Preplan generation method and device based on hydrodynamic model, equipment and medium

Abstract

The invention discloses a plan generation method and device based on a hydrodynamic model, equipment and a medium, and the method comprises the steps: obtaining current flood data, and determining a pre-stored hydrodynamic model based on the flood data; outputting a current plan corresponding to the current flood data based on a preset multi-objective optimization function; monitoring the flood data in real time, and optimizing the current plan according to the real-time monitoring data. According to the method, the plan generation time can be shortened, and the plan generation time can be shortened to be within ten minutes from several hours of traditional manual work based on the GPU acceleration and agent model. Through the high-precision hydrodynamic model and real-time data assimilation, the prediction error of submerging loss can be reduced. Meanwhile, multi-target conflicts are balanced through an optimization algorithm, and the emergency resource utilization rate can be increased.

Description

Technical Field

[0001] This application relates to the field of emergency plan generation, and specifically relates to a method, device, equipment and medium for generating an emergency plan based on a hydrodynamic model. Background Art

[0002] An emergency plan refers to a systematic and forward-looking preparation and response mechanism, aiming to minimize disaster losses. By generating an emergency plan, it is possible to plan in advance and allocate resources, improve response efficiency, reduce casualties and property losses, and ensure social order. Without an emergency plan, there may be resource contention, command chaos, and delay in the golden rescue time.

[0003] However, in the prior art, when generating an emergency plan corresponding to a flood scenario in the event of a flood, there are the following drawbacks: Traditional emergency plans rely on historical experience and cannot be dynamically adjusted according to the real-time flood scenario. In the prior art, hydrodynamic models are mostly used to simulate flood evolution, but lack a direct linkage mechanism with emergency decision-making. The generation of emergency plans relies on manual experience and it is difficult to quickly balance multi-objective conflicts. Summary of the Invention

[0004] To solve the above problems, this application proposes a method, device, equipment and medium for generating an emergency plan based on a hydrodynamic model, and the method includes: Obtain current flood data, and determine a pre-stored hydrodynamic model based on the flood data; output a current emergency plan corresponding to the current flood data based on a preset multi-objective optimization function; monitor the flood data in real time, and optimize the current emergency plan according to the real-time monitoring data.

[0005] In one embodiment, the flood data includes terrain data, hydrological data and engineering data; the terrain data includes river cross-section data, digital elevation model data and grid terrain data; the hydrological data includes upstream inflow data, downstream water level data, rainfall spatial distribution data; the engineering data includes parameters of each water conservancy facility, and the water conservancy facilities include at least one of sluice dams, pumping stations and levees.

[0006] In one embodiment, the pre-stored hydrodynamic model includes a one-dimensional river channel model, a two-dimensional flood inundation model, a model coupling formula, and boundary conditions.

[0007] In one embodiment, before outputting the current plan corresponding to the current flood data based on a preset multi-objective optimization function, the method further includes: determining a submerged economic loss function, an emergency response time function, and a resource consumption cost function corresponding to the flood plan; the submerged economic loss function is related to the asset density coefficient, the submerged depth, and the grid area; the emergency response time function is related to the evacuation time, the emergency rescue time, and the material arrival time; the resource consumption cost function is related to a preset coupling parameter, a human resource parameter, the number of input personnel, a device resource parameter, and the number of input devices; based on the submerged economic loss function, the emergency response time function, the resource consumption cost function, and the preset weights corresponding to each function, determining the multi-objective optimization function corresponding to the flood plan.

[0008] In one embodiment, outputting the current plan corresponding to the current flood data based on a preset multi-objective optimization function specifically includes: encoding the plan parameters into chromosomes in a preset format; running a hydrodynamic model for each chromosome and calculating the objective function value corresponding to each chromosome; based on the objective function value corresponding to each chromosome, hierarchically sorting all the chromosomes according to the Pareto dominance relationship; simulating the genetic operations corresponding to all the chromosomes by means of simulated binary crossover and polynomial mutation; merging the parent and offspring populations and retaining the chromosomes with objective function values not lower than a first preset threshold to the next generation; repeating the above genetic and retention processes until a target chromosome with an objective function value higher than a second preset threshold appears; outputting the plan parameters corresponding to the target chromosome to generate the current plan corresponding to the current flood data.

[0009] In one embodiment, before outputting the current plan corresponding to the current flood data based on a preset multi-objective optimization function, the method further includes: determining a key index value and an index threshold corresponding to the key index value; the key index types include at least one of water level exceeding the warning level, submerged depth, and flow velocity danger value; when the key index value is higher than the preset threshold, triggering corresponding response actions, and the response actions include at least one of starting flood diversion, starting evacuation, closing traffic, closing material allocation, and prohibiting people from entering dangerous areas.

[0010] In one embodiment, optimizing the current plan according to real-time monitoring data specifically includes: obtaining interval flood data in the real-time monitoring data based on a preset interval time; re-outputting the current plan through the interval flood data to replace the current plan corresponding to the previous preset interval time period.

[0011] The present application also provides a pre - plan generation device based on a hydrodynamic model, including: a model determination module, which acquires current flood data and determines a pre - stored hydrodynamic model based on the flood data; a pre - plan output module, which outputs a current pre - plan corresponding to the current flood data based on a preset multi - objective optimization function; and a pre - plan optimization module, which monitors flood data in real time and optimizes the current pre - plan according to the real - time monitoring data.

[0012] The present application also provides a pre - plan generation device based on a hydrodynamic model, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to: acquire current flood data and determine a pre - stored hydrodynamic model based on the flood data; output a current pre - plan corresponding to the current flood data based on a preset multi - objective optimization function; monitor flood data in real time and optimize the current pre - plan according to the real - time monitoring data.

[0013] The present application also provides a non - volatile computer storage medium storing computer - executable instructions, which are set to: acquire current flood data and determine a pre - stored hydrodynamic model based on the flood data; output a current pre - plan corresponding to the current flood data based on a preset multi - objective optimization function; monitor flood data in real time and optimize the current pre - plan according to the real - time monitoring data.

[0014] The method proposed by the present application can bring the following beneficial effects: it can shorten the pre - plan generation time. Based on GPU acceleration and surrogate models, the pre - plan generation time can be shortened from several hours of traditional manual work to within ten minutes. Through a high - precision hydrodynamic model and real - time data assimilation, the prediction error of flood losses can be reduced. At the same time, by optimizing the algorithm to balance multi - objective conflicts, the utilization rate of emergency resources can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings: Figure 1 is a schematic flow chart of a pre - plan generation method based on a hydrodynamic model in an embodiment of the present application; Figure 2 is a schematic structural diagram of a pre - plan generation device based on a hydrodynamic model in an embodiment of the present application; Figure 3 is a schematic structural diagram of a pre - plan generation device based on a hydrodynamic model in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0017] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0018] Figure 1 A schematic flow chart of a method for generating a plan based on a hydrodynamic model for one or more embodiments of this specification. The method can be applied to different flooding scenarios, such as emergency dispatching of urban rainstorm waterlogging, response to river flooding exceeding the standard, and flood control dispatching of major water conservancy projects. The process can be executed by a computing device in the corresponding field, and some input parameters or intermediate results in the process can be manually intervened and adjusted to help improve accuracy.

[0019] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.

[0020] It should be noted that the server can be a single device or a system composed of multiple devices, that is, a distributed server, and this application does not make any specific limitations on this.

[0021] like Figure 1 As shown, the embodiment of the present application provides a method for generating a plan based on a hydrodynamic model, comprising: S101: Acquire current flood data, and determine a pre-stored hydrodynamic model based on the flood data.

[0022] First, in order to determine the selected hydrodynamic model, it is necessary to collect current flood data to determine a hydrodynamic model that is more adaptable to the current flood scenario from multiple pre-stored hydrodynamic models.

[0023] Among them, the current flood data includes terrain data, hydrological data and engineering data; the terrain data includes river section data, digital elevation model data and grid terrain data; the hydrological data includes upstream inflow data, downstream water level data, and rainfall spatial distribution data; the engineering data includes parameters of various water conservancy facilities, and the water conservancy facilities include at least one of dams, pumping stations and dikes.

[0024] In one embodiment, the hydrodynamic model includes a one-dimensional river channel model, a two-dimensional flood inundation model, a model coupling formula, and boundary conditions.

[0025] An example of a hydrodynamic model is given here: Among them, the one-dimensional river channel model uses the Saint-Venant equations to describe the river flow movement, and the governing equations are:

[0026] Where, is the cross-sectional area of flow ( ), is the flow rate ( ), is the water level ( ), is the friction slope (dimensionless), is the lateral inflow ( ).

[0027] The two-dimensional flood inundation model can use the shallow water equations to describe the surface inundation process:

[0028] Where, , are respectively the flow velocities in the , directions ( ); is the ground elevation ( ), is the rainfall intensity ( ), I is the infiltration rate ( ), , are the bottom shear stresses (Pa).

[0029] The model coupling formula is used to achieve dynamic interaction through mass conservation at the junction of the river channel and the flood inundation area, and its formula is:

[0030] Where, is the dynamic interaction flow rate at the junction of the river channel (1D) and the flood inundation area (2D); is the flow coefficient (empirical value, usually taken as 0.6 - 0.8); is the length of the interaction interface (m); is the water level of the one-dimensional model, is the ground elevation of the two-dimensional model.

[0031] S102: Based on a preset multi-objective optimization function, output the current plan corresponding to the current flood data.

[0032] Through the preset multi-objective optimization function, the optimal plan corresponding to the current flood data can be output.

[0033] In one embodiment, before outputting the plan, it is necessary to determine a multi-objective optimization function. Specifically, the multi-objective optimization function includes a flooding economic loss function, an emergency response time function, and a resource consumption cost function. The flooding economic loss function is related to the asset density coefficient, the flooding depth, and the grid area; the emergency response time function is related to the evacuation time, the rescue time, and the arrival time of materials; the resource consumption cost function is related to the preset coupling parameters, the human resource parameters, the number of human resources invested, the equipment resource parameters, and the number of equipment invested. After determining the above-mentioned flooding economic loss function, the emergency response time function, and the resource consumption cost function, the multi-objective optimization function corresponding to the flood plan can be determined based on the flooding economic loss function, the emergency response time function, the resource consumption cost function, and the preset weights corresponding to each function.

[0034] In one embodiment, the flooding economic loss function can be expressed as:

[0035] in, is the flooding economic loss function, is the number of computational units or grid edges at the interface. If the boundary between the river channel and the floodplain is divided into 100 grid edges, then n=100. For the The asset density coefficient corresponding to the grid edge is: For the The flooding depth corresponding to each grid edge is For the The grid area.

[0036] In one embodiment, the emergency response time function can be expressed as:

[0037] in, is the emergency response time function, Evacuation time refers to the time from warning to the evacuation of all personnel (hours); The emergency rescue time refers to the time from the issuance of the order to the completion of the embankment reinforcement (hours); The arrival time of materials refers to the time (in hours) from dispatch to the arrival of materials in the disaster area.

[0038] In one embodiment, the resource consumption cost function can be expressed as:

[0039] in, is the resource consumption cost function, is the total number of resource types, is the resource parameter corresponding to the th type of human resource, is the th type of equipment resource corresponding to the resource parameter, is the th type of human resource input manpower quantity. For example, if 10 rescue teams are called, with 5 people in each team, then . is the th type of equipment resource input equipment quantity. For example, if 20 water pumps are deployed, then .

[0040] At this time, the multi-objective optimization function can be expressed as:

[0041] Among them, is the multi-objective optimization function expression.

[0042] In one embodiment, after determining the multi-objective optimization function, when outputting the current plan corresponding to the current flood data, a suitable flood plan can be determined by the genetic algorithm. Specifically, it is necessary to encode the plan parameters into a chromosome in a preset format. For example, chromosome = [flood diversion volume, gate opening sequence, evacuation path node]. Then run the hydrodynamic model for each chromosome and calculate the objective function value corresponding to each chromosome. Then, based on the objective function value corresponding to each chromosome, all chromosomes are sorted hierarchically according to the Pareto dominance relationship. At this time, the crowding degree can be calculated to ensure the diversity of the solution set, and then the genetic operations corresponding to all chromosomes are simulated in the way of simulated binary crossover and polynomial mutation. By merging the parent and offspring populations, and retaining the chromosomes whose objective function values are not lower than the first preset threshold to the next generation. Repeat the above genetic and retention processes until a target chromosome with an objective function value higher than the second preset threshold appears. At this time, the plan parameters corresponding to the target chromosome are output to generate the current plan corresponding to the current flood data.

[0043] In one embodiment, based on the preset multi-objective optimization function, before outputting the current plan corresponding to the current flood data, the key index value and the index threshold corresponding to the key index value can also be determined; the key index types include at least one of water level over-warning, inundation depth, and flow velocity danger value. When the key index value is higher than the preset threshold, corresponding response actions are triggered, and the response actions include at least one of starting flood diversion, starting evacuation, closing traffic, closing allocated materials, and prohibiting people from entering the dangerous area.

[0044] S103: Real-time monitor the flood data, and optimize the current plan according to the real-time monitoring data.

[0045] In one embodiment, after the above genetic model is determined, the model state can be updated through Kalman filtering and rolling horizon optimization can be performed to ensure that the optimized output plan can meet the flood scenario requirements under the current situation.

[0046] Among them, when performing rolling horizon optimization, interval flood data can be obtained from the real-time monitoring data based on a preset interval time; through the interval flood data, the current plan is re-output to replace the current plan corresponding to the previous preset interval time period.

[0047] Through the method provided by this application, the time for generating a plan can be shortened. Based on GPU acceleration and surrogate models, the time for generating a plan can be shortened from several hours of traditional manual work to within ten minutes. Through a high-precision hydrodynamic model and real-time data assimilation, the prediction error of flood losses can be reduced. At the same time, by optimizing the algorithm to balance multi-objective conflicts, the utilization rate of emergency resources can be improved.

[0048] As Figure 2 shown, an embodiment of this application also provides a plan generation device based on a hydrodynamic model, including: A model determination module 201, which obtains current flood data and determines a pre-stored hydrodynamic model based on the flood data. A plan output module 202, which outputs the current plan corresponding to the current flood data based on a preset multi-objective optimization function.

[0049] A plan optimization module 203, which monitors flood data in real time and optimizes the current plan according to the real-time monitoring data.

[0050] As Figure 3 shown, an embodiment of this application also provides a plan generation device based on a hydrodynamic model, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Obtain current flood data, and determine a pre-stored hydrodynamic model based on the flood data; output the current plan corresponding to the current flood data based on a preset multi-objective optimization function; monitor flood data in real time, and optimize the current plan according to the real-time monitoring data.

[0051] An embodiment of this application also provides a non-volatile computer storage medium, storing computer-executable instructions, and the computer-executable instructions are set as: Each embodiment in this application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the corresponding descriptions in the method embodiments.

[0052] The devices and media provided in the embodiments of this application correspond one by one to the methods. Therefore, the devices and media also have beneficial technical effects similar to those of their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be elaborated here.

[0053] Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program code.

[0054] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0055] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0057] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0058] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0059] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0060] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0061] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A pre-plan generation method based on a hydrodynamic model, characterized in that, Including: Obtain current flood data and determine a pre-stored hydrodynamic model based on the flood data; Output a current plan corresponding to the current flood data based on a preset multi-objective optimization function; Monitor flood data in real time and optimize the current plan according to the real-time monitoring data.

2. The method according to claim 1, wherein The flood data includes terrain data, hydrological data, and engineering data; The terrain data includes river cross-section data, digital elevation model data, and grid terrain data; The hydrological data includes upstream inflow data, downstream water level data, and rainfall spatial distribution data; The engineering data includes parameters of each water conservancy facility, and the water conservancy facilities include at least one of a sluice dam, a pumping station, and a levee.

3. The method according to claim 1, wherein The pre-stored hydrodynamic model includes a one-dimensional river model, a two-dimensional flood inundation model, a model coupling formula, and boundary conditions.

4. The method according to claim 1, wherein Before outputting the current plan corresponding to the current flood data based on the preset multi-objective optimization function, the method further includes: Determine a flood inundation economic loss function, an emergency response time function, and a resource consumption cost function corresponding to the flood plan; The flood inundation economic loss function is related to an asset density coefficient, a flood inundation depth, and a grid area; The emergency response time function is related to an evacuation time, a rescue time, and a material arrival time; The resource consumption cost function is related to a preset coupling parameter, a human resource parameter, the number of input human resources, a device resource parameter, and the number of input devices; Based on the flood inundation economic loss function, the emergency response time function, the resource consumption cost function, and preset weights corresponding to each function, determine the multi-objective optimization function corresponding to the flood plan.

5. The method according to claim 1, characterized in that, Outputting the current plan corresponding to the current flood data based on the preset multi-objective optimization function specifically includes: Encode the plan parameters into chromosomes in a preset format; Run the hydrodynamic model for each chromosome and calculate the objective function value corresponding to each chromosome; Based on the objective function values corresponding to each chromosome, perform hierarchical sorting on all chromosomes according to the Pareto dominance relationship; Simulate genetic operations corresponding to all the chromosomes by means of simulated binary crossover and polynomial mutation; Merge the parent and offspring populations and retain the chromosomes with objective function values not lower than a first preset threshold for the next generation; Repeat the above genetic and retention processes until a target chromosome with an objective function value higher than a second preset threshold appears; Output the plan parameters corresponding to the target chromosome to generate the current plan corresponding to the current flood data.

6. The method according to claim 1, characterized in that, Before outputting the current plan corresponding to the current flood data based on the preset multi-objective optimization function, the method further includes: Determine key index values and index thresholds corresponding to the key index values; the key index types include at least one of a water level exceeding the warning level, a flood inundation depth, and a flow velocity danger value; When the key index value is higher than the preset threshold, trigger corresponding response actions, and the response actions include at least one of starting flood diversion, starting evacuation, closing traffic, closing material allocation, and prohibiting people from entering dangerous areas.

7. The method according to claim 1, characterized in that Optimizing the current plan according to the real-time monitoring data specifically includes: Obtain interval flood data from the real-time monitoring data based on a preset interval time; Based on the interval flood data, re-output the current plan to replace the current plan corresponding to the previous preset interval time period.

8. A pre-plan generation device based on a hydrodynamic model, characterized in that, Comprising: A model determination module, which obtains current flood data and determines a pre-stored hydrodynamic model based on the flood data; A plan output module, which outputs the current plan corresponding to the current flood data based on a preset multi-objective optimization function; A plan optimization module, which monitors flood data in real time and optimizes the current plan according to the real-time monitoring data.

9. A pre-plan generation device based on a hydrodynamic model, characterized in that, Comprising: At least one processor; And a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute: Obtain current flood data and determine a pre-stored hydrodynamic model based on the flood data; Output the current plan corresponding to the current flood data based on a preset multi-objective optimization function; Monitor flood data in real time and optimize the current plan according to the real-time monitoring data.

10. A non-volatile computer storage medium stores computer-executable instructions, characterized in that, The computer-executable instructions are set to: Obtain current flood data and determine a pre-stored hydrodynamic model based on the flood data; Output the current plan corresponding to the current flood data based on a preset multi-objective optimization function; Monitor flood data in real time and optimize the current plan according to the real-time monitoring data.

Images