainfall scenarios. By extracting and fusing rainfall features within a rainfall event area, concise and representative characteristic rainfall scenarios can be generated. These scenarios can not only reflect the main features of actual rainfall events but also provide effective input data for the calculation of the flood drainage response compliance of the drainage network.

[0022] P20: Calculate the flood drainage response compliance of the drainage network of the target city according to the multiple characteristic rainfall scenarios, and obtain the flood drainage response compliance coefficients for each scenario.

[0023] Furthermore, step P20 of the embodiment of the present application further includes: P21: Extract the first characteristic rainfall scenario according to the multiple characteristic rainfall scenarios; P22: Retrieve the flood drainage response duration of the drainage network according to the first characteristic rainfall scenario to obtain the first rainfall scenario flood drainage duration set; P23: Select the first rainfall scenario flood drainage duration set according to the standard flood drainage response duration to obtain the first compliant flood drainage duration space less than or equal to the standard flood drainage response duration; P24: Calculate the sample numbers of the first rainfall scenario flood drainage duration set and the first compliant flood drainage duration space to obtain the first scenario duration sample number and the first compliant duration sample number; P25: Calculate the ratio of the first compliant duration sample number to the first scenario duration sample number to obtain the first scenario flood drainage response compliance coefficient, and add the first scenario flood drainage response compliance coefficient to the flood drainage response compliance coefficients for each scenario.

[0024] Optionally, based on the identified multiple characteristic rainfall scenarios, a quantitative evaluation of the flood drainage capacity of the existing drainage network system in the target city is carried out, and finally the flood drainage response compliance coefficients for each scenario are obtained. This compliance coefficient is used to reflect the efficiency and reliability of the drainage network in completing the flood drainage task in the corresponding rainfall scenario and is an important indicator for formulating subsequent network optimization strategies.

[0025] First, extract the first characteristic rainfall scenario to be evaluated from the multiple characteristic rainfall scenarios in sequence, for establishing a drainage performance evaluation model corresponding to this scenario. This scenario can represent a rainfall pattern with specific intensity, spatial distribution, or temporal characteristics, and has a clear evaluation objective.

[0026] Subsequently, based on the first characteristic rainfall scenario, retrieve the historical drainage operation data of the urban drainage pipe network corresponding to this type of rainfall scenario, and extract the corresponding drainage response duration records to form the first rainfall scenario drainage duration set. This set contains multiple historical drainage response durations, reflecting the actual drainage efficiency of the drainage pipe network in different historical rainfall events.

[0027] Next, screen the first rainfall scenario drainage duration set according to the preset standard drainage response duration. The standard drainage response duration is determined according to urban planning or relevant specifications, and is used to measure the longest time for the drainage pipe network to complete the drainage task under specified rainfall conditions. Select the historical drainage response durations in the first rainfall scenario drainage duration set that are less than or equal to the standard drainage response duration to form the first qualified drainage duration space. The number of samples in this space is the number of times the drainage pipe network reaches the standard drainage response duration under this characteristic rainfall scenario.

[0028] Furthermore, calculate the number of samples in the first rainfall scenario drainage duration set and the first qualified drainage duration space. Count the total number of samples in the first rainfall scenario drainage duration set, denoted as the first scenario duration sample number; at the same time, count the number of samples in the first qualified drainage duration space, denoted as the first qualified duration sample number. The calculation of these two sample numbers provides the basic data for the subsequent calculation of the qualified coefficient.

[0029] Finally, calculate the ratio of the first qualified duration sample number to the first scenario duration sample number. By dividing the first qualified duration sample number by the first scenario duration sample number, the first scenario drainage response qualified coefficient is obtained. This coefficient reflects the probability that the drainage pipe network reaches the standard drainage response duration under the first characteristic rainfall scenario, that is, the drainage response qualified ability of the drainage pipe network. The calculation formula is: First scenario drainage response qualified coefficient = First qualified duration sample number / First scenario duration sample number. The calculated first scenario drainage response qualified coefficient will be added to the set of drainage response qualified coefficients for each scenario, providing a key quantitative index for the subsequent optimization of the urban drainage pipe network.

[0030] This process not only makes full use of historical data and preset standards, but also provides a scientific basis for the optimization of the drainage pipe network through quantitative analysis, avoiding subjective evaluation methods that rely on single simulations or expert experience, and ensuring the objectivity, repeatability, and engineering applicability of the evaluation results.

[0031] P30: Conduct compliance checks on the multiple characteristic rainfall scenarios based on the drainage response compliance coefficients of the scenarios to generate a target rainfall scenario.

[0032] Furthermore, step P30 in the embodiment of the present application further includes: P31: Determine whether the drainage response compliance coefficient of each scenario is less than the drainage response compliance threshold, and obtain multiple drainage response compliance test results; P32: Filter the multiple characteristic rainfall scenarios according to the multiple drainage response compliance test results, and obtain a screening set of rainfall scenarios with unqualified responses; P33: Fusion the screening set of rainfall scenarios with unqualified responses to obtain the target rainfall scenario.

[0033] Specifically, based on the drainage response compliance coefficients corresponding to the aforementioned multiple characteristic rainfall scenarios, a compliance judgment operation is performed to screen out key rainfall scenarios whose drainage capacity has not yet met the standards, thereby forming a target rainfall scenario that has constraining guiding significance for drainage network optimization.

[0034] Specifically, the compliance of the drainage response compliance coefficient corresponding to each characteristic rainfall scenario is first determined. The judgment logic is to compare the compliance coefficient of each scenario with the preset drainage response compliance threshold. This threshold is usually determined by urban planning or industry standards and is used to determine whether the pipeline network has compliant drainage capacity. For example, if the threshold is set to 0.6, it means that at least 60% of historical drainage samples in this scenario meet the standard response time for the drainage capacity in this scenario to be considered to meet the standard. The judgment results are recorded as Boolean values or labels, forming multiple drainage response compliance test results.

[0035] Next, based on the compliance test results, characteristic rainfall scenarios that failed the compliance test were further screened. For all scenarios whose compliance coefficients fell below the set threshold, their corresponding characteristic rainfall scenarios were marked as unqualified and aggregated into a screening set of unqualified rainfall scenarios. This screening set represents the set of risk scenarios within the current drainage network and serves as the core basis for subsequent optimization strategy design. By centralizing these unqualified scenarios, we can more systematically analyze and address these problematic scenarios, providing clear targets for subsequent optimization strategies.

[0036] Finally, in step P33, the filtered set of unsatisfactory rainfall scenarios is fused to generate a target rainfall scenario. This fusion can be performed using strategies such as superposition of primary feature frequencies between scenarios, weighted averaging, and reconstruction of representative samples. This extracts representative and structurally feasible rainfall input conditions, which are used to drive the input boundaries of the subsequent drainage system optimization model. The target rainfall scenario is not simply a superposition of the original feature scenarios, but rather a composite rainfall-driven model formed by focusing and abstracting the system's weak responses.

[0037] Through the compliance inspection and target scenario extraction process, not only a closed-loop drainage capacity diagnosis mechanism is constructed, but also precise environmental input conditions are provided for the layout adjustment and optimization path in the subsequent steps, enhancing the targeting and engineering value of the overall optimization strategy.

[0038] P40: Obtain the above-ground and underground data sets of the target city, adaptively adjust the layout of the drainage pipe network in combination with the target rainfall scenario, and establish a pipe network layout adjustment space.

[0039] Furthermore, step P40 of the embodiment of the present application further includes: P41: Model according to the pipe network layout plan of the drainage pipe network to obtain a three-dimensional pipe network model, and expand the three-dimensional pipe network model according to the above-ground and underground data sets to generate an urban drainage pipe network model; P42: Simulate the drainage of the urban drainage pipe network model according to the target rainfall scenario to obtain pipe network simulated drainage data; P43: Identify risks according to the pipe network simulated drainage data to obtain a pipe network drainage risk identification result; P44: Adjust the pipe network layout plan according to the pipe network drainage risk identification result to generate the pipe network layout adjustment space.

[0040] Optionally, combine the comprehensive spatial information and key rainfall scenarios of the target city to intelligently adjust the spatial layout of the existing drainage pipe network, thereby constructing a pipe network layout adjustment space with adjustment feasibility and structural optimization potential. This space serves as the input set for subsequent optimization solutions and bears the drainage capacity performance of different layout plans under the target rainfall scenario.

[0041] In specific implementation, first, based on the existing design blueprint or operation data of the drainage pipe network, construct its initial three-dimensional pipe network model, that is, a spatial geometric expression including structured elements such as pipe routes, node positions, and elevation information. Subsequently, further introduce the above-ground and underground data sets of the target city, including information such as topography, ground building layout, underground pipeline routes, and underground space usage, to expand and model the three-dimensional model, thereby forming an urban drainage pipe network model with the characteristics of multi-source data superposition. This model is the basic environment for subsequent simulation and layout evaluation.

[0042] Next, based on the generated urban drainage pipe network model, input the previously extracted target rainfall scenario parameters to carry out dynamic drainage simulation. The simulation process can use hydrodynamic simulation tools such as SWMM (Storm Water Management Model), take the rainfall characteristics (such as rainfall intensity, rainfall duration, rainfall distribution, etc.) of the target rainfall scenario as input conditions, and simulate the drainage process of the drainage pipe network under these rainfall conditions. Obtain the simulated drainage data of each drainage unit in this scenario, including multiple indicators such as water level changes, pipe segment flow velocities, and node overflows.

[0043] Next, perform structured analysis and anomaly identification on the simulated drainage data. By analyzing data such as the water level changes and flow distributions at each node during the simulated drainage process, identify potential risk points in the drainage pipe network. For example, problems such as excessively high water levels and overly long drainage times may occur in certain areas, indicating possible defects in the layout or design of the drainage pipe network in these areas. The risk identification results will detail the locations, types, and severities of these potential problems, providing clear guidance for subsequent pipe network layout adjustment.

[0044] Finally, relying on the risk identification results, automatically or semi-automatically adjust the original drainage pipe network layout plan to construct several pipe network layout adjustment plans with different structural characteristics. For example, it may be necessary to increase the pipe diameter, adjust the pipe slope, add drainage pump stations, or change the pipe connection method. Through these adjustments, generate multiple pipe network layout adjustment plans to form a pipe network layout adjustment space. These adjustment plans will provide multiple options for subsequent optimization strategies, ensuring that the drainage pipe network can drain more effectively under the target rainfall scenario and reducing the risk of waterlogging.

[0045] This process not only makes full use of above-ground and underground data and target rainfall scenario information but also provides a scientific basis for the optimization of the drainage pipe network through simulation and risk assessment, ensuring the scientific nature and effectiveness of the entire optimization method.

[0046] P50: Perform multi-degree-of-freedom optimization on the pipe network layout adjustment space according to the pipe network loss prediction model to generate the first pipe network layout optimization strategy.

[0047] Furthermore, step P50 of the embodiment of the present application further includes: P51: Perform drainage response optimization on the pipe network layout adjustment space according to the standard drainage response duration to establish the first optimization space for pipe network layout adjustment; P52: Perform pipe network loss prediction optimization on the first optimization space for pipe network layout adjustment according to the pipe network loss prediction model to obtain the second optimization space for pipe network layout adjustment; P53: Assign weights to the multi-dimensional indexes of the pipe network loss prediction of the pipe network loss prediction model to obtain a pipe network comprehensive loss calculation model; P54: Perform pipe network comprehensive loss minimization optimization on the second optimization space for pipe network layout adjustment according to the pipe network comprehensive loss calculation model to obtain the first pipe network layout optimization strategy.

[0048] It should be understood that with the core goal of reducing the operation loss of the drainage system, perform systematic and multi-dimensional optimization analysis on the previously established pipe network layout adjustment space, and finally output the first pipe network layout optimization strategy that can be used for engineering deployment. This strategy further takes into account various structural and economic losses generated during the long-term operation of the pipe network on the basis of ensuring the drainage response efficiency, thereby achieving the overall optimal performance at the layout level.

[0049] Specifically, first, using the standard drainage response duration as the basic evaluation index, the initial drainage performance screening is carried out for each scheme in the regulation space of the pipe network layout, eliminating the schemes with significantly exceeding response time or insufficient regulation effect, and constructing the first optimization space of the pipe network layout that meets the basic drainage requirements. This space only retains those candidate schemes with strong drainage capacity as the basic set for further optimization.

[0050] Immediately afterwards, a pipe network loss prediction model is introduced to conduct loss analysis on the schemes in the above first optimization space. This prediction model is trained based on historical operation data, engineering statistical data and hydraulic simulation results, and can quantitatively evaluate the operation results of different layout schemes under the target rainfall scenario, outputting multiple prediction indicators including node ponding loss, structural settlement trend, pipe breakage rate, etc. By predicting the pipe network loss of each scheme in the first optimization space, eliminating the schemes with significantly exceeding loss prediction or relatively high comprehensive risk, the second optimization space after preliminary loss prediction screening is formed.

[0051] On this basis, a multi-dimensional loss trade-off mechanism is introduced to configure weights for several loss dimensions included in the pipe network loss prediction model, forming a unified pipe network comprehensive loss calculation model. In this application, the multi-dimensional indicators of the pipe network loss prediction model include drainage waterlogging loss, drainage ground settlement loss and drainage pipe loss. These indicators respectively reflect the potential loss situations of the drainage pipe network in different aspects. In order to comprehensively evaluate the advantages and disadvantages of each layout scheme, it is necessary to allocate weights to these multi-dimensional indicators. The weight allocation can be adjusted according to the specific needs and priorities of the city. For example, if the city pays special attention to the waterlogging risk, a higher weight can be given to the drainage waterlogging loss. Through weight allocation, the pipe network comprehensive loss calculation model is obtained, and its formula is: Among them, is the pipe network comprehensive loss, is the drainage waterlogging loss, is the drainage ground settlement loss, is the drainage pipe loss, 、 、 are the weight coefficients of the drainage waterlogging loss, the drainage ground settlement loss and the drainage pipe loss respectively, and can be configured according to the actual operation focus or safety-sensitive area of the city.

[0052] Finally, taking this comprehensive loss model as the objective function, optimize the pipeline network for minimizing the comprehensive loss of all solutions within the second optimization space. A heuristic algorithm (such as genetic algorithm, particle swarm optimization) or an exact algorithm (such as integer programming) can be used to perform a global search for multi-degree-of-freedom variables. Under the condition of ensuring the drainage response constraints, by calculating the comprehensive loss value of each layout solution, a set of layout adjustment solutions with the minimum loss is selected, thereby obtaining the first strategy for optimizing the pipeline network layout. This strategy not only considers the requirements of the drainage response time but also comprehensively considers the potential losses of the pipeline network in different aspects, ensuring that the optimized pipeline network layout reaches the optimal in terms of overall performance.

[0053] Furthermore, step P51 of the embodiment of the present application further includes: P51-1: Based on the target rainfall scenario, predict the drainage response duration for each pipeline network layout adjustment solution within the pipeline network layout adjustment space, obtaining multiple predicted drainage response durations; P51-2: Determine whether the multiple predicted drainage response durations are less than or equal to the standard drainage response duration, obtaining multiple drainage response judgment results; P51-3: Screen the pipeline network layout adjustment space according to the multiple drainage response judgment results, obtaining the first optimization space for the pipeline network layout adjustment.

[0054] In a possible embodiment of the present application, to improve the accurate screening efficiency of the drainage capacity of the pipeline network, the process of optimizing the drainage response for the pipeline network layout adjustment space based on the standard drainage response duration can be further refined.

[0055] Specifically, first, based on the characteristic parameters such as rainfall intensity, duration, and spatial distribution of the target rainfall scenario, predict the drainage response duration for each layout adjustment solution within the pipeline network layout adjustment space. This prediction can be achieved through a hydraulic model (such as the SWMM model) or an integrated machine learning model (such as a regression prediction network trained based on historical simulation data), outputting the drainage response duration of each solution under the current rainfall input condition, that is, simulating the whole process time from rainfall occurrence to no water accumulation at the node, denoted as the predicted drainage response duration.

[0056] Subsequently, compare and judge the above multiple predicted drainage response durations with the preset standard drainage response duration respectively. This standard is usually set according to urban drainage design specifications or regional specific drainage performance indicators. For example, it is set to 3 hours or 2.5 hours, representing that in the target scenario, the drainage system should complete the water accumulation removal task within the limited time. The comparison result is output as a logical judgment, that is, judge whether the predicted drainage response duration is less than or equal to the standard drainage response duration, thereby obtaining multiple drainage response judgment results. Exemplarily, if a certain predicted drainage response duration is less than or equal to the standard drainage response duration, it is considered that the pipeline network layout adjustment solution meets the requirements in terms of drainage response time.

[0057] Finally, filter all the solutions in the original pipe network layout adjustment space according to the above judgment results, and only retain the solutions that meet the drainage response standard. Specifically, screen out all the solutions corresponding to the predicted drainage response duration less than or equal to the standard value, and add them to the first optimization space for pipe network layout adjustment. This space represents a set of solutions that are structurally feasible and have the basic drainage compliance ability, and is the solution set basis for subsequent multi-dimensional loss prediction and comprehensive optimization. In this way, each solution in the first optimization space for pipe network layout adjustment has the ability to complete the drainage task within the standard drainage response duration, thus providing a solid foundation for subsequent pipe network loss prediction and optimization.

[0058] Furthermore, step P52 of the embodiment of the present application further includes: P52-1: Extract the nth pipe network layout adjustment solution according to the first optimization space for pipe network layout adjustment, where n is a positive integer; P52-2: Input the nth pipe network layout adjustment solution and the target rainfall scenario into the pipe network loss prediction model to obtain the nth pipe network loss prediction result, and the nth pipe network loss prediction result includes the nth drainage waterlogging loss coefficient, the nth drainage ground settlement loss coefficient, and the nth drainage pipeline loss coefficient; P52-3: Set multi-dimensional constraints for pipe network loss prediction according to the multi-dimensional indexes of pipe network loss prediction; P52-4: Determine whether the nth pipe network loss prediction result meets the multi-dimensional constraints of pipe network loss prediction; P52-5: If the nth pipe network loss prediction result meets the multi-dimensional constraints of pipe network loss prediction, add the nth pipe network layout adjustment solution to the second optimization space for pipe network layout adjustment.

[0059] Optionally, to further evaluate and control the operation risk of the drainage system while ensuring the drainage response efficiency, prediction and constraint screening operations are carried out for multi-dimensional losses in the pipe network operation.

[0060] First, extract the nth pipe network layout adjustment solution from the first optimization space for pipe network layout adjustment, where n is a positive integer. This process is the starting point for gradually evaluating the pipe network layout adjustment solutions. By extracting each solution one by one, a specific object is provided for subsequent loss prediction. Each pipe network layout adjustment solution contains specific parameters of the pipe network, such as pipe diameter, slope, connection method, etc. These parameters will be used as input conditions for the subsequent loss prediction model.

[0061] Next, input the extracted nth pipe network layout adjustment plan and the target rainfall scenario parameters into the pipe network loss prediction model. This prediction model is constructed by multi-source data driving and works in combination with the following core modules: a hydraulic simulation module for predicting the risk of node waterlogging and the overflow intensity; a structural response analysis module for simulating the ground settlement caused by flow concentration and foundation disturbance; a material fatigue and service life model for evaluating the damage trend caused by pipe structure compression, corrosion, and aging. Through the cooperation of these sub-modules, the model outputs the loss prediction results of the nth plan under the given rainfall scenario, including the nth drainage waterlogging loss coefficient (reflecting the degree of node waterlogging risk), the nth drainage ground settlement loss coefficient (reflecting the potential of structural settlement), and the nth drainage pipe loss coefficient (reflecting the potential of system failure or maintenance cost).

[0062] Subsequently, set multi-dimensional constraints for the pipe network loss prediction according to the multi-dimensional indicators of the pipe network loss prediction. These constraint conditions are set based on various requirements such as urban planning, environmental protection, and engineering safety, and are used to ensure that the optimized pipe network layout can meet the minimum standards in all aspects. For example, it can be set that the drainage waterlogging loss coefficient does not exceed 0.5, the ground settlement does not exceed 0.3, the pipe loss does not exceed 0.2, etc., to form a specific threshold vector.

[0063] Next, compare the nth pipe network loss prediction result with the set multi-dimensional constraints to determine whether it meets the control requirements of all dimensions at the same time. The judgment logic is full-index compliance, that is, all three loss coefficients are lower than or equal to the set thresholds before it can be determined that the constraints are met. Exemplarily, compare the nth drainage waterlogging loss coefficient, the nth drainage ground settlement loss coefficient, and the nth drainage pipe loss coefficient with the corresponding constraint conditions respectively. If all loss coefficients meet the corresponding constraint conditions, it is considered that the pipe network layout adjustment plan is feasible in terms of loss prediction.

[0064] If the nth pipe network loss prediction result meets the multi-dimensional constraints of the pipe network loss prediction, add the nth pipe network layout adjustment plan to the second optimization space for pipe network layout adjustment. All plans in this space have good drainage response performance and have passed multiple safety assessments of waterlogging risk, structural settlement, and maintenance loss, constituting the candidate solution set for the subsequent comprehensive optimization stage.

[0065] By implementing this step, the scheme selection no longer relies solely on the drainage efficiency index, but introduces the loss assessment logic during the system operation period, constructs a multi-dimensional and refined assessment closed-loop, and makes the optimization path more in line with the life cycle control objectives and sustainable operation and maintenance requirements of the urban drainage system.

[0066] P60: Obtain the multi-dimensional data of the pipe network monitoring of the drainage pipe network, and perform pipe network state compensation optimization on the first strategy for pipe network layout optimization according to the multi-dimensional data of the pipe network monitoring to obtain the second optimization strategy for pipe network optimization.

[0067] Further, step P60 of the embodiment of the present application further includes: P61: Detect the abnormal state of the drainage pipe network according to the multi-dimensional data of the pipe network monitoring, and obtain the detection result of the abnormal state of the pipe network; P62: Compensate and optimize the first strategy for optimizing the pipe network layout according to the detection result of the abnormal state of the pipe network, and generate the second optimized strategy for optimizing the pipe network.

[0068] It should be understood that by introducing a real-time monitoring data feedback mechanism, the first strategy for optimizing the pipe network layout obtained through model prediction and simulation analysis before is dynamically corrected and engineering adapted, so as to generate a second optimized strategy for optimizing the pipe network that is more in line with the actual operation state, has higher robustness and implementation feasibility.

[0069] Specifically, first, detect the abnormal state of the drainage pipe network according to the multi-dimensional data of the pipe network monitoring of the drainage pipe network, and obtain the detection result of the abnormal state of the pipe network. The multi-dimensional data of the pipe network monitoring usually includes but is not limited to water level monitoring data, flow monitoring data, pipeline pressure monitoring data, water quality monitoring data, and equipment operation state monitoring data, etc. These data can comprehensively reflect various state information of the drainage pipe network in actual operation. Based on the above data, apply abnormal detection algorithms (such as K-means clustering, isolation forest algorithm, sliding window threshold detection, etc.) to identify abnormal conditions in the overall network operation, and output the detection result of the abnormal state of the pipe network, including the abnormal location (node or pipe section), abnormal type (waterlogging, flow velocity disorder, structural deformation, siltation and blockage, etc.), its time tag and severity score.

[0070] Then, based on the above detection results, perform state compensation optimization on the first strategy for optimizing the pipe network layout that has been constructed. The compensation process is executed in combination with the following two types of logics: one is structural redundancy compensation, for high-risk or high-frequency abnormal areas, dynamically add auxiliary drainage units, overflow channels or expand drainage pipelines; the other is strategy redirection compensation, if some original layout paths are affected by abnormal states and operate poorly, then adjust the drainage path, drainage direction or node sharing mechanism. The compensation strategy can either be rule-driven or introduce actual state constraints into the existing optimization model to form an iterative optimization solution model based on real-time constraint feedback.

[0071] Finally, the result generated by fusing the abnormal state detection and structural adjustment is output as the second optimized strategy for optimizing the pipe network. This strategy not only inherits the theoretical optimality of the first strategy in the model space, but also fully absorbs the data feedback information on the operation site, which can ensure the stability, emergency response ability and maintenance convenience of the system in the real complex environment.

[0072] In summary, the embodiment of the present application has at least the following technical effects: This application constructs multiple characteristic rainfall scenarios based on differential clustering of historical rainfall events, evaluates the compliance of the drainage pipe network's flood drainage response under each scenario, screens and generates target rainfall scenarios, combines above-ground and underground data for adaptive layout adjustment, establishes a layout adjustment space, performs multi-degree-of-freedom optimization based on a pipe network loss prediction model to form an optimization strategy, and performs status compensation through real-time monitoring data, finally generating a dynamically adaptive drainage pipe network optimization plan.

[0073] It achieves the technical effect of effectively improving the flood drainage response ability and operation efficiency of the drainage pipe network through multi-scenario optimization and real-time monitoring compensation.

[0074] Embodiment 2, based on the same inventive concept as the method for optimizing an urban drainage pipe network based on big data in the foregoing embodiment, as Figure 2 shown, this application provides an apparatus for optimizing an urban drainage pipe network based on big data. The apparatus in the embodiments of this application and the method embodiments are based on the same inventive concept. Among them, the apparatus includes: A rainfall scenario sorting module 11, which is used to perform differential clustering sorting on the historical rainfall event set of the target city to obtain multiple characteristic rainfall scenarios.

[0075] A flood drainage response compliance calculation module 12, which is used to calculate the flood drainage response compliance of the drainage pipe network of the target city according to the multiple characteristic rainfall scenarios to obtain the flood drainage response compliance coefficients for each scenario.

[0076] A compliance inspection module 13, which is used to perform compliance inspection on the multiple characteristic rainfall scenarios according to the flood drainage response compliance coefficients for each scenario to generate target rainfall scenarios.

[0077] A pipe network layout adjustment module 14, which is used to obtain the above-ground and underground data sets of the target city, and perform adaptive layout adjustment on the drainage pipe network in combination with the target rainfall scenario to establish a pipe network layout adjustment space.

[0078] A multi-degree-of-freedom optimization module 15, which is used to perform multi-degree-of-freedom optimization on the pipe network layout adjustment space according to a pipe network loss prediction model to generate a first pipe network layout optimization strategy.

[0079] A pipe network status compensation module 16, which is used to obtain the multi-dimensional pipe network monitoring data of the drainage pipe network, and perform pipe network status compensation optimization on the first pipe network layout optimization strategy according to the multi-dimensional pipe network monitoring data to obtain a second pipe network optimization strategy.

[0080] Further, the rainfall scenario sorting module 11 is further used to perform the following steps: Perform pairwise difference degree evaluation based on the set of historical rainfall events to obtain a first differential detection distribution; classify the set of historical rainfall events according to the first differential detection distribution to obtain multiple rainfall event classes; perform inter-class difference degree evaluation on the multiple rainfall event classes to obtain a second differential detection distribution, and perform inter-class fusion on the multiple rainfall event classes according to the second differential detection distribution to obtain multiple rainfall event areas; perform rainfall feature recognition fusion for each rainfall event area within the multiple rainfall event areas to generate the multiple characteristic rainfall scenarios.

[0081] Furthermore, the waterlogging drainage response compliance calculation module 12 is further configured to perform the following steps: Extract a first characteristic rainfall scenario according to the multiple characteristic rainfall scenarios; retrieve the waterlogging drainage response duration of the drainage pipe network according to the first characteristic rainfall scenario to obtain a first rainfall scenario waterlogging drainage duration set; select the first rainfall scenario waterlogging drainage duration set according to the standard waterlogging drainage response duration to obtain a first compliant waterlogging drainage duration space less than or equal to the standard waterlogging drainage response duration; calculate the sample numbers of the first rainfall scenario waterlogging drainage duration set and the first compliant waterlogging drainage duration space to obtain a first scenario duration sample number and a first compliant duration sample number; calculate the ratio of the first compliant duration sample number to the first scenario duration sample number to obtain a first scenario waterlogging drainage response compliance coefficient, and add the first scenario waterlogging drainage response compliance coefficient to the waterlogging drainage response compliance coefficients of each scenario.

[0082] Furthermore, the compliance inspection module 13 is further configured to perform the following steps: Judge whether each scenario waterlogging drainage response compliance coefficient is less than the waterlogging drainage response compliance threshold to obtain multiple waterlogging drainage response compliance inspection results; screen the multiple characteristic rainfall scenarios according to the multiple waterlogging drainage response compliance inspection results to obtain a screening set of rainfall scenarios with unqualified responses; fuse the screening set of rainfall scenarios with unqualified responses to obtain the target rainfall scenario.

[0083] Furthermore, the pipe network layout adjustment module 14 is further configured to perform the following steps: Build a model according to the pipe network layout scheme of the drainage pipe network to obtain a three-dimensional pipe network model, and expand the three-dimensional pipe network model according to the above-ground and underground data sets to generate an urban drainage pipe network model; perform simulated drainage on the urban drainage pipe network model according to the target rainfall scenario to obtain pipe network simulated drainage data; perform risk identification according to the pipe network simulated drainage data to obtain a pipe network drainage risk identification result; adjust the pipe network layout scheme according to the pipe network drainage risk identification result to generate the pipe network layout adjustment space.

[0084] Furthermore, the multi-degree-of-freedom optimization module 15 is further configured to perform the following steps: Optimize the drainage response of the pipe network layout adjustment space according to the standard drainage response duration to establish the first optimization space for the pipe network layout adjustment; optimize the pipe network loss prediction for the first optimization space of the pipe network layout adjustment according to the pipe network loss prediction model to obtain the second optimization space for the pipe network layout adjustment; allocate weights to the multi-dimensional indexes of the pipe network loss prediction of the pipe network loss prediction model to obtain the pipe network comprehensive loss calculation model; optimize the minimization of the pipe network comprehensive loss for the second optimization space of the pipe network layout adjustment according to the pipe network comprehensive loss calculation model to obtain the first strategy for optimizing the pipe network layout.

[0085] Further, the multi-degree-of-freedom optimization module 15 is further configured to perform the following steps: Based on the target rainfall scenario, predict the drainage response duration for each pipe network layout adjustment plan in the pipe network layout adjustment space to obtain multiple predicted drainage response durations; determine whether the multiple predicted drainage response durations are less than or equal to the standard drainage response duration to obtain multiple drainage response judgment results; screen the pipe network layout adjustment space according to the multiple drainage response judgment results to obtain the first optimization space for the pipe network layout adjustment.

[0086] Further, the multi-degree-of-freedom optimization module 15 is further configured to perform the following steps: Extract the nth pipe network layout adjustment plan according to the first optimization space of the pipe network layout adjustment, where n is a positive integer; input the nth pipe network layout adjustment plan and the target rainfall scenario into the pipe network loss prediction model to obtain the nth pipe network loss prediction result, and the nth pipe network loss prediction result includes the nth drainage waterlogging loss coefficient, the nth drainage ground settlement loss coefficient, and the nth drainage pipeline loss coefficient; set multi-dimensional constraints for the pipe network loss prediction according to the multi-dimensional indexes of the pipe network loss prediction; determine whether the nth pipe network loss prediction result meets the multi-dimensional constraints of the pipe network loss prediction; if the nth pipe network loss prediction result meets the multi-dimensional constraints of the pipe network loss prediction, add the nth pipe network layout adjustment plan to the second optimization space of the pipe network layout adjustment.

[0087] Further, the pipe network state compensation module 16 is further configured to perform the following steps: Detect the abnormal state of the drainage pipe network according to the multi-dimensional data of the pipe network monitoring to obtain the detection result of the abnormal state of the pipe network; compensate and optimize the first strategy for optimizing the pipe network layout according to the detection result of the abnormal state of the pipe network to generate the second optimized strategy for optimizing the pipe network.

[0088] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the above description of specific embodiments of this specification has been made. Moreover, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0090] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An optimization method for urban drainage pipe networks based on big data, characterized in that, Including: Performing differential clustering on the historical rainfall event set of the target city to obtain multiple characteristic rainfall scenarios; Calculating the flood drainage response compliance of the drainage network of the target city according to the multiple characteristic rainfall scenarios to obtain the flood drainage response compliance coefficients for each scenario; Performing compliance inspection on the multiple characteristic rainfall scenarios according to the flood drainage response compliance coefficients for each scenario to generate the target rainfall scenario; Obtaining the above-ground and underground data set of the target city, adaptively adjusting the layout of the drainage network in combination with the target rainfall scenario, and establishing a pipe network layout adjustment space; Performing multi-degree-of-freedom optimization on the pipe network layout adjustment space according to the pipe network loss prediction model to generate the first pipe network layout optimization strategy; Obtaining the multi-dimensional pipe network monitoring data of the drainage network, and compensating and optimizing the pipe network state of the first pipe network layout optimization strategy according to the multi-dimensional pipe network monitoring data to obtain the second pipe network optimization strategy.

2. The method for optimizing urban drainage pipe networks based on big data according to claim 1, wherein, Performing differential clustering on the historical rainfall event set of the target city to obtain multiple characteristic rainfall scenarios, including: Evaluating the pairwise difference degree according to the historical rainfall event set to obtain the first differential detection distribution; Classifying the historical rainfall event set according to the first differential detection distribution to obtain multiple rainfall event classes; Evaluating the inter-class difference degree according to the multiple rainfall event classes to obtain the second differential detection distribution, and performing inter-class fusion on the multiple rainfall event classes according to the second differential detection distribution to obtain multiple rainfall event areas; Performing rainfall feature recognition and fusion for each rainfall event area in the multiple rainfall event areas to generate the multiple characteristic rainfall scenarios.

3. The method for optimizing urban drainage pipe networks based on big data according to claim 1, characterized in that, Calculating the flood drainage response compliance of the drainage network of the target city according to the multiple characteristic rainfall scenarios to obtain the flood drainage response compliance coefficients for each scenario, including: Extracting the first characteristic rainfall scenario according to the multiple characteristic rainfall scenarios; Retrieving the flood drainage response duration of the drainage network according to the first characteristic rainfall scenario to obtain the first rainfall scenario flood drainage duration set; Selecting the first rainfall scenario flood drainage duration set according to the standard flood drainage response duration to obtain the first compliant flood drainage duration space less than or equal to the standard flood drainage response duration; Calculating the sample numbers of the first rainfall scenario flood drainage duration set and the first compliant flood drainage duration space to obtain the first scenario duration sample number and the first compliant duration sample number; Calculating the proportion of the first compliant duration sample number and the first scenario duration sample number to obtain the flood drainage response compliance coefficient for the first scenario, and adding the flood drainage response compliance coefficient for the first scenario to the flood drainage response compliance coefficients for each scenario.

4. The method for optimizing urban drainage pipe networks based on big data according to claim 1, wherein, Obtaining the above-ground and underground data set of the target city, adaptively adjusting the layout of the drainage network in combination with the target rainfall scenario, and establishing a pipe network layout adjustment space, including: Modeling according to the pipe network layout plan of the drainage network to obtain a three-dimensional pipe network model, and expanding the three-dimensional pipe network model according to the above-ground and underground data set to generate an urban drainage pipe network model; Performing simulated drainage on the urban drainage pipe network model according to the target rainfall scenario to obtain the pipe network simulated drainage data; Perform risk identification based on the simulated drainage data of the pipe network to obtain the pipe network drainage risk identification result; Adjust the pipe network layout plan according to the pipe network drainage risk identification result to generate the pipe network layout adjustment space.

5. The method for optimizing urban drainage pipe networks based on big data according to claim 1, characterized in that Perform multi-degree-of-freedom optimization on the pipe network layout adjustment space according to the pipe network loss prediction model to generate the first pipe network layout optimization strategy, including: Perform drainage response optimization on the pipe network layout adjustment space according to the standard drainage response duration to establish the first optimization space for pipe network layout adjustment; Perform pipe network loss prediction optimization on the first optimization space for pipe network layout adjustment according to the pipe network loss prediction model to obtain the second optimization space for pipe network layout adjustment; Allocate weights to the multi-dimensional indexes of pipe network loss prediction of the pipe network loss prediction model to obtain the pipe network comprehensive loss calculation model; Perform pipe network comprehensive loss minimization optimization on the second optimization space for pipe network layout adjustment according to the pipe network comprehensive loss calculation model to obtain the first pipe network layout optimization strategy.

6. The method for optimizing urban drainage pipe networks based on big data according to claim 5, wherein, Perform drainage response optimization on the pipe network layout adjustment space according to the standard drainage response duration to establish the first optimization space for pipe network layout adjustment, including: Based on the target rainfall scenario, predict the drainage response duration for each pipe network layout adjustment plan in the pipe network layout adjustment space to obtain multiple predicted drainage response durations; Judge whether the multiple predicted drainage response durations are less than or equal to the standard drainage response duration to obtain multiple drainage response judgment results; Screen the pipe network layout adjustment space according to the multiple drainage response judgment results to obtain the first optimization space for pipe network layout adjustment.

7. The method for optimizing urban drainage pipe networks based on big data according to claim 5, characterized in that Perform pipe network loss prediction optimization on the first optimization space for pipe network layout adjustment according to the pipe network loss prediction model to obtain the second optimization space for pipe network layout adjustment, including: Extract the nth pipe network layout adjustment plan according to the first optimization space for pipe network layout adjustment, where n is a positive integer; Input the nth pipe network layout adjustment plan and the target rainfall scenario into the pipe network loss prediction model to obtain the nth pipe network loss prediction result, where the nth pipe network loss prediction result includes the nth drainage waterlogging loss coefficient, the nth drainage ground settlement loss coefficient, and the nth drainage pipe loss coefficient; Set multi-dimensional constraints for pipe network loss prediction according to the multi-dimensional indexes of pipe network loss prediction; Judge whether the nth pipe network loss prediction result meets the multi-dimensional constraints for pipe network loss prediction; If the nth pipe network loss prediction result meets the multi-dimensional constraints for pipe network loss prediction, add the nth pipe network layout adjustment plan to the second optimization space for pipe network layout adjustment.

8. The method for optimizing urban drainage pipe networks based on big data according to claim 1, characterized in that Perform pipe network state compensation optimization on the first pipe network layout optimization strategy according to the multi-dimensional pipe network monitoring data to obtain the second pipe network optimization strategy, including: Perform state anomaly detection on the drainage pipe network according to the multi-dimensional pipe network monitoring data to obtain the pipe network state anomaly detection result; Perform compensation optimization on the first pipe network layout optimization strategy according to the pipe network state anomaly detection result to generate the second pipe network optimization strategy.

9. The method for optimizing urban drainage pipe networks based on big data according to claim 1, wherein Performing compliance tests on the multiple characteristic rainfall scenarios according to the drainage response compliance coefficients of the respective scenarios to generate a target rainfall scenario, including: Judging whether the drainage response compliance coefficients of the respective scenarios are less than the drainage response compliance threshold to obtain multiple drainage response compliance test results; Screening the multiple characteristic rainfall scenarios according to the multiple drainage response compliance test results to obtain a screening set of rainfall scenarios with unqualified responses; Fusing the screening set of rainfall scenarios with unqualified responses to obtain the target rainfall scenario.

10. An urban drainage pipe network optimization device based on big data, characterized in that, The device is used to execute the big data-based urban drainage pipe network optimization method according to any one of claims 1 to 9. The device includes: A rainfall scenario sorting module, which is used to perform differential clustering sorting on the historical rainfall event set of the target city to obtain multiple characteristic rainfall scenarios; A drainage response compliance calculation module, which is used to perform drainage response compliance calculation on the drainage pipe network of the target city according to the multiple characteristic rainfall scenarios to obtain the drainage response compliance coefficients of the respective scenarios; A compliance test module, which is used to perform compliance tests on the multiple characteristic rainfall scenarios according to the drainage response compliance coefficients of the respective scenarios to generate a target rainfall scenario; A pipe network layout adjustment module, which is used to obtain the above-ground and underground data sets of the target city, and adaptively adjust the layout of the drainage pipe network in combination with the target rainfall scenario to establish a pipe network layout adjustment space; A multi-degree-of-freedom optimization module, which is used to perform multi-degree-of-freedom optimization on the pipe network layout adjustment space according to the pipe network loss prediction model to generate a first pipe network layout optimization strategy; A pipe network state compensation module, which is used to obtain the multi-dimensional pipe network monitoring data of the drainage pipe network, and perform pipe network state compensation optimization on the first pipe network layout optimization strategy according to the multi-dimensional pipe network monitoring data to obtain a second pipe network optimization strategy.

Images