CN111859707A - Pipeline diameter determining method, urban waterlogging early warning method and device - Google Patents
Pipeline diameter determining method, urban waterlogging early warning method and device Download PDFInfo
- Publication number
- CN111859707A CN111859707A CN202010754453.9A CN202010754453A CN111859707A CN 111859707 A CN111859707 A CN 111859707A CN 202010754453 A CN202010754453 A CN 202010754453A CN 111859707 A CN111859707 A CN 111859707A
- Authority
- CN
- China
- Prior art keywords
- urban
- diameter
- pipeline
- depth
- ponding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Pipeline Systems (AREA)
Abstract
The invention provides a pipeline diameter determining method, an urban waterlogging early warning method and an urban waterlogging early warning device, and relates to the technical field of urban waterlogging management. The method for determining the diameter of the pipeline comprises the steps of obtaining the data of the amount of diffusion in seawater; acquiring urban drainage system parameters and urban precipitation data; according to the data of the amount of overflowing in seawater, urban precipitation data and urban drainage system parameters, establishing a mapping relation between the diameter of a pipeline in an urban drainage system and the depth of urban accumulated water; acquiring detection data of urban ponding depth; and determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding. The depth of the urban ponding is obtained through the overflowing amount data and the urban precipitation data in the sea water, then compared with the detection data of the depth of the urban ponding, the diameter of the pipeline is estimated through the Markov decision process, so that the diameter of the underground pipeline can be estimated, and the modeling precision of storm surge and flood simulation is improved.
Description
Technical Field
The invention relates to the technical field of urban waterlogging management, in particular to a pipeline diameter determining method, an urban waterlogging early warning method and an urban waterlogging early warning device.
Background
As storm surge disasters are listed as important factors threatening the safety of citizens, the marine physical model aims to solve the problem of urban flood caused by storm surge in coastal urban areas.
During storm surge, the sensors distributed in the urban areas of the Internet of things can be used for flood detection, the sensors are arranged in all areas in a city and used for monitoring the depth of accumulated water in the city so as to help the modeling of urban flood, but the degradation state of the sensors is difficult to identify because the pipeline is located underground.
Therefore, a method that can estimate the diameter of an underground pipe is urgently needed.
Disclosure of Invention
The problem solved by the invention is that the diameter of the existing underground pipeline is difficult to predict.
In order to solve the above problems, the present invention provides a method for determining a diameter of a pipe, including:
acquiring the data of the amount of overflowing in seawater;
acquiring urban drainage system parameters and urban precipitation data;
according to the seawater overflowing amount data, the urban precipitation data and the urban drainage system parameters, establishing a mapping relation between the diameter of a pipeline in the urban drainage system and the depth of urban accumulated water;
acquiring detection data of the depth of the urban ponding;
and determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding.
Therefore, as storm surge is mainly influenced by the ocean model and precipitation, the mapping relation between the diameter of the pipeline in the urban drainage system and the depth of urban ponding is established by acquiring the data of the overflowing amount in the seawater and the data of the urban precipitation, so that the depth of the urban ponding is obtained. In addition, the depth of the urban ponding is compared with the detection data of the depth of the urban ponding, and the diameter of the pipeline is continuously adjusted by utilizing the Markov decision process according to the comparison result, so that the more suitable diameter of the pipeline can be estimated, and the estimated diameter of the pipeline is closer to the actual application scene. Therefore, the obtained pipeline diameter is the optimal pipeline diameter and is relatively the closest to the actual scene, and the depth of the urban ponding is simulated through the obtained estimated pipeline diameter, so that the depth of the urban ponding obtained through simulation is closer to the actual urban ponding depth, and therefore the modeling precision of storm surge flood simulation is improved.
Optionally, in the obtaining of the seawater internal diffusion volume data, the seawater internal diffusion volume data is obtained through a SWAN model.
Therefore, the influence of the seawater volume data in the storm surge on the urban flood can be effectively simulated through the SWAN model, and the urban ponding depth calculation is facilitated.
Optionally, the establishing a mapping relationship between a diameter of a pipeline in the urban drainage system and a depth of the urban ponding according to the seawater internal diffusion data, the urban rainfall data and the urban drainage system parameters includes:
establishing an SWMM model according to the urban drainage system parameters;
and inputting the urban precipitation data into the SWMM model, wherein the SWMM model for inputting the urban precipitation data is the mapping between the diameter of the pipeline and the depth of the urban ponding.
Therefore, the mapping relation between the diameter of the pipeline in the urban drainage system and the depth of the urban ponding is established through the SWMM model, and after the diameter of the pipeline is obtained, the corresponding depth of the urban ponding can be obtained as long as the SWMM model with the established mapping relation is input, so that the calculation of the depth of the urban ponding is facilitated.
Optionally, the determining, according to the mapping relationship between the pipeline diameter and the depth of the urban water and the detection data of the depth of the urban water, the pipeline diameter through a markov decision process includes:
initializing the diameter of a pipeline;
performing a plurality of action treatments on the diameter of the pipeline to obtain a plurality of diameters of the pipeline after the action treatments;
according to the mapping relation between the pipeline diameter and the depth of the urban ponding, obtaining a plurality of calculated values of the depth of the urban ponding corresponding to the pipeline diameter after action processing;
iteratively calculating a feedback value of each action process according to the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding, acquiring the diameter of the pipeline corresponding to the maximum feedback value and updating the diameter of the initialized pipeline;
calculating the accuracy according to the calculated value of the depth of the urban ponding water corresponding to the updated diameter of the initialized pipeline and the detection data of the depth of the urban ponding water;
judging whether the accuracy meets a stopping condition;
and if the accuracy meets the stopping condition, taking the pipeline diameter corresponding to the maximum feedback value as the final pipeline diameter.
Like this, through the mapping relation of pipeline diameter and urban ponding degree of depth obtains a plurality of after action processing the calculated value of the urban ponding degree of depth that the pipeline diameter corresponds according to the calculated value of urban ponding degree of depth and the degree of proximity of the detection data of urban ponding degree of depth, constantly revises pipeline diameter, until obtaining the pipeline diameter that more accords with actual conditions, just stops judging. And the diameter of the pipeline corresponding to the maximum feedback value is used as the final diameter of the pipeline, so that the simulation precision of storm surge and flood is facilitated.
Optionally, determining the diameter of the pipeline through a markov decision process according to the mapping relationship between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding, further comprising:
and if the accuracy does not meet the stop condition, re-executing the step of performing a plurality of action processes on the pipe diameter to obtain a plurality of action-processed pipe diameters.
Therefore, when the accuracy rate fails to reach the satisfied stop condition, the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding still have a large deviation, and the diameter of the pipeline needs to be continuously adjusted. If the adjustment is not continued, the error between the obtained diameter of the pipeline and the actual diameter of the pipeline is larger, and the improvement of the simulation of urban flood is not facilitated.
Optionally, the accuracy calculation formula is:
wherein D issiCalculated value of urban ponding depth for the ith ponding point, DaiThe number of the water accumulation points is N.
Therefore, through a calculation formula of the accuracy, the deviation between the obtained simulated urban ponding depth and the actual detection data of the urban ponding depth can be calculated, and the diameter of the pipeline is adjusted through the deviation value, so that the obtained diameter of the pipeline is closer to the actual situation.
Optionally, the stopping condition is that the accuracy is greater than or equal to 90%.
Therefore, when the accuracy is greater than or equal to 90%, the deviation ratio between the simulated urban water depth and the actual detection data of the urban water depth is smaller, and the corresponding obtained pipeline diameter is more accurate than the actual pipeline diameter.
Secondly, a pipe diameter determining device is provided, comprising:
a first acquisition unit for acquiring the seawater overflowing amount data;
the second acquisition unit is used for acquiring urban drainage system parameters and urban precipitation data;
the mapping unit is used for establishing a mapping relation between the diameter of a pipeline in the urban drainage system and the depth of the urban accumulated water according to the seawater overflowing amount data, the urban precipitation data and the urban drainage system parameters;
the third acquisition unit is used for acquiring detection data of the depth of the urban ponding;
and the decision unit is used for determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding.
Compared with the prior art, the pipeline diameter determining device and the pipeline diameter determining method have the same beneficial effects, and are not repeated herein.
The urban waterlogging early warning method comprises the following steps:
acquiring predicted seawater overflowing amount, urban drainage system parameters and predicted urban precipitation data;
inputting the predicted seawater overflowing amount data, the predicted urban precipitation data, the urban drainage system parameters and the final pipeline diameter into an SWMM model to obtain a calculated value of the depth of the urban ponding, wherein the final pipeline diameter is obtained by adopting the pipeline diameter determining method;
and if the calculated value of the urban accumulated water depth is greater than the early warning value, early warning is carried out on a disaster prevention system.
Therefore, the obtained pipeline diameter is the optimal pipeline diameter and is relatively the closest to the actual scene, and the depth of the urban ponding is simulated through the obtained estimated pipeline diameter, so that the calculated value of the depth of the urban ponding obtained through simulation is closer to the actual depth of the urban ponding, and therefore the modeling precision of the storm surge and flood simulation is improved.
From time to time, provide an urban waterlogging early warning device, include:
the system comprises an acquisition unit, a storage unit and a control unit, wherein the acquisition unit is used for acquiring predicted seawater internal diffusion, urban drainage system parameters and predicted urban precipitation data;
the determining unit is used for inputting the predicted seawater internal diffusion data, the predicted urban precipitation data, the urban drainage system parameters and the final pipeline diameter into an SWMM model to obtain a calculated value of the urban ponding depth, wherein the final pipeline diameter is obtained by the method for determining the pipeline diameter;
and the early warning unit is used for early warning the disaster prevention system if the calculated value of the urban accumulated water depth is greater than the early warning value.
Compared with the prior art, the urban waterlogging early warning device and the urban waterlogging early warning method have the same beneficial effects, and are not repeated herein.
Finally, a computer readable storage medium is provided, storing instructions which, when loaded and executed by a processor, implement the method for determining a diameter of a pipeline as described above, or implement the method for warning of urban inland inundation as described above.
Drawings
FIG. 1 is a first flowchart of a method for determining a diameter of a pipe according to an embodiment of the present invention;
FIG. 2 is a second flowchart of a method for determining a diameter of a pipe according to an embodiment of the present invention;
FIG. 3 is a third flowchart of a method for determining a diameter of a pipe according to an embodiment of the present invention;
FIG. 4 is a fourth flowchart of a method for determining a diameter of a pipe according to an embodiment of the present invention;
FIG. 5 is a block diagram of a pipe diameter determining apparatus according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating an urban waterlogging warning method according to an embodiment of the present invention;
FIG. 7 is a flowchart illustrating a method for warning of urban waterlogging according to another embodiment of the present invention;
fig. 8 is a block diagram of an urban waterlogging warning device according to an embodiment of the present invention.
Description of reference numerals:
10-a first acquisition unit; 20-a second acquisition unit; 30-a mapping unit; 40-a third acquisition unit; 50-a decision unit; 91-an acquisition unit; 92-a determination unit; 93-early warning unit.
Detailed Description
Since storm surge disasters have been listed as important factors threatening the safety of citizens, these marine physical models are dedicated to solving the urban flood problem caused by storm surge in coastal urban areas. In 2013, zheng et al evaluated the correlation between extreme rainfall and storm surge at australian coastline 14 using a binary logic threshold excess model. In 2015, Jacob et al simulated hurricanes using the adirc model (advanced circular current model) and the simulated near-Shore Wave (SWAN) model and analyzed the effect of storm surge on the amount of garwitton rainfall in the houston area. In 2018, xu et al simulated storm surge in the lake area of the city of china using the maximum sustained wind model and the personal computer storm water management model, and evaluated the expected economic losses. These studies discuss the impact of rainstorms in urban areas. However, in practice, a number of factors in the city can affect the flood volume, severely reducing the accuracy of conventional methods.
The rainfall model, the runoff model and the surge model are important research contents for accurately predicting urban flood. Some studies have been directed to solving the coupling problem due to the lack of some a priori knowledge about the quantitative relationship between these three models. The SWMM Model (Storm Water Management Model) is widely used for rainstorm analysis, risk early warning, Water resource Management, and the like. A PCWMM model (urban storm sewage and rainfall flood management model) is generated by an SWMM model and is embedded into a geographic information system, and one-dimensional and two-dimensional analysis of rainfall runoff processes is provided. The PCWMM model can be used for real-time rainfall simulation, river modeling and the like. To combine the runoff model with the storm surge model, copula was used to obtain the appropriate distribution between the multiple parameters. copula functions describe the dependencies between variables and are actually a class of functions that connect together a joint distribution function and their respective edge distribution functions, and are therefore also referred to as connection functions. copula is used for flood risk assessment, rainfall frequency analysis, wind and surge analysis. However, if the accuracy of the input parameters is not reliable, the results of storm surge models and runoff models can introduce more uncertainty when using simple copula.
Traditional storm surge model precision is not high, and in addition, during storm surge, the thing networking sensor that distributes in urban area can be used for flood to detect, and these sensors set up each region in the city, monitor the interior ponding depth of city to help urban flood's modeling, nevertheless because the pipeline is located the underground, its degradation state is difficult to discern.
Therefore, a simulation model that can improve accuracy and a method that can estimate the diameter of an underground pipe are urgently needed.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Fig. 1 is a flowchart illustrating a method for determining a diameter of a pipe according to an embodiment of the present invention. The embodiment of the invention provides a method for determining the diameter of a pipeline, which comprises the following steps:
and S100, acquiring the data of the amount of diffusion in the seawater.
In the storm surge model, the ponding of the urban system is mainly influenced by strong precipitation caused by storm surge and the data of the amount of diffusion in the seawater caused by storm surge. The influence of storm surge on urban system ponding is simulated by acquiring the overflowing amount in seawater.
And S200, acquiring urban drainage system parameters and urban precipitation data.
The method comprises the steps of acquiring urban drainage system parameters, initializing the urban drainage system parameters, and acquiring urban precipitation data, wherein the urban precipitation data are the number of millimeters of daily precipitation collected from a meteorological website.
S300, establishing a mapping relation between the diameter of a pipeline in the urban drainage system and the depth of the urban accumulated water according to the seawater overflowing amount data, the urban precipitation data and the urban drainage system parameters.
The method comprises the steps of establishing a mapping relation between the diameter of a pipeline and the depth of urban ponding through an SWMM model, initializing parameters of the urban drainage system, inputting overflowing amount data in seawater, urban rainfall data and the parameters of the urban drainage system into the SWMM model, establishing the mapping relation between the diameter of the pipeline and the urban ponding, and inputting the diameter of the pipeline into the SWMM model to obtain a calculated value of the depth of the urban ponding corresponding to the diameter of the pipeline.
And S400, acquiring detection data of the depth of the urban ponding.
The detection data of the urban ponding depth refers to the actual ponding depth of a city, the detection data of the urban ponding depth is obtained through detection of a detection sensor, the water detection sensor in the Internet of things system is used as a small and cheap device and is an effective tool for monitoring the flood condition, and the detection sensor is arranged at important positions such as a pipeline junction point, a sub-basin and the like, so that real-time detection data are obtained.
S500, determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding.
Wherein, the mapping relation between the pipeline diameter and the urban water accumulation depth is established through an SWMM model. In the SWMM model, many elements in a city, such as related parameters of buildings, underground pipe networks and water storage equipment, need to be constructed, the parameters are initialized according to actual conditions, but no accurate actual data exist for the diameter of the underground pipe networks, so that the diameter of a pipeline needs to be continuously adjusted through a Markov decision process, and finally the diameter of the pipeline is determined. Among them, the markov Decision process is also called mdp (markov Decision process).
Therefore, as storm surge is mainly influenced by the ocean model and precipitation, the mapping relation between the diameter of the pipeline in the urban drainage system and the depth of urban ponding is established by acquiring the data of the overflowing amount in the seawater and the data of the urban precipitation, and thus the calculated value of the depth of the urban ponding is obtained. In addition, the calculated value of the depth of the urban ponding is compared with the detection data of the depth of the urban ponding, and the diameter of the pipeline is continuously adjusted by utilizing the Markov decision process according to the comparison result, so that the more suitable diameter of the pipeline can be estimated, and the estimated diameter of the pipeline is closer to the practical application scene. And inverting unknown data of the urban underground drainage system through a Markov decision process, and establishing a storm surge simulation system. Therefore, the obtained pipeline diameter is the optimal pipeline diameter and is relatively the closest to the actual scene, and the depth of the urban ponding is simulated through the obtained estimated pipeline diameter, so that the calculated value of the depth of the urban ponding obtained through simulation is closer to the actual depth of the urban ponding, and therefore the modeling precision of the storm surge and flood simulation is improved. Here, the storm surge is a storm surge which has occurred in history.
Specifically, in the step S100, in acquiring the seawater seepage data, the seawater seepage data is acquired through the SWAN model.
Therefore, the influence of the seawater volume data in the storm surge on the urban flood can be effectively simulated through the SWAN model, and the urban ponding depth calculation is facilitated.
The SWAN model is called a scaling Wave nershore, also called a shallow Wave numerical model. Obtaining the seawater overflowing amount data through the SWAN model, specifically, in step S100, obtaining the seawater overflowing amount data includes:
obtaining ocean historical data;
format conversion is carried out on the SWAN model parameters according to the ocean historical data to obtain initial SWAN model parameters;
and processing the initial SWAN model parameters according to a SWAN model to obtain the seawater internal diffusion data.
For example, when the downloaded historical data is in txt text format, the historical data needs to be input data in netCDF format when the SWAN model is input, so that the corresponding content in txt is filled into netCDF in the form of codes to complete the input of the SWAN model. After the data are input into the SWAN model, the SWAN model calculates to obtain the seawater diffusion data by using a nonlinear kinetic equation according to historical marine data.
Fig. 2 is a flowchart illustrating a method for determining a diameter of a pipe according to an embodiment of the present invention. Specifically, the S300, according to the seawater internal diffusion data, the urban precipitation data and the urban drainage system parameters, establishing a mapping relationship between a pipeline diameter and an urban accumulated water depth in the urban drainage system, including:
s310, establishing an SWMM model according to the urban drainage system parameters;
the urban drainage system parameters comprise inlet nodes, outlet nodes, descriptions, labels, shapes, maximum depths, length roughness, inlet offset, outlet offset, initial flow, maximum flow, inlet loss coefficients, outlet loss coefficients, average loss coefficients, flap gates and culvert specifications, and an SWMM model is established according to the urban drainage system parameters, namely the urban drainage system parameters are initialized, wherein part of the urban drainage system parameters have default values, and part of the parameters need to be set according to actual conditions. In practical application, the specific setting of the parameters of the urban drainage system can be set according to actual needs. The software of the SWMM model provides an interface for inputting the parameters and can be directly input into the software.
The parameters of the urban drainage system can also be called as SWMM model parameters, when the SWMM model parameters are initialized, the building and the pipeline can be well set, and the specific positions and connections can be well designed.
S320, inputting the urban precipitation data into the SWMM model, wherein the SWMM model for inputting the urban precipitation data is the mapping between the diameter of the pipeline and the depth of the urban ponding.
Therefore, the mapping relation between the diameter of the pipeline in the urban drainage system and the depth of the urban ponding is established through the SWMM model, and after the diameter of the pipeline is obtained, the calculated value of the depth of the urban ponding can be obtained as long as the SWMM model with the established mapping relation is input, so that the calculation of the depth of the urban ponding is facilitated. Among them, the SWMM is called Storm Water management model, also called Storm flood management model.
Fig. 3 is a flow chart of a method for determining a diameter of a pipe according to an embodiment of the present invention. The step S500 of determining the diameter of the pipeline through a markov decision process according to the mapping relationship between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding includes:
s510, initializing the diameter of the pipeline.
Wherein initializing the pipe diameter refers to assigning a value to the pipe diameter.
And S520, performing a plurality of action processes on the pipeline diameter to obtain a plurality of pipeline diameters subjected to the action processes.
Wherein, in the plurality of action treatments of the pipeline diameter, the action treatment refers to that the pipeline diameter is increased, or the pipeline diameter is reduced or kept unchanged. The multiple action processing of the pipe diameter refers to an operation of increasing or decreasing the pipe diameter more than once, but a plurality of operations of the pipe diameter. Different operation treatments are carried out each time, and different pipeline diameters are obtained.
In other words, the action processing refers to an operation of increasing or decreasing the diameter of the pipe by increasing or decreasing the diameter of the pipe, and there may be an operation of increasing or decreasing for each pipe. Each pipe may be added several times, for example, it may be set to what diameter of one unit of movement plus or minus is, for example, 0.1m, and on this basis, each pipe may be added once or added twice, or subtracted once or subtracted twice. Plus once means plus 0.1m per diameter and plus twice means plus 0.2m, and similarly, minus once means 0.1m per diameter reduction and minus twice means 0.2m diameter reduction. When the diameter of the pipeline is adjusted, the unit moving amplitude is relatively small, for example 0.01m, and although a relatively large pipe diameter range can be covered, the number of times of MDP iteration is relatively large, and the calculation amount is relatively large during calculation. When the diameter of the pipeline is adjusted, if the unit moving amplitude is large, for example, 0.5m, although the number of iterations of the MDP is reduced and the calculation amount is reduced, the final accuracy that can be finally achieved is poor. In the invention, the diameter unit movement of the pipeline is generally set to be 0.2m or 0.3m in the range that the comprehensive sampling can be carried out and the more pipe diameter ranges are covered and the iteration times are more suitable.
When a plurality of actions are processed, different actions are not related, and each action mainly tests the performance of each action independently.
Alternatively, to save computation time, several sets of actions may be chosen for the measurement, but ideally, it is desirable that all MDPs can be measured. For example, when there are only two pipelines, the arithmetic case of two pipelines is increased by the power of 2, the arithmetic case of three pipelines is increased by the power of 3, the arithmetic cases are all increased by the exponent, and when the single-core computer runs, the calculation load is very large. So sometimes monte carlo sampling is used, giving an upper limit, where it is then sampled uniformly, selecting several values to determine the result.
S530, obtaining a plurality of calculated values of the depth of the urban ponding corresponding to the pipeline diameter after action processing according to the mapping relation between the pipeline diameter and the depth of the urban ponding.
The mapping relation between the pipeline diameter and the depth of the urban ponding is realized through an SWMM model, different pipeline diameters are input into the SWMM model, and calculated values of different urban ponding depths are obtained correspondingly.
And S540, according to the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding, iteratively calculating the feedback value of each action process, acquiring the diameter of the pipeline corresponding to the maximum feedback value and updating the initialized diameter of the pipeline.
The detection data of the urban ponding depth refers to data obtained by detecting a plurality of ponding points respectively and correspondingly by a plurality of detection sensors. Specifically, the corresponding relationship between the ponding point and the detection sensor is that a plurality of detection sensors are arranged in a region of the detection sensors for measuring the ponding depth at positions near the urban building, one ponding point corresponds to one position point for arranging the detection sensors, each detection sensor respectively measures the detection data of the urban ponding depth of each ponding point, and each ponding point is independently measured. Secondly, the calculated value of the depth of urban ponding obtained according to the SWMM model is the ponding situation of one area, namely the situation of a plurality of ponding points. Comparing the calculated value of the simulated depth of the urban ponding water obtained by each ponding point with the detection data of the actually detected urban ponding depth, and comparing whether the calculated value of the simulated depth of the ponding water is close to the actual depth of the ponding water. If the deviation between the calculated value of the simulated water accumulation depth and the actual water accumulation depth is overlarge, the obtained feedback value is reverse feedback, and the reward (feedback value) is-1; if the deviation ratio between the calculated value of the simulated water accumulation depth and the actual water accumulation depth is small, the obtained feedback value is a positive feedback reward of +1. Each time the action processing is carried out, a corresponding feedback value is obtained, and the feedback values of the action processing carried out for a plurality of times are added, so that the better pipeline diameter can be obtained by comparing the magnitude of the feedback values. And after the pipeline diameter which is obtained correspondingly when the feedback value is maximum is judged, taking the pipeline diameter as the initial pipeline diameter of the next round.
And S550, calculating the accuracy according to the calculated value of the depth of the urban ponding corresponding to the updated diameter of the initialized pipeline and the detection data of the depth of the urban ponding.
And the accuracy is obtained by comparing the calculated value of the simulated accumulated water depth of each accumulated water point with the actual accumulated water depth and calculating the deviation between the calculated values. And calculating the deviation of each accumulated water point, and further judging the obtained accuracy.
S560, judging whether the accuracy meets the stop condition;
therefore, in order to enable the calculated value of the urban ponding depth of each ponding point to be as close as possible to the actually detected ponding depth and also take the practical application condition into consideration, the accuracy is set to judge whether the diameter of the pipeline at the moment is adjusted to be the closest to the actual condition.
And S570, if the accuracy meets the stop condition, taking the pipeline diameter corresponding to the maximum feedback value as the final pipeline diameter.
The accuracy is set within a certain range, as long as the accuracy reaches the required range, or the error is considered to be within the allowable range, namely the calculated value of the urban ponding depth of each ponding point is considered to be closer to the actually detected actual ponding depth at the moment, the diameter of the obtained pipeline is adjusted to be within the range closer to the actual situation at the moment, and therefore the diameter of the obtained pipeline is taken as the final diameter of the pipeline.
Like this, through the pipeline diameter and the mapping relation of the depth of urban ponding obtain the calculated value of the depth of urban ponding that a plurality of pipeline diameters correspond, according to the calculated value of the depth of urban ponding and the degree of proximity of the detection data of the depth of urban ponding, constantly modify pipeline diameter, until obtaining the pipeline diameter that more accords with actual conditions, just stop judging. And the diameter of the pipeline corresponding to the maximum feedback value is taken as the final diameter of the pipeline, so that the simulation of storm surge and flood is facilitated.
Specifically, in S530, obtaining a plurality of depths of the urban ponding corresponding to the diameters of the pipelines according to the mapping relationship between the diameters of the pipelines and the depths of the urban ponding includes:
and inputting the parameters of the urban drainage system, the data of the amount of diffusion in the seawater, the data of precipitation and the diameter of the pipeline into an SWMM model to obtain the depth of the urban accumulated water corresponding to the diameter of the pipeline.
The method comprises the steps of providing a data input interface for an SWMM model, initializing parameters of the SWMM model, namely parameters of the urban drainage system, inputting the initialized parameters of the urban drainage system, data of the diffusion in seawater, precipitation data and the diameter of a pipeline into the SWMM model through the data input interface, and outputting to obtain a calculated value of the depth of the urban ponding. Through the SWMM model, the simulation of urban ponding is facilitated.
Fig. 4 is a flowchart illustrating a method for determining a diameter of a pipe according to a fourth embodiment of the present invention. And S540, according to the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding, iteratively calculating each feedback value of the action processing, acquiring the diameter of the pipeline corresponding to the maximum feedback value and updating the diameter of the initialized pipeline, wherein the method comprises the following steps:
s541, calculating a standard deviation according to the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding, and obtaining a feedback value processed by each action;
wherein, the detection sensors are uniformly arranged in the city, and sensors for measuring water depth are arranged at the crossed positions of the pipelines. The action processing refers to changing the diameter of the pipeline to be thicker or thinner or not. There are different places of survey water level in the city, and city inside has a plurality of different ponding points promptly, and different ponding points have different water levels. And (3) acquiring the water accumulation depth of each simulated water accumulation point with different water accumulation points through the SWMM model, acquiring detection data of each water accumulation point with different water accumulation points through the detection sensor, and comparing the calculated value with the true value of each water accumulation point, wherein the deviation value between the calculated value and the true value is large or small. The standard deviation here refers to whether the deviation between the calculated value and the true value of the respective water accumulation point is large or small in the present case. When the deviation of the two values is larger, the real urban ponding depth is not similar to the calculated value of the simulated urban ponding depth, and the current action processing is not reasonable.
S542, iteratively calculating a feedback value of each action process;
since the action processing is performed more than once, that is, more than one step, more than several steps. When the first action processing decision is made, the next step is followed by a plurality of steps. After the action process is performed once, if the action process is not yet executed, the action process is performed again a plurality of times. In this way, whether or not the preceding operation processing is reasonable is determined by the feedback value. Iterative computation refers to accumulating feedback values for multiple actions.
And S543, acquiring the diameter of the pipeline corresponding to the maximum feedback value, and updating the initialized diameter of the pipeline.
Therefore, the feedback value of the iterative calculation can be compared to further feed back whether the action processing effect performed before is good or not good, so that the updating of the diameter of the pipeline is determined, and the final determination of the diameter of the pipeline is facilitated.
For iterative computation of feedback, three parameters are proposed, respectively a state transition probability matrix, a reward function and a discount factor. When the action is performed for the first time, a plurality of possible action states can be set as required, after the action for the first time is completed, the next possible action is continued on the basis, for example, 27 states exist in the action for the first time, 27 states exist in each possible action for the next action, the calculation is continued, and finally, a result exists in each case. Comparing the obtained result with the real measured value, so that an accuracy is provided, judging whether the two values are close, accumulating a plurality of rewarded actions, only participating in the discount factor nearest to the action, and multiplying the action far away from the action by a plurality of discount factors.
The initialization generates a plurality of actions, each action is weighted equally at the beginning, the probability of the first round is 1/27, for example, the probability of the first round is the same, because it is not known which action is better and which action is not better at the beginning of the action processing, and the probabilities are the same without any difference. After the first round is finished, it is known that some actions have very poor effects and some actions have better effects, an accumulated reward is calculated according to the result of the first round, the accumulated reward can be used for revising the state transition matrix, different actions in the second round have different probabilities, and when reward is calculated finally, the accumulated reward has a direct relation with the probability, namely the reward is multiplied by the probability, and then the final size is obtained, and then the pipeline selects which action to continue to execute.
Taking one pipe diameter as an example, for example, the initial pipe diameter is 3.0m, and after the operation processing, the initial pipe diameter becomes 3.1m and 2.9m, and the deviation ratio of 3.1 is small at this time, it is preferable to increase the pipe diameter, and at this time, the probability of the increased weight becomes large, the probability of the transition matrix becomes large, and the weight becomes large, so that in the case of performing the same calculation again for the second time, even if the pipe diameter obtained at the time of the next calculation is 3.0 to 3.2,3.2 may be selected due to the probability problem, and the state transition probability matrix is not corrected to a certain extent according to the previously calculated reward value as well, unlike the first time, the average probability is not selected.
Generally, there are 9 action processes, and 3 chances of seeing, that is, 3 action processes are performed as much as possible.
To facilitate understanding of the present invention, the iterative process, which is specifically illustrated below, takes 3 pipes as an example, first initializes the pipe diameters of the 3 pipes, all of which are set to 3m, 3m, 3m, and then generates a plurality of actions according to the MDP, wherein the actions refer to increasing the pipe diameter, decreasing the pipe diameter, or keeping the pipe diameter unchanged. The diameter of the pipeline can be increased/decreased by 0.1m, 0.2m or 0.3m, and the diameter can be adjusted by a little bit or more each time, and the diameter can be adjusted according to actual needs. When the pipe diameter is subjected to the operation processing, the increase of 0.1m in the pipe diameter is represented by +1.0, the decrease of 0.1 in the pipe diameter is represented by-1, and the constant change of the pipe diameter is represented by 0. After the pipe diameters of the 3 pipes are initialized, a plurality of actions are generated, for example, two actions in the plurality of actions, such as (+1.0, +1.0,0), (+1.0, -1.0, +1.0), are correspondingly generated, two corresponding pipe diameter groups are (3.1,3.1,3.0), (3.1,2.9,3.1), and are simulated by using SWMM respectively, so that two different calculated values of the urban ponding depth are obtained. After the calculated values of the depth of the urban water are obtained, the obtained calculated values of the depth of the urban water are respectively compared with the real detected values of the depth of the urban water, and a feedback value (reward) in the MDP is calculated to obtain R1 and R2. After calculating R1 and R2, the next action processing is continued based on (3.1,3.1,3.0), (3.1,2.9,3.1), such as processing actions of (+1.0, +1.0,0), (+1.0, -1.0, +1.0) for the first group and processing actions of (-1.0, -1.0, -1.0), (+1.0, -1.0, +1.0) for the second group, corresponding to (3.2,3.2,3.0), (3.2,3.0,3.1), (3.0,2.8,3.0), (3.2,2.8,3.2), and the obtained pipeline diameter is input to SWMM model simulation and compared with the detected data of city water depth to obtain four feedback values, R3626, R671, R672, R2 and R2, and then the previous iteration feedback values are obtained, the first two sets of actions (+1.0, +1.0,0) to be performed (+1.0, -1.0, +1.0) are obtained as feedback values R1+ discount rate (R1_1+ R1_2) and R2+ discount rate (R2_1+ R2_2), and a large feedback value is selected by comparing the two feedback values, and the corresponding pipe diameter having a large feedback value is selected as the pipe radius to be updated, for example, (3.1,3.1,3.0) is better if the value is larger by comparing R1+ discount rate (R1_1+ R1_2), and (3.1,2.9,3.1) is considered as a bad pipe diameter, and is discarded. The pipe diameter is updated to (3.1,3.1, 3.0). At this time, whether the calculation accuracy is greater than 90% is performed through a calculation formula of the accuracy, if the accuracy does not reach 90%, a next iteration is required, the next iteration is based on the pipeline diameters (3.1,3.1 and 3.0), a next cycle is performed, the cycle is stopped until the accuracy obtained through calculation reaches 90%, and the finally updated pipeline diameter is output as the final pipeline diameter.
Optionally, in S500, determining the diameter of the pipeline through a markov decision process according to the mapping relationship between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding, further including:
if the accuracy does not meet the stop condition, re-executing the step S520, performing a plurality of action processes on the pipe diameter, and obtaining a plurality of action-processed pipe diameters.
Therefore, when the accuracy rate fails to reach the satisfied stop condition, the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding still have a large deviation, and the diameter of the pipeline needs to be continuously adjusted. If the adjustment is not continued, the error between the obtained diameter of the pipeline and the actual diameter of the pipeline is larger, and the improvement of the simulation precision of the urban flood is not facilitated.
For the calculation of the accuracy, the accuracy is obtained through the depth of the urban ponding and the detection data of the depth of the urban ponding, and specifically, the accuracy calculation formula is as follows:
where Dsi is a calculated value of the depth of the urban ponding of the ith ponding point, Dai is detection data of the depth of the urban ponding of the ith ponding point, N is the number of ponding points, and it is stated in another way that N is a total number of points for testing ponding.
The method refers to the deviation of the inspection data of the depth of the urban ponding water of the ith ponding point and the depth of the urban ponding water of the ith ponding point, and the accuracy is determined by calculating a deviation value.
Like this, through the computational formula of rate of accuracy, can calculate the deviation between the calculated value of the simulation urban ponding degree of depth that obtains and the detection data of actual urban ponding degree of depth, and then adjust the pipeline diameter through the deviation value to make the pipeline diameter who obtains be the comparison and press close to actual conditions.
Optionally, the stopping condition is that the accuracy is greater than or equal to 90%.
Therefore, when the accuracy is greater than or equal to 90%, the deviation ratio between the calculated value of the simulated urban water depth and the actual detection data of the urban water depth is smaller, and the pipeline diameter obtained correspondingly at the moment is closer to the actual situation compared with the actual pipeline diameter.
In order to facilitate understanding of the scheme of the invention, the whole scheme is described as follows by way of example, for example, a storm surge disaster occurs, water depths of different areas of the current city are recorded through a sensor, and through the scheme of the invention, a city drainage system, namely the diameter of a pipeline of an underground pipe network, can be fitted, the drainage condition of the city is simulated, history fitting is completed, and the scheme can help to pre-simulate the city water depth before other storm surges come, so that the early warning purpose is achieved. Specifically, firstly, simulating the current storm surge by using a SWAN model and combining with ocean historical data to obtain the data of the amount of diffusion in the seawater in different places of the city. Inputting the data of the amount of diffusion in the seawater, the urban precipitation data, the initialized urban drainage system parameters and the pipeline diameter which are obtained by the SWAN model into the SWMM model to obtain the depth of the urban ponding. And then, comparing the obtained depth of the urban ponding with the depth of the urban ponding detected by the detection sensor, if the two depth values are different, resetting the diameter of the pipeline of the underground pipe network by using the MDP, and recalculating until the output simulated urban ponding depth is closer to the real detected urban ponding depth, thereby determining that the pipe network diameter of the underground pipe network obtained at the moment is the optimal simulated inner diameter.
The invention relates to an integrated city Internet of things detection system, which is combined with a SWAN model and a SWMM model to simulate storm surge and flood and utilizes MDP to fit the degradation state of an underground pipeline so as to achieve the aim of early warning and control of the storm surge disaster of a coastal city. Specifically, the ocean history data is processed and then input into a SWAN model for simulating offshore storm surge. The seawater overflowing amount data contained in the simulation result of the SWAN model can be used in the SWMM model. Meanwhile, the SWMM model has parameters needing initialization, namely urban system drainage system parameters, and the parameters need to initialize object attributes such as impervious areas, pipelines, nodes and the like according to an actual scene.
Fig. 5 is a block diagram of a pipe diameter determining apparatus according to an embodiment of the present invention. The embodiment of the invention also provides a device for determining the diameter of the pipeline, which comprises:
a first acquisition unit 10 for acquiring seawater overflowing amount data;
a second obtaining unit 20, configured to obtain urban drainage system parameters and urban precipitation data;
the mapping unit 30 is used for establishing a mapping relation between the diameter of a pipeline in the urban drainage system and the depth of the urban accumulated water according to the seawater overflowing amount data, the urban precipitation data and the urban drainage system parameters;
a third obtaining unit 40, configured to obtain detection data of the depth of the urban ponding;
and the decision unit 50 is used for determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding.
Compared with the prior art, the pipeline diameter determining device and the pipeline diameter determining method have the same beneficial effects, and are not repeated herein.
Further, in the first obtaining unit 10, the seawater overflowing amount data is obtained through a SWAN model.
Further, in the mapping unit 30, an SWMM model is established according to the parameters of the urban drainage system; and inputting the urban precipitation data into the SWMM model, wherein the SWMM model for inputting the urban precipitation data is the mapping between the diameter of the pipeline and the depth of the urban ponding.
Further, the decision unit 50 is further configured to initialize a pipe diameter, perform multiple action processing on the pipe diameter, and obtain multiple pipe diameters subjected to action processing; according to the mapping relation between the pipeline diameter and the depth of the urban ponding, obtaining a plurality of calculated values of the depth of the urban ponding corresponding to the pipeline diameter after action processing; iteratively calculating a feedback value of each action process according to the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding, acquiring the diameter of the pipeline corresponding to the maximum feedback value and updating the diameter of the initialized pipeline; calculating the accuracy according to the calculated value of the depth of the urban ponding water corresponding to the updated diameter of the initialized pipeline and the detection data of the depth of the urban ponding water; judging whether the accuracy meets a stopping condition; and if the accuracy meets the stop condition, taking the pipeline diameter corresponding to the maximum feedback value as the final pipeline diameter.
Further, in the decision unit 50, if the accuracy does not satisfy the stop condition, the multiple motion processing on the pipe diameter is executed again, and multiple motion processed pipe diameters are obtained.
Further, the accuracy calculation formula is as follows:
wherein D issiCalculated value of urban ponding depth for the ith ponding point, DaiThe number of the water accumulation points is N.
Further, the stopping condition is that the accuracy is greater than or equal to 90%.
Fig. 6 is a flowchart illustrating an urban waterlogging warning method according to an embodiment of the present invention. The embodiment of the invention also provides an urban waterlogging early warning method, which comprises the following steps:
s1, acquiring the predicted amount of diffusion in the seawater, the urban drainage system parameters and the predicted urban precipitation data;
s2, inputting the predicted seawater overflowing amount data, the predicted urban precipitation data, the urban drainage system parameters and the final pipeline diameter into an SWMM model to obtain a calculated value of the depth of the urban ponding, wherein the final pipeline diameter is obtained by adopting the pipeline diameter determining method;
wherein, in the final pipeline diameter obtained, the pipeline setting will cover the research area, each pipeline will be set with a diameter, and the same pipeline is the same diameter.
And S3, if the calculated value of the urban accumulated water depth is larger than the early warning value, early warning is carried out on the disaster prevention system.
Generally, a safety threshold value is preset in a flood control system of a city system, when a calculated value of the depth of urban accumulated water is within the safety threshold value, the calculated value indicates that the urban accumulated water is still in a safe state, and if the depth of the accumulated water exceeds the safety threshold value, early warning is carried out to remind a corresponding management department to take certain flood fighting measures so as to ensure the personal and property safety of urban citizens.
Like this, because storm surge is mainly influenced by ocean model and urban precipitation data, through obtaining the interior overflowing volume data of sea water, urban precipitation data and urban drainage system parameter, establish the mapping relation of pipeline diameter and urban ponding degree of depth in the urban drainage system, in addition, through the calculated value of urban ponding degree of depth and the detection data of urban ponding degree of depth, estimate out the pipeline diameter through markov's decision-making process to confirm the size that can estimate underground pipeline diameter in the urban system, improved storm surge flood simulation's modeling precision. Through the obtained final diameter of the pipeline, the prediction and simulation of the depth of urban ponding can be performed before other storm surge comes, and the early warning purpose is achieved.
Historical marine data is simulated by using SWAN, then the diameter of an underground pipeline is determined by other methods, and if the future diffusion in seawater is to be predicted, other data, such as predicted wind field data, are needed and input into the SWAN model, and then the prediction can be carried out by combining with the previously obtained pipeline diameter of the underground pipe network. Therefore, the obtained seawater diffusion amount can be obtained not only through one or two data, and if the future seawater diffusion amount is to be predicted, the final pipeline diameter is determined and then combined with other data, and then prediction is carried out. Fig. 7 is a flowchart illustrating an urban waterlogging warning method according to another embodiment of the present invention. Specifically, the step S1 of obtaining the predicted seawater internal diffusion amount includes:
s11, acquiring estimated ocean data;
and S12, inputting the estimated ocean data into the SWAN model to obtain the predicted seawater internal diffusion.
Wherein the marine data comprises: shore line data, water depth data, salinity data, temperature data, wind field data and tide data. Some of the input data in the input SWAN model is real-time changing, such as wind field data, and some is considered constant over time, such as tidal data. Or taking wind field data and tide data as an example, when the wind field data is input into the SWAN model, the wind field data is estimated before being input, and then the wind field data is input into the model, wherein the wind field can be estimated by using the WRF model. For tidal data, harmonic constants are input. The ocean data which are estimated firstly and the ocean data which are relatively constant are input into the SWAN model, so that the predicted seawater internal diffusion is obtained. Therefore, the estimated ocean data is input into the SWAN model by estimating the ocean data, so that the predicted seawater diffusion is obtained.
Wherein some of these said ocean data are available for download abroad.
Fig. 8 is a block diagram of an urban waterlogging warning device according to an embodiment of the present invention. The embodiment of the invention also provides an urban waterlogging early warning device, which comprises:
an obtaining unit 91 for obtaining the predicted amount of flooding in seawater, the parameter of the urban drainage system, and the predicted urban precipitation data;
a determining unit 92, configured to input the predicted seawater internal diffusion data, the predicted urban precipitation data, the urban drainage system parameter, and a final pipeline diameter into an SWMM model to obtain a calculated value of an urban ponding depth, where the final pipeline diameter is obtained by using the method for determining a pipeline diameter as described above;
and the early warning unit 93 is used for early warning the disaster prevention system if the calculated value of the urban water accumulation depth is greater than the early warning value.
Compared with the prior art, the urban waterlogging early warning device and the urban waterlogging early warning method have the same beneficial effects, and are not repeated herein.
The embodiment of the present disclosure provides a computer-readable storage medium, which stores instructions, and when the instructions are loaded and executed by a processor, the method for determining a pipeline diameter is implemented, or the method for early warning of urban waterlogging is implemented.
The technical solution of the embodiment of the present invention substantially or partly contributes to the prior art, or all or part of the technical solution may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method according to the embodiment of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.
Claims (11)
1. A method of determining a diameter of a pipe, comprising:
acquiring the data of the amount of overflowing in seawater;
acquiring urban drainage system parameters and urban precipitation data;
according to the seawater overflowing amount data, the urban precipitation data and the urban drainage system parameters, establishing a mapping relation between the diameter of a pipeline in the urban drainage system and the depth of urban accumulated water;
acquiring detection data of the depth of the urban ponding;
and determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding.
2. The method according to claim 1, wherein the obtaining of the seawater internal diffusion data is performed by obtaining the seawater internal diffusion data through a SWAN model.
3. The method for determining the diameter of the pipeline according to claim 1 or 2, wherein the step of establishing a mapping relation between the diameter of the pipeline in the urban drainage system and the depth of the urban drainage system according to the data of the amount of diffusion in the seawater, the data of the urban precipitation and the parameters of the urban drainage system comprises the following steps:
establishing an SWMM model according to the urban drainage system parameters;
and inputting the urban precipitation data into the SWMM model, wherein the SWMM model for inputting the urban precipitation data is the mapping between the diameter of the pipeline and the depth of the urban ponding.
4. The method for determining the diameter of the pipeline according to claim 1 or 2, wherein the step of determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding comprises the following steps:
initializing the diameter of a pipeline;
performing a plurality of action treatments on the diameter of the pipeline to obtain a plurality of diameters of the pipeline after the action treatments;
according to the mapping relation between the pipeline diameter and the depth of the urban ponding, obtaining a plurality of calculated values of the depth of the urban ponding corresponding to the pipeline diameter after action processing;
iteratively calculating a feedback value of each action process according to the calculated value of the depth of the urban ponding and the detection data of the depth of the urban ponding, acquiring the diameter of the pipeline corresponding to the maximum feedback value and updating the diameter of the initialized pipeline;
calculating the accuracy according to the calculated value of the depth of the urban ponding water corresponding to the updated diameter of the initialized pipeline and the detection data of the depth of the urban ponding water;
judging whether the accuracy meets a stopping condition;
and if the accuracy meets the stopping condition, taking the pipeline diameter corresponding to the maximum feedback value as the final pipeline diameter.
5. The method of claim 4, wherein the determining the diameter of the pipeline through a Markov decision process according to the mapping relationship between the diameter of the pipeline and the depth of the municipal water and the detection data of the depth of the municipal water further comprises:
and if the accuracy does not meet the stop condition, re-executing the pipeline diameter to perform a plurality of action processes, and acquiring a plurality of pipeline diameters subjected to the action processes.
6. The pipe diameter determination method according to claim 4, wherein the accuracy calculation formula is:
wherein D issiCalculated value of urban ponding depth for the ith ponding point, DaiThe number of the water accumulation points is N.
7. The pipe diameter determination method according to claim 4, wherein the stop condition is that the accuracy is greater than or equal to 90%.
8. A pipe diameter determining apparatus, comprising:
a first acquisition unit (10) for acquiring seawater overflowing amount data;
a second acquisition unit (20) for acquiring urban drainage system parameters and urban precipitation data;
the mapping unit (30) is used for establishing a mapping relation between the diameter of a pipeline in the urban drainage system and the depth of the urban accumulated water according to the seawater overflowing amount data, the urban precipitation data and the urban drainage system parameters;
a third acquisition unit (40) for acquiring detection data of the depth of the urban ponding;
and the decision unit (50) is used for determining the diameter of the pipeline through a Markov decision process according to the mapping relation between the diameter of the pipeline and the depth of the urban ponding and the detection data of the depth of the urban ponding.
9. An urban waterlogging early warning method is characterized by comprising the following steps:
acquiring predicted seawater overflowing amount, urban drainage system parameters and predicted urban precipitation data;
inputting the predicted seawater internal diffusion data, the predicted urban precipitation data, the urban drainage system parameters and the final pipeline diameter into an SWMM model to obtain a calculated value of the urban ponding depth, wherein the final pipeline diameter is obtained by adopting the pipeline diameter determining method according to any one of claims 1 to 7;
and if the calculated value of the urban accumulated water depth is greater than the early warning value, early warning is carried out on a disaster prevention system.
10. The utility model provides an urban waterlogging early warning device which characterized in that includes:
an acquisition unit (91) for acquiring the predicted amount of flooding in seawater, urban drainage system parameters and predicted urban precipitation data;
a determining unit (92) for inputting the predicted seawater overflow data, the predicted urban precipitation data, the urban drainage system parameters and a final pipe diameter into a SWMM model to obtain a calculated value of the depth of the urban ponding, wherein the final pipe diameter is obtained by the method for determining the pipe diameter according to any one of claims 1 to 7;
and the early warning unit (93) is used for early warning the disaster prevention system if the calculated value of the urban water accumulation depth is greater than the early warning value.
11. A computer readable storage medium storing instructions which, when loaded and executed by a processor, carry out the method of pipe diameter determination according to any one of claims 1 to 7 or carry out the method of early warning of urban waterlogging according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010754453.9A CN111859707B (en) | 2020-07-31 | 2020-07-31 | Pipeline diameter determining method, urban waterlogging early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010754453.9A CN111859707B (en) | 2020-07-31 | 2020-07-31 | Pipeline diameter determining method, urban waterlogging early warning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111859707A true CN111859707A (en) | 2020-10-30 |
| CN111859707B CN111859707B (en) | 2023-06-16 |
Family
ID=72945249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010754453.9A Active CN111859707B (en) | 2020-07-31 | 2020-07-31 | Pipeline diameter determining method, urban waterlogging early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111859707B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101692273A (en) * | 2009-09-28 | 2010-04-07 | 北京工业大学 | Modeling method of on-line hydraulic model of municipal drainage pipe network |
| CN105550803A (en) * | 2015-12-08 | 2016-05-04 | 哈尔滨航天恒星数据系统科技有限公司 | Urban water-logging analysis method and urban water-logging analysis system |
| CN106777460A (en) * | 2016-11-11 | 2017-05-31 | 重庆大学 | A kind of method that Urban Rainwater Pipe Networks caliber and the gradient are determined based on SWMM hydraulic models |
| CN107687878A (en) * | 2016-09-14 | 2018-02-13 | 宝沃汽车（中国）有限公司 | Method, apparatus and vehicle for the estimation depth of accumulated water of vehicle |
| CN108107488A (en) * | 2017-12-21 | 2018-06-01 | 广州积雨云科技有限公司 | Urban waterlogging method for early warning |
| CN110837925A (en) * | 2019-11-04 | 2020-02-25 | 浙江贵仁信息科技股份有限公司 | Urban waterlogging prediction method and device |
| CN111080070A (en) * | 2019-11-19 | 2020-04-28 | 同济大学 | Urban land utilization cellular automata simulation method based on spatial error |
-
2020
- 2020-07-31 CN CN202010754453.9A patent/CN111859707B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101692273A (en) * | 2009-09-28 | 2010-04-07 | 北京工业大学 | Modeling method of on-line hydraulic model of municipal drainage pipe network |
| CN105550803A (en) * | 2015-12-08 | 2016-05-04 | 哈尔滨航天恒星数据系统科技有限公司 | Urban water-logging analysis method and urban water-logging analysis system |
| CN107687878A (en) * | 2016-09-14 | 2018-02-13 | 宝沃汽车（中国）有限公司 | Method, apparatus and vehicle for the estimation depth of accumulated water of vehicle |
| CN106777460A (en) * | 2016-11-11 | 2017-05-31 | 重庆大学 | A kind of method that Urban Rainwater Pipe Networks caliber and the gradient are determined based on SWMM hydraulic models |
| CN108107488A (en) * | 2017-12-21 | 2018-06-01 | 广州积雨云科技有限公司 | Urban waterlogging method for early warning |
| CN110837925A (en) * | 2019-11-04 | 2020-02-25 | 浙江贵仁信息科技股份有限公司 | Urban waterlogging prediction method and device |
| CN111080070A (en) * | 2019-11-19 | 2020-04-28 | 同济大学 | Urban land utilization cellular automata simulation method based on spatial error |
Non-Patent Citations (4)
| Title |
|---|
| 宋耘等: "基于SWMM模型的南京典型易涝区暴雨内涝模拟", 《水利水电科技进展》 * |
| 符锐等: "SWMM模型在城市排水防涝系统能力评估中的应用", 《中国农村水利水电》 * |
| 贾艳梅等: "基于SWMM模型的沧州市区暴雨积水深度模拟", 《河北工程技术高等专科学校学报》 * |
| 黄丹萍等: "南宁城市内涝分布特征及其监测预警系统应用分析", 《防灾科技学院学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111859707B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Benedetti et al. | Modelling and monitoring of integrated urban wastewater systems: review on status and perspectives | |
| Onen et al. | Prediction of flood frequency factor for Gumbel distribution using regression and GEP model | |
| Kisi et al. | A machine code-based genetic programming for suspended sediment concentration estimation | |
| Nandalal et al. | Event based modeling of a watershed using HEC-HMS | |
| CN115471078B (en) | Flood risk point assessment method and device based on urban water affair system | |
| Emamgholizadeh et al. | Comparison of artificial neural networks, geographically weighted regression and Cokriging methods for predicting the spatial distribution of soil macronutrients (N, P, and K) | |
| Ay et al. | Artificial intelligence (AI) studies in water resources | |
| CN115909664A (en) | BIM-based river channel safety early warning method, device and equipment | |
| Balla et al. | A nonlinear predictive control approach for urban drainage networks using data-driven models and moving horizon estimation | |
| Yin et al. | Identification of pollution sources in rivers using a hydrodynamic diffusion wave model and improved Bayesian-Markov chain Monte Carlo algorithm | |
| Domhof et al. | Discharge and location dependency of calibrated main channel roughness: case study on the River Waal | |
| Wang et al. | Uncertainty analysis of a pollutant-hydrograph model in assessing inflow and infiltration of sanitary sewer systems | |
| Petersen‐Øverleir et al. | Bayesian analysis of stage–fall–discharge models for gauging stations affected by variable backwater | |
| Mazzoleni et al. | Data assimilation in hydrologic routing: Impact of model error and sensor placement on flood forecasting | |
| CN111859707B (en) | Pipeline diameter determining method, urban waterlogging early warning method and device | |
| KR101703809B1 (en) | Discharge estimation method for ungauged basin using known discharge transfer | |
| CN117132575A (en) | Improved PointNet++ based three-dimensional detection method for defects of drainage pipeline | |
| Viero | Comment on “Can assimilation of crowdsourced data in hydrological modelling improve flood prediction?” by Mazzoleni et al.(2017) | |
| Wu et al. | Modeling probabilistic lag time equation in a watershed based on uncertainties in rainfall, hydraulic and geographical factors | |
| Tananaev | Fitting sediment rating curves using regression analysis: a case study of Russian Arctic rivers | |
| Li et al. | System response curve correction method of runoff error for real-time flood forecast | |
| Hansen et al. | Flow forecasting in urban drainage systems using deterministic updating of water levels in distributed hydraulic models | |
| Wu et al. | Application of modified nonlinear storage function on runoff estimation | |
| CN112417705A (en) | Island sea area extreme value wave calculation method based on environment contour line | |
| CN116882215B (en) | Multi-element self-excitation early warning method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |