CN115689168A - Accumulated water emergency scheduling method based on accumulated water prediction - Google Patents
Accumulated water emergency scheduling method based on accumulated water prediction Download PDFInfo
- Publication number
- CN115689168A CN115689168A CN202211241381.3A CN202211241381A CN115689168A CN 115689168 A CN115689168 A CN 115689168A CN 202211241381 A CN202211241381 A CN 202211241381A CN 115689168 A CN115689168 A CN 115689168A
- Authority
- CN
- China
- Prior art keywords
- rainfall
- ponding
- target area
- prediction
- model
- 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.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000009825 accumulation Methods 0.000 claims abstract description 34
- 238000009826 distribution Methods 0.000 claims abstract description 33
- 239000002352 surface water Substances 0.000 claims abstract description 21
- 238000003062 neural network model Methods 0.000 claims description 24
- 230000008595 infiltration Effects 0.000 claims description 12
- 238000001764 infiltration Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000000611 regression analysis Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 13
- 238000012545 processing Methods 0.000 description 6
- 230000006735 deficit Effects 0.000 description 5
- 230000008020 evaporation Effects 0.000 description 5
- 238000001704 evaporation Methods 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000010865 sewage Substances 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 206010000210 abortion Diseases 0.000 description 1
- 231100000176 abortion Toxicity 0.000 description 1
- 239000005442 atmospheric precipitation Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- 235000020681 well water Nutrition 0.000 description 1
- 239000002349 well water Substances 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Sewage (AREA)
Abstract
The invention discloses a ponding emergency scheduling method based on ponding prediction, which overcomes the problems of low comprehensive automation degree and comprehensive operation efficiency of urban drainage in the prior art, and comprises the following steps: s1: according to rainfall forecast data, a rainfall prediction model is established; s2: according to the rainfall, establishing a surface water prediction model; s3: acquiring underground pipe network distribution information of a target area, and determining a drainage pump station of a ponding point; s4: and scheduling the drainage pump station by combining the predicted distribution condition of the water accumulation points and the water accumulation depth. The rainfall can be predicted according to the meteorological data, and the ponding distribution information can be predicted according to the rainfall, so that the drainage system is dispatched, the comprehensive automation of drainage is realized, and the comprehensive operation efficiency of drainage is improved.
Description
Technical Field
The invention relates to the technical field of flood prevention dispatching, in particular to a ponding emergency dispatching method based on ponding prediction.
Background
In recent years, the frequency and intensity of extreme weather has increased significantly due to global warming. The method has the advantages of strong rainfall in many places in China, long duration, large accumulated rainfall, concentrated time periods and extreme property. Due to the shortage of urban space resources, electric power equipment such as cables, power transformation equipment, power distribution equipment and the like are gradually transferred to the underground. Under the influence of extreme rainfall, the urban frequent underground distribution/transformation houses and cable well water accumulation events. The power equipment is soaked in the accumulated water, so that flashover discharge and short-circuit faults of the insulation part of the equipment are caused, even tripping is caused, large-area power failure is caused, in addition, electric leakage is easily caused, personal injury is caused, and heavy rainfall and waterlogging are becoming major hidden dangers of power safety.
The drainage system is an engineering facility system for treating and removing sewage and rainwater, and is a component of urban public facilities, and the urban drainage system planning is a component of urban overall planning. Municipal drainage systems usually consist of drainage pipelines and sewage treatment plants. The urban drainage system is called as one of urban lifeline systems, is an important mark for measuring the urban modernization level, is the most important infrastructure for ensuring the normal operation of urban life, and any link lag or failure can cause the paralysis of the whole system.
However, the operation scheduling, pump station maintenance, sewage discharge management, flood control command and the like of the domestic urban drainage system still stay in the manual stage at present, the system has low automation degree and poor strain capacity, and simultaneously, the emergency treatment capacity for icons or disaster weather conditions is lacked. Therefore, how to realize the comprehensive automation of urban drainage and improve the comprehensive operation efficiency of urban drainage becomes a problem to be solved urgently.
Disclosure of Invention
The invention aims to solve the problems of low comprehensive automation degree and comprehensive operation efficiency of urban drainage in the prior art, and provides a ponding emergency scheduling method based on ponding prediction, which can predict rainfall according to meteorological data and predict ponding distribution information according to the rainfall so as to schedule a drainage system, realize comprehensive automation of drainage and improve the comprehensive operation efficiency of drainage.
In order to achieve the purpose, the invention adopts the following technical scheme: a ponding emergency dispatching method based on ponding prediction comprises the following steps:
s1: according to rainfall forecast data, a rainfall prediction model is established;
s2: according to rainfall, a surface water prediction model is established;
s3: acquiring underground pipe network distribution information of a target area, and determining a drainage pump station of a ponding point;
s4: and scheduling the drainage pump station by combining the predicted distribution condition of the water accumulation points and the water accumulation depth.
The rainfall forecast data includes data relating to an average surface temperature, atmospheric precipitation, surface relative humidity, surface atmospheric pressure, cloud cover, near-surface east wind, and/or near-surface north wind equaling rainfall. And may also include data such as atmospheric circulation factors, radar echo maps, etc. According to the invention, the rainfall is predicted by utilizing meteorological data, the surface water is predicted in advance according to the predicted rainfall, and the pump station is scheduled in advance according to the predicted distribution condition of the surface water, so that the potential safety hazard caused by the fact that the surface water is accumulated during rainfall is avoided. The comprehensive automation of drainage is realized, the comprehensive operation efficiency of drainage is improved, and the electric power safety is guaranteed.
Preferably, the step S1 is further expressed as:
s1.1: acquiring rainfall forecast data of a target area at different time periods and actual rainfall corresponding to the rainfall forecast data, and establishing a rainfall database of the target area;
s1.2: establishing a neural network model, taking rainfall forecast data of each acquisition time period as input of the neural network model, and taking output of the neural network model as a rainfall forecast value of the rainfall forecast data;
s1.3: training a neural network model by using the actual rainfall of the rainfall forecast data to obtain an optimized neural network model;
s1.4: and collecting rainfall forecast data of the target area at the current time, and taking the rainfall forecast data of the current time as input of the optimized neural network model to obtain a rainfall prediction value of the target area in a future time period.
The rainfall prediction model is a neural network model, the neural network model is constructed by utilizing rainfall forecast data of historical time periods and actual rainfall, and reliability prediction of the future rainfall of the target area is achieved through the rainfall forecast data at the current moment. Namely, the rainfall forecast data at the current moment, and the rainfall in the future time period is obtained.
Preferably, the step S2 is further expressed as:
s2.1: acquiring building planning information of a target area, and dividing the target area into a plurality of areas according to the building planning information;
s2.2: collecting historical rainfall and ponding information corresponding to the rainfall in each area, and establishing a ponding database, wherein the rainfall in the ponding database corresponds to the ponding information corresponding to the rainfall in a one-to-one correspondence manner;
s2.3: and acquiring a rainfall prediction value predicted at the current moment in a future time period, inputting the rainfall prediction value into a ponding database for similarity matching, and acquiring the ponding information predicted at the current moment according to a matching result.
The ponding information comprises the distribution of ponding points and the ponding depth corresponding to the ponding points, the building planning information is used for more accurately determining the flood control level of the area, and whether power equipment (such as a transformer substation) exists or not, whether population gathers or not can be judged according to the building planning information, so that the area is divided, and the waterlogging prevention and allocation can be orderly carried out when the flood risk occurs.
Preferably, step S2.3 is further expressed as:
a1: if the similarity is smaller than a preset threshold value, successful matching is carried out, and ponding point distribution information corresponding to the rainfall is obtained and is the ponding information predicted at the current moment;
a2: if the similarity is larger than a preset threshold value, selecting a set number of historical rainfall and ponding point distribution information corresponding to the rainfall from large to small according to the similarity value, taking the historical rainfall as input and the corresponding ponding information as output, and training a ponding prediction model; and inputting the rainfall prediction value predicted at the current moment into the trained ponding prediction model to obtain the ponding information predicted at the current moment.
The ponding prediction model is a neural network model, and when ponding prediction is carried out, similarity calculation and the neural network model are combined based on historical rainfall and corresponding ponding information, so that the prediction result is more accurate. When the similarity meets a preset threshold, acquiring historical rainfall matched with the current predicted rainfall and ponding information corresponding to the historical rainfall, and taking the ponding information as predicted ponding information; when the similarity does not meet the set requirement, the accumulated water data is predicted by combining an accumulated water prediction model; the calculation process is simplified, and meanwhile the accuracy of the ponding information prediction is guaranteed.
Preferably, the step S2 is further expressed as:
s2.1: establishing a terrain model according to the geographic information of the target area;
s2.2: dividing the terrain model into a plurality of areas, and calculating the gradient condition of each area;
s2.3: and calculating the water accumulation point distribution of each area and the water accumulation depth of the corresponding water accumulation point.
The accumulated water condition of the area is related to the gradient of the area, the gradient is calculated by using the remote sensing image and the elevation image, and the result is more accurate.
Said step S2.2 further comprises:
s2.2.1: acquiring a remote sensing image of a target area, and preprocessing the remote sensing image to obtain a digital elevation image and a digital ortho-image;
s2.2.2: constructing a target area gradient model by using the digital elevation image and the digital orthographic image;
s2.2.3: and acquiring a remote sensing image of the area to be measured, and inputting the remote sensing image into the target area slope model to obtain the slope of the area to be measured.
The preprocessing can be point cloud dense matching, point cloud rasterization, DEM editing, image orthorectification processing and image mosaic processing.
Preferably, the step s2.2.2 further comprises:
b1: calculating a shape index value of a target area according to the digital orthophoto map;
b2: calculating according to the digital elevation model data by adopting a gradient calculation formula to obtain a gradient map, and performing spatial superposition on the gradient map and the target area to obtain earth surface gradient data of the target area;
b3: and performing regression analysis fitting based on a power function model according to the terrain gradient data of the target area, the shape index value of the target area and the earth surface gradient data of the target area to construct a target area gradient model. By establishing the gradient model of the target area, the gradient of the area to be measured can be quickly calculated.
Preferably, said step S2.3 is further represented by:
s2.3.1: calculating the runoff corresponding to the rainfall amount of the target area by utilizing the actual rainfall amount and the rainfall impairment;
s2.3.2: generalizing each catchment area into a nonlinear reservoir, and establishing a nonlinear reservoir model, wherein the model takes rainfall as input and earth surface confluence and infiltration as output;
s2.3.3: and obtaining the discharge at the time when the time step length ends, namely the surface water depth according to the nonlinear reservoir model.
Runoff production is the process of surface runoff generated by rainfall through the processes of plant interception, infiltration, evaporation and the like on the surface. The runoff yield value is obtained by subtracting the rainfall impairment from the actual rainfall. The rainfall convergence refers to a process that the produced flow generated by rainfall is converged to the drainage basin outlet to flow out; the surface confluence is a process of converging from the surface to a drainage basin outlet after the production flow in each catchment area. The calculation principle of the nonlinear reservoir model is as follows:
in the formula: v is the water accumulation amount of the catchment area, and V = A x d; d is the water depth; a is the area of the catchment area; i is net rain; q is the flow rate.
Wherein,
in the formula: w is the width of the cross flow of the catchment area; n is the rough coefficient of the earth surface Mannin; the surface stagnant water storage depth is adopted; and S is the width of the catchment area.
Preferably, the step S3 is further expressed as:
s3.1: acquiring space coordinate information of the ponding point;
s3.2: calculating a drainage area corresponding to each pump station according to the distribution information of the underground pipe network of the target area;
s3.3: and comparing the space coordinates of the ponding points with the drainage areas corresponding to the pump stations, and judging the drainage pump stations of the ponding points.
Selecting a pump station according to the distribution information of underground pipe networks in a target area, traversing by taking the pump station as a starting point, and obtaining drainage facilities (a rainwater grate, an inspection well and the like) corresponding to the pump station; and calculating an external polygon of a dot matrix formed by the pump station and the drainage facility, and buffering the external polygon according to the set distance to obtain the drainage area of the selected pump station.
Preferably, the step S4 is further expressed as:
s4.1: dividing the target area into a plurality of areas according to the gradient, setting a ponding threshold value of each area, and judging whether the predicted ponding point ponding water depth exceeds the water depth threshold value of the area where the ponding point is located;
s4.2: and if the water depth exceeds the water depth threshold value, giving an alarm, starting a drainage pump station corresponding to the water accumulation point, and closing the pump station after rainfall is finished.
And the pump station is opened according to the accumulated water information, so that the cost is saved. Meanwhile, facilities (such as power equipment) needing important attention can be marked on the map, the water accumulation condition of the area where the facilities are located is determined, and if the depth of the water accumulation exceeds a threshold value, the area is subjected to pre-control treatment by workers in advance.
Therefore, the invention has the following beneficial effects: 1. according to the invention, the rainfall is predicted by utilizing meteorological data, the surface water is predicted in advance according to the predicted rainfall, and the pump station is scheduled in advance according to the predicted distribution condition of the surface water, so that the potential safety hazard caused by the fact that the surface water is accumulated during rainfall is avoided. The comprehensive automation of drainage is realized, and the comprehensive operation efficiency of drainage is improved; 2. the method and the device have the advantages that by combining with the terrain trend of the target area, the timeliness and the accuracy of accumulated water monitoring and early warning are enhanced, corresponding pre-control processing is favorably carried out on the power equipment which is likely to break down due to heavy rainfall, the probability of hidden danger occurrence is reduced, and the power safety is guaranteed.
Drawings
FIG. 1 is a flow chart of the operation of the method of the present invention.
FIG. 2 is a flow chart of one step of the present invention for modeling surface water predictions.
FIG. 3 is a flow chart of another step in the present invention for modeling surface water predictions.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
the first embodiment is as follows:
in the embodiment shown in fig. 1, a method for emergency dispatching of accumulated water based on accumulated water prediction can be seen, and the operation flow is as follows: step one, establishing a rainfall prediction model according to meteorological data; step two, establishing a surface water prediction model according to rainfall; step three, acquiring underground pipe network distribution information of a target area, and determining a drainage pump station of a water accumulation point; and step four, scheduling the drainage pump station by combining the distribution condition of the water accumulation points and the water accumulation depth. According to the invention, the rainfall is predicted by utilizing meteorological data, the surface water is predicted in advance according to the predicted rainfall, and the pump station is scheduled in advance according to the predicted distribution condition of the surface water, so that the potential safety hazard caused by the fact that the surface water is accumulated during rainfall is avoided. The comprehensive automation of drainage is realized, the comprehensive operation efficiency of drainage is improved, and the electric power safety is guaranteed.
The technical solution of the present application is further described below by specific examples.
The first step is as follows: and establishing a rainfall prediction model according to the meteorological data.
Acquiring rainfall forecast data of a target area at different time periods and actual rainfall corresponding to the rainfall forecast data, and establishing a rainfall database of the target area; establishing a neural network model, taking rainfall forecast data of each acquisition time period as input of the neural network model, and taking output of the neural network model as a rainfall forecast value of the rainfall forecast data; training a neural network model by using the actual rainfall of the rainfall forecast data to obtain an optimized neural network model; and collecting rainfall forecast data of the target area at the current time, and taking the rainfall forecast data of the current time as input of the optimized neural network model to obtain a rainfall prediction value of the target area in a future time period.
And constructing a rainfall prediction model according to the rainfall forecast data in the past time and the actual rainfall corresponding to the rainfall forecast data, so as to realize the reliability prediction in the aspect of future rainfall of the target area.
Meanwhile, in the actual rainfall process, rainfall data are collected and compared with the predicted rainfall data, and whether the difference value between the rainfall prediction value and the actual rainfall is too large is judged, so that whether the rainfall estimation model needs to be optimized again can be judged, and the obtained rainfall prediction value is more accurate.
The second step is that: and establishing a surface water prediction model according to the rainfall.
Acquiring building planning information of a target area, and dividing the target area into a plurality of areas according to the building planning information; collecting historical rainfall and ponding information corresponding to the rainfall in each area, and establishing a ponding database, wherein the rainfall in the ponding database corresponds to the ponding information corresponding to the rainfall in a one-to-one correspondence manner; obtaining a rainfall prediction value predicted at the current moment in a future time period, and inputting the rainfall prediction value into a ponding database for similarity matching: if the similarity is smaller than a preset threshold value, successful matching is carried out, and water accumulation point distribution information corresponding to the rainfall is obtained and is water accumulation information predicted at the current moment; if the similarity is larger than a preset threshold value, selecting a set number of historical rainfall and ponding point distribution information corresponding to the rainfall from large to small according to the similarity, and training a ponding prediction model by taking the historical rainfall as input and the corresponding ponding information as output; and inputting the rainfall prediction value predicted at the current moment into the trained ponding prediction model to obtain the ponding information predicted at the current moment.
The ponding information comprises ponding point distribution and ponding depth corresponding to the ponding points, the building planning information is used for more accurately determining flood prevention levels of the areas, and whether power equipment (such as a transformer substation) and population are gathered or not can be judged according to the building planning information, so that the areas are divided, and waterlogging prevention and allocation can be performed orderly when flood risks occur.
The ponding prediction model is a neural network model, and when ponding prediction is carried out, similarity calculation and the neural network model are combined on the basis of historical rainfall and corresponding ponding information, so that the prediction result is more accurate. When the similarity meets a preset threshold, acquiring historical rainfall matched with the current predicted rainfall and ponding information corresponding to the historical rainfall, and taking the ponding information as predicted ponding information; when the similarity does not meet the set requirement, the accumulated water data is predicted by combining an accumulated water prediction model; the calculation process is simplified, and meanwhile the accuracy of the ponding information prediction is guaranteed.
The third step: and acquiring the distribution information of the underground pipe network in the target area, and determining a drainage pump station of the accumulated water point.
Acquiring space coordinate information of the ponding point; calculating a drainage area corresponding to each pump station according to the distribution information of the underground pipe network of the target area; and comparing the space coordinates of the ponding points with the drainage areas corresponding to the pump stations, and judging the drainage pump stations of the ponding points.
Specifically, the method comprises the following steps:
selecting a pump station according to the distribution information of underground pipe networks in a target area, traversing by taking the pump station as a starting point, and obtaining drainage facilities (a rainwater grate, an inspection well and the like) corresponding to the pump station; and calculating an external polygon of a dot matrix formed by the pump station and the drainage facility, and buffering the external polygon according to the set distance to obtain the drainage area of the selected pump station.
The fourth step: and scheduling the drainage pump station by combining the predicted distribution condition of the water accumulation points and the water accumulation depth.
Dividing the target area into a plurality of areas according to the gradient, setting a ponding threshold value of each area, and judging whether the predicted ponding point ponding water depth exceeds the water depth threshold value of the area where the ponding point is located; and if the water depth exceeds the water depth threshold value, giving an alarm, starting a drainage pump station corresponding to the water accumulation point, and closing the pump station after the rainfall is finished.
In this embodiment, a facility (such as an electric power device) that needs to pay attention to in a focused manner may also be labeled on a constructed topographic map, a water accumulation condition of a region where the facility is located is determined, and if a water accumulation depth exceeds a threshold, a worker may perform pre-control processing on the region in advance.
Taking a transformer substation as an example, the ponding condition of the transformer substation can be determined, whether the ponding depth exceeds the preset ponding threshold value of the transformer substation is judged, and if the ponding depth exceeds the preset ponding threshold value, the staff is arranged in advance to wait for the purpose that the transformer substation can be subjected to fault rush repair at any time in the rainfall process. The rapidly implemented disaster reduction and relief emergency actions aim at rapidly recovering equipment faults and minimizing comprehensive power failure loss, and the importance difference of different equipment in power grid dispatching is fully considered to optimize an emergency repair strategy.
The second embodiment:
the embodiment provides another scheme for building a surface water prediction model according to rainfall on the basis of the first embodiment:
1. and establishing a terrain model according to the geographic information of the target area.
2. The ponding is related to the gradient, and the terrain model is divided into a plurality of areas, and the gradient condition of each area is calculated.
Acquiring a remote sensing image of a target area, and preprocessing the remote sensing image (wherein the preprocessing can be point cloud dense matching, point cloud rasterization, DEM editing, image orthorectification processing and image mosaic processing) to obtain a digital elevation image and a digital orthoimage; calculating a shape index value of a target area according to the digital orthophoto map; calculating according to the digital elevation model data by adopting a gradient calculation formula to obtain a gradient map, and performing spatial superposition on the gradient map and the target area to obtain earth surface gradient data of the target area; performing regression analysis fitting based on a power function model according to the terrain gradient data of the target area, the shape index value of the target area and the earth surface gradient data of the target area to construct a target area gradient model; and acquiring a remote sensing image of the area to be measured, and inputting a target area gradient model to obtain the gradient of the area to be measured. By establishing a target area gradient model, the gradient of the area to be measured can be rapidly calculated.
3. And calculating the water accumulation point distribution of each area and the water accumulation depth of the corresponding water accumulation point.
1. And calculating the runoff corresponding to the rainfall of the target area by utilizing the actual rainfall and the rainfall impairment.
Runoff production is the process of surface runoff generated by rainfall through the processes of plant interception, infiltration, evaporation and the like on the surface. The production flow value is obtained by subtracting rainfall impairment from actual rainfall, namely:
W abortion ＝Q General assembly -q Infiltration of water -q Evaporation with evaporation ，
In the formula: the parameters are respectively the rainwater surface runoff, the total precipitation, the rainfall amount and the rainwater evaporation amount.
The soil infiltration impairment formula is as follows:
q infiltration of water ＝I t *Δt*S
I t ＝f 0 +(f 1 -f 0 )e -α ，
In the formula: I.C. A t Average infiltration rate over Δ t (time interval) time; s is the area of a permeable area; f. of 0 The final infiltration rate is obtained; f. of 1 The initial infiltration rate; alpha is the rate of infiltration decrease.
2. And calculating rainfall surface convergence by using a nonlinear reservoir model to obtain the depth of the surface accumulated water.
The rainfall confluence refers to a process that the produced flows generated by rainfall are converged to a drainage basin outlet to flow out. The surface confluence is a process of converging the produced flow in each catchment area from the surface to a drainage basin outlet.
In the embodiment, each catchment area is generalized into a nonlinear reservoir, and a nonlinear reservoir model is established, wherein the model takes rainfall as input and surface confluence and infiltration as output; and obtaining the discharge at the time when the time step length ends, namely the surface water depth according to the nonlinear reservoir model.
The calculation principle of the nonlinear reservoir model is as follows:
in the formula: v is the water accumulation amount of the catchment area, and V = A x d; d is the water depth; a is the area of the catchment area; i is net rain; q is the flow rate.
Wherein:
in the formula: w is the width of the cross flow of the catchment area; n is the rough coefficient of the earth surface Mannin; the surface stagnant water storage depth is adopted; and S is the width of the catchment area. And finally, the outflow rate at the time of the time step length end, namely the surface water depth, can be obtained.
And (3) the convergence of the rainfall pipe network can be calculated to obtain the depth of underground accumulated water: the pipe network confluence is jointly determined by the drainage capacity and the drainage duration of the pipe network:
in the formula: n is the roughness of the pipe wall; d is the pipe diameter; s is the gradient of the bottom of the pipe; Δ t is the drain duration.
This embodiment still includes: judging whether the water accumulation rate exceeds the pump station drainage rate, if so, indicating that the pump station cannot discharge accumulated water in time, having the risk of waterlogging, needing to make a waterlogging prevention emergency rescue scheme in time, and if the crowd gathered region, needing to evacuate the crowd in advance.
This embodiment further includes, in the fourth step: in the actual rainfall process, judging whether the operation parameters of the pump station are normal and whether the drainage flow of the pump station at the current moment is normal; if the operation parameters are normal and the water discharge amount is abnormal, the blockage of the water discharge pipeline of the water discharge system or the leakage and the breakage of the water discharge pipeline are indicated; if the drainage flow and the operation parameters are abnormal, the pump station is indicated to be in failure.
And determining whether the drainage system is normal or not so as to take a countermeasure in time when the drainage system fails, ensure the normal operation of drainage, prevent water accumulation and reduce accidents.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (10)
1. A ponding emergency dispatching method based on ponding prediction is characterized by comprising the following steps:
s1: according to rainfall forecast data, a rainfall prediction model is established;
s2: according to the rainfall, establishing a surface water prediction model;
s3: acquiring underground pipe network distribution information of a target area, and determining a drainage pump station of a ponding point;
s4: and scheduling the drainage pump station by combining the predicted distribution condition of the water accumulation points and the water accumulation depth.
2. The ponding emergency dispatching method based on ponding prediction according to claim 1, characterized in that the step S1 is further represented as:
s1.1: acquiring rainfall forecast data of a target area at different time periods and actual rainfall corresponding to the rainfall forecast data, and establishing a rainfall database of the target area;
s1.2: establishing a neural network model, taking rainfall forecast data of each acquisition time period as input of the neural network model, and taking output of the neural network model as a rainfall forecast value of the rainfall forecast data;
s1.3: training a neural network model by using the actual rainfall of the rainfall forecast data to obtain an optimized neural network model;
s1.4: and collecting rainfall forecast data of the target area at the current time, and taking the rainfall forecast data of the current time as input of the optimized neural network model to obtain a rainfall prediction value of the target area in a future time period.
3. The ponding emergency dispatching method based on ponding prediction according to claim 1, characterized in that the step S2 is further represented as:
s2.1: acquiring building planning information of a target area, and dividing the target area into a plurality of areas according to the building planning information;
s2.2: collecting historical rainfall and ponding information corresponding to the rainfall in each area, and establishing a ponding database, wherein the rainfall in the ponding database corresponds to the ponding information corresponding to the rainfall in a one-to-one correspondence manner;
s2.3: and acquiring a rainfall prediction value predicted at the current time in a future time period, inputting the rainfall prediction value into a ponding database for similarity matching, and acquiring the ponding information predicted at the current time according to a matching result.
4. A method for emergency dispatch of accumulated water based on accumulated water forecast as claimed in claim 3, wherein said step S2.3 is further represented by:
a1: if the similarity is smaller than a preset threshold value, successful matching is carried out, and ponding point distribution information corresponding to the rainfall is obtained and is the ponding information predicted at the current moment;
a2: if the similarity is larger than a preset threshold value, selecting a set number of historical rainfall and ponding point distribution information corresponding to the rainfall from large to small according to the similarity value, taking the historical rainfall as input and the corresponding ponding information as output, and training a ponding prediction model; and inputting the rainfall prediction value predicted at the current moment into the trained ponding prediction model to obtain the ponding information predicted at the current moment.
5. The ponding emergency dispatching method based on ponding prediction according to claim 1, characterized in that the step S2 is further represented as:
s2.1: establishing a terrain model according to the geographic information of the target area;
s2.2: dividing the terrain model into a plurality of areas, and calculating the gradient condition of each area;
s2.3: and calculating the water accumulation point distribution of each area and the water accumulation depth of the corresponding water accumulation point.
6. The ponding emergency dispatching method based on ponding prediction according to claim 5, characterized in that the step S2.2 further comprises:
s2.2.1: acquiring a remote sensing image of a target area, and preprocessing the remote sensing image to obtain a digital elevation image and a digital orthographic image;
s2.2.2: constructing a target area gradient model by using the digital elevation image and the digital orthographic image;
s2.2.3: and acquiring a remote sensing image of the area to be measured, and inputting a target area gradient model to obtain the gradient of the area to be measured.
7. The ponding emergency dispatching method based on ponding prediction according to claim 6, characterized in that the step S2.2.2 further comprises:
b1: calculating a shape index value of a target area according to the digital orthophoto map;
b2: calculating by adopting a gradient calculation formula according to the digital elevation model data to obtain a gradient map, and performing spatial superposition on the gradient map and the target area to obtain earth surface gradient data of the target area;
b3: and performing regression analysis fitting based on a power function model according to the terrain gradient data of the target area, the shape index value of the target area and the earth surface gradient data of the target area to construct a target area gradient model.
8. A method for emergency dispatch of stagnant water based on its prediction as claimed in claim 5 or 6 or 7, wherein said step S2.3 is further expressed as:
s2.3.1: calculating the runoff yield corresponding to the rainfall amount of the target area by utilizing the actual rainfall amount and the rainfall loss;
s2.3.2: generalizing each catchment area into a nonlinear reservoir, and establishing a nonlinear reservoir model, wherein the model takes rainfall as input and takes surface confluence and infiltration as output;
s2.3.3: and obtaining the outflow at the time of finishing the time step according to the nonlinear reservoir model, namely the surface water depth.
9. The ponding emergency dispatching method based on ponding prediction according to claim 1, characterized in that the step S3 is further represented as:
s3.1: acquiring space coordinate information of the ponding point;
s3.2: calculating a drainage area corresponding to each pump station according to the distribution information of the underground pipe network of the target area;
s3.3: and comparing the space coordinates of the ponding points with the drainage areas corresponding to the pump stations, and judging the drainage pump stations of the ponding points.
10. A method for emergency dispatch of accumulated water based on accumulated water forecast according to claim 1, 2 or 9, characterized in that said step S4 is further represented by:
s4.1: dividing the target area into a plurality of areas according to the gradient, setting a ponding threshold value of each area, and judging whether the predicted ponding point ponding water depth exceeds the water depth threshold value of the area where the ponding point is located;
s4.2: and if the water depth exceeds the water depth threshold value, giving an alarm, starting a drainage pump station corresponding to the water accumulation point, and closing the pump station after the rainfall is finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211241381.3A CN115689168A (en) | 2022-10-11 | 2022-10-11 | Accumulated water emergency scheduling method based on accumulated water prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211241381.3A CN115689168A (en) | 2022-10-11 | 2022-10-11 | Accumulated water emergency scheduling method based on accumulated water prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115689168A true CN115689168A (en) | 2023-02-03 |
Family
ID=85064580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211241381.3A Pending CN115689168A (en) | 2022-10-11 | 2022-10-11 | Accumulated water emergency scheduling method based on accumulated water prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115689168A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116628998A (en) * | 2023-05-30 | 2023-08-22 | 中国铁路广州局集团有限公司广州工程建设指挥部 | Rainfall catchment calculation method suitable for mountain areas |
| CN116858277A (en) * | 2023-07-13 | 2023-10-10 | 遂宁市玖云通科技有限公司 | Computer data processing system based on big data analysis |
| CN117035234A (en) * | 2023-08-10 | 2023-11-10 | 南京新高智联信息技术有限公司 | Regional ponding depth monitoring method based on rainfall forecast |
| CN117727187A (en) * | 2023-12-14 | 2024-03-19 | 广州巨隆科技有限公司 | Big data analysis processing method and system based on terminal |
| CN117911750A (en) * | 2023-12-24 | 2024-04-19 | 振宁(无锡)智能科技有限公司 | Edge intelligent data processing method and edge server |
| CN118333355A (en) * | 2024-06-14 | 2024-07-12 | 江西省交通科学研究院有限公司 | Expressway tide-based sewage emergency treatment method and control system |
-
2022
- 2022-10-11 CN CN202211241381.3A patent/CN115689168A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116628998A (en) * | 2023-05-30 | 2023-08-22 | 中国铁路广州局集团有限公司广州工程建设指挥部 | Rainfall catchment calculation method suitable for mountain areas |
| CN116628998B (en) * | 2023-05-30 | 2023-12-29 | 中国铁路广州局集团有限公司广州工程建设指挥部 | Rainfall catchment calculation method suitable for mountain areas |
| CN116858277A (en) * | 2023-07-13 | 2023-10-10 | 遂宁市玖云通科技有限公司 | Computer data processing system based on big data analysis |
| CN117035234A (en) * | 2023-08-10 | 2023-11-10 | 南京新高智联信息技术有限公司 | Regional ponding depth monitoring method based on rainfall forecast |
| CN117035234B (en) * | 2023-08-10 | 2024-05-14 | 南京新高智联信息技术有限公司 | Regional ponding depth monitoring method based on rainfall forecast |
| CN117727187A (en) * | 2023-12-14 | 2024-03-19 | 广州巨隆科技有限公司 | Big data analysis processing method and system based on terminal |
| CN117911750A (en) * | 2023-12-24 | 2024-04-19 | 振宁(无锡)智能科技有限公司 | Edge intelligent data processing method and edge server |
| CN118333355A (en) * | 2024-06-14 | 2024-07-12 | 江西省交通科学研究院有限公司 | Expressway tide-based sewage emergency treatment method and control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115689168A (en) | Accumulated water emergency scheduling method based on accumulated water prediction | |
| CN107169645B (en) | Power transmission line fault probability online evaluation method considering influence of rainstorm disaster | |
| CN105005827B (en) | A kind of emergency response method for early warning based on electric power accident | |
| CN109544865B (en) | Early warning method and early warning system for waterlogging of transformer substation | |
| CN110633865A (en) | Urban ponding prediction and safety early warning system based on drainage model | |
| CN104951993A (en) | Comprehensive monitoring and early warning system based on meteorology and power grid GIS and method thereof | |
| CN105046445A (en) | Flood prevention dispatching decision support system | |
| CN112506994B (en) | Power equipment flood hidden danger point monitoring and early warning method and related device | |
| CN107657336B (en) | Power transmission and distribution equipment typhoon early warning system based on microclimate and microtopography | |
| CN110274656B (en) | Urban inland river water level forecasting and early warning method | |
| CN115186858A (en) | Transformer substation flood inundation risk early warning method and system based on different influence types | |
| CN115879363A (en) | Accumulated water prediction method based on rainfall | |
| CN114611756A (en) | Urban combined drainage system water quantity load prediction method based on remote sensing technology | |
| CN111738617A (en) | Transformer substation risk assessment method and early warning system in heavy rainfall weather | |
| CN209417901U (en) | Mountain flood dynamic early-warning system based on soil moisture content real time correction | |
| CN110570628A (en) | Power transmission line pole tower geological disaster monitoring, early warning and analyzing system and using method | |
| KR102143039B1 (en) | Remote monitoring and control apparatus for the type of multi-path | |
| CN116402291B (en) | Method and system for overall scheduling of sewage in river basin of river | |
| CN117150600B (en) | Roof water storage and drainage control method for urban waterlogging prevention | |
| CN212007314U (en) | Hydrological robot | |
| CN110542936B (en) | Method and system for forecasting power grid rainstorm disaster forecast deviation based on dominant circulation | |
| CN113609752B (en) | Southwest vortex-oriented distribution transformer loss evaluation system and southwest vortex-oriented distribution transformer loss evaluation method | |
| CN204462788U (en) | A kind of sewerage system | |
| Araujo et al. | Hydrological and meteorological forecast combined systems for flood alerts and reservoir management: the Iguaçu river basin case | |
| CN115640884B (en) | Power grid load scheduling method based on rainfall |
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 |