Urban inland inundation risk early warning system and method

Abstract

The invention discloses an urban inland inundation risk early warning system and method, relates to the technical field of urban inland inundation risk early warning, and solves the problems that in the prior art, a large amount of silt and sundries are often contained in accumulated water, the effective sectional area of a pipeline is reduced due to silt accumulation, the water flow speed is reduced, and the drainage capacity of an accumulated water area is reduced; waterlogging is intensified, and pipeline abrasion is intensified. The waterlogging data of the target area are collected in real time, the drainage evaluation coefficient is calculated based on the waterlogging data, and whether waterlogging early warning is carried out or not is judged through the drainage evaluation coefficient and the preset drainage threshold value; training an artificial intelligence model through the historical ponding data to obtain a waterlogging prediction model; and on the basis of the waterlogging prediction model, predicting the waterlogging data of the target area to obtain a prediction result, and the prediction result is compared with the preset threshold value and the preset drainage threshold value, whether waterlogging early warning is carried out or not is judged, and the technical problem is solved.

Description

Technical Field

[0001] The present invention belongs to the field of urban waterlogging risk warning, and in particular to an urban waterlogging risk warning system and method. Background Art

[0002] With the acceleration of urbanization, urban drainage systems are facing increasingly severe challenges. Under extreme weather conditions such as heavy rains, urban waterlogging problems frequently occur, posing a great threat to urban safety and residents' lives.

[0003] The prior art (the invention application with the publication number CN117133098A) proposes an urban waterlogging monitoring and early warning system, which involves the field of urban waterlogging early warning technology, including a water measuring facility terminal device: used to collect the location information and waterlogging information of urban waterlogging points in real time; a waterlogging safety monitoring terminal device: used to monitor the waterlogging information of urban waterlogging points in real time; a waterlogging supervision platform, a waterlogging safety early warning device and a waterlogging safety monitoring terminal device are connected in communication, and used to upload the waterlogging information of waterlogging points or waterlogging points to the waterlogging supervision platform; and an alarm is issued after receiving the instruction of the waterlogging supervision platform; the invention application realizes the real-time monitoring of waterlogging data of each node through the waterlogging supervision platform, supports remote control, and the waterlogging safety early warning device issues an alarm after receiving the instruction of the waterlogging supervision platform, so as to achieve the effect of automatic alarm. However, the prior art does not take into account that the accumulated water often contains a large amount of silt and debris. The accumulation of silt will not only reduce the effective cross-sectional area of ​​the pipeline, reduce the flow rate of water, and lead to a decrease in the drainage capacity of the waterlogging area, causing the waterlogging to intensify, but also lead to aggravated wear of the pipeline and shorten its service life.

[0004] Therefore, the present invention proposes an urban waterlogging risk early warning system and method to solve the above problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an urban waterlogging risk warning system and method, which are used to solve the technical problem that the prior art does not take into account that accumulated water often contains a large amount of silt and debris, and the accumulation of silt will not only reduce the effective cross-sectional area of ​​the pipeline, reduce the flow rate of water, and lead to a decrease in the drainage capacity of the accumulated water area, causing the waterlogging to worsen, but also lead to increased wear of the pipeline and shorten its service life.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides an urban waterlogging risk warning system, comprising: a data collection module, a data analysis module, a waterlogging prediction module and a waterlogging warning module;

[0007] Data acquisition module: used to obtain water accumulation data in the target area;

[0008] Data analysis module: determines whether to issue a waterlogging warning based on waterlogging data and preset thresholds; if yes, sends warning information to the waterlogging warning module; if no, continues monitoring and judgment; and,

[0009] The drainage assessment coefficient is calculated based on the water accumulation data;

[0010] Waterlogging prediction module: train the artificial intelligence model based on historical waterlogging data to obtain the waterlogging prediction model; predict the waterlogging data of the target area based on the waterlogging prediction model to obtain the prediction result;

[0011] Waterlogging warning module: Determine whether to issue a waterlogging warning based on the prediction results, drainage assessment coefficient and preset drainage threshold; if yes, send warning information; if no, continue monitoring and judgment; and,

[0012] Based on the warning information, an alarm is issued through the early warning device.

[0013] Preferably, the data acquisition module communicates and / or is electrically connected to the data analysis module and the waterlogging prediction module respectively; the waterlogging warning module communicates and / or is electrically connected to the data analysis module and the waterlogging prediction module respectively.

[0014] Preferably, the step of obtaining water accumulation data of the target area includes:

[0015] The water accumulation data of the target area is collected in real time through data acquisition equipment; the water accumulation data includes: rainfall, water level, drainage flow rate, drainage volume and sediment concentration in the water accumulation.

[0016] It should be noted that the target area refers to the flood-prone area in the city, including low-lying areas, flood-prone streets and tunnels, etc.

[0017] Preferably, the determining whether to issue a waterlogging warning based on the waterlogging data and a preset threshold value includes:

[0018] Determine whether the rainfall in the preset time period is greater than the drainage volume; if yes, generate warning information; if no, continue monitoring and judgment; the preset time period is set according to the time period that needs to be monitored for actual urban waterlogging;

[0019] Determine whether the accumulated water level is greater than the preset water level threshold; if yes, generate an early warning message; if no, continue to monitor and judge; the preset water level threshold is set according to the actual urban waterlogging safety standards.

[0020] Preferably, the drainage assessment coefficient is calculated based on the water accumulation data, including:

[0021] The drainage velocity is marked as V, the drainage volume is marked as N, and the sediment concentration in the accumulated water is marked as C;

[0022] The drainage assessment coefficient is calculated through the waterlogging assessment formula: P = X / ln(V+1)+Y / e^(N+1)+Z×(e^C) / ln(C+1); where P is the drainage assessment coefficient, X, Y, and Z are proportional coefficients, and ln(*) is a logarithmic function with the natural number e as the base.

[0023] The present invention collects water accumulation data of the target area in real time, calculates the drainage assessment coefficient based on the water accumulation data, and determines whether to issue a waterlogging warning through the drainage assessment coefficient and a preset drainage threshold. This is beneficial to real-time monitoring of drainage conditions in flood-prone areas and preventing the accumulation of silt and debris.

[0024] Preferably, the artificial intelligence model is trained based on historical waterlogging data to obtain a waterlogging prediction model, including:

[0025] S1: Obtain the corresponding relationship between waterlogging data by analyzing historical waterlogging data and urban hydrological data; wherein the corresponding relationship between waterlogging data includes: the corresponding relationship between rainfall and waterlogging level, the corresponding relationship between drainage volume and waterlogging level, the corresponding relationship between drainage velocity and drainage volume, and the corresponding relationship between sediment concentration in waterlogging and drainage velocity;

[0026] S2: Obtain the rainfall at the historical prediction time from the historical water accumulation data;

[0027] S3: based on the correspondence between the rainfall at the time of historical prediction and the waterlogging data, the waterlogging data at the time of prediction is obtained; wherein the waterlogging data at the time of prediction includes: the water level at the time of prediction, the drainage velocity at the time of prediction, the drainage volume at the time of prediction, and the sediment concentration in the waterlogging at the time of prediction;

[0028] S4: Integrate historical waterlogging data and rainfall at the time of historical prediction as standard input data; integrate waterlogging data at the time of prediction as standard output data;

[0029] S5: Train an artificial intelligence model based on standard input data and standard output data to obtain a waterlogging prediction model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0030] It should be noted that the historical waterlogging data refers to the historical data of waterlogging data collected in the target area; the prediction time refers to the time point that needs to be predicted, and the time setting for predicting urban waterlogging is based on the time;

[0031] Urban hydrological data refers to various data related to the urban hydrological cycle and urban drainage system. These data are used to describe the movement, distribution and changes of water in the city.

[0032] The rainfall at the historical forecast time refers to the rainfall at the forecast time in the historical waterlogging data;

[0033] The historical waterlogging data refers to the historical data of waterlogging data collected in the target area; the prediction time refers to the time point that needs to be predicted, which is set according to the time that needs to be predicted according to the actual urban waterlogging;

[0034] Historical waterlogging data include a variety of variables (such as rainfall, water level, drainage volume, drainage velocity, sediment concentration, etc.). By analyzing the relationship between these variables, a more systematic waterlogging prediction model can be constructed to improve the accuracy of the prediction. For example, there is a certain relationship between drainage velocity and drainage volume. An increase in drainage velocity usually means an increase in drainage volume; the relationship between sediment concentration and drainage velocity reflects the ability of water flow to carry substances.

[0035] Preferably, the method of obtaining waterlogging data at the prediction time based on the correspondence between rainfall and water accumulation data at the historical prediction time includes:

[0036] S1: Obtain the accumulated water level at the predicted time based on the rainfall at the historical predicted time and the corresponding relationship between the rainfall and the accumulated water level;

[0037] S2: obtaining the discharge volume at the prediction time based on the corresponding relationship between the accumulated water level at the prediction time and the discharge volume and the accumulated water level;

[0038] S3: obtaining the drainage flow rate at the prediction time based on the drainage volume at the prediction time and the corresponding relationship between the drainage flow rate and the drainage volume;

[0039] S4: Obtaining the sediment concentration in the accumulated water at the prediction time based on the drainage flow rate at the prediction time and the corresponding relationship between the sediment concentration in the accumulated water and the drainage flow rate.

[0040] Preferably, the predicting of waterlogging data of the target area based on the waterlogging prediction model to obtain the prediction result includes:

[0041] Obtain the rainfall at the predicted time through the weather forecast platform;

[0042] The real-time waterlogging data of the target area and the rainfall at the prediction time are input into the waterlogging prediction model to obtain the prediction result; wherein the prediction result refers to the waterlogging data at the prediction time corresponding to the real-time waterlogging data of the target area.

[0043] The present invention trains an artificial intelligence model through historical waterlogging data to obtain a waterlogging prediction model; and, based on the waterlogging prediction model, predicts the waterlogging data of the target area to obtain a prediction result; and determines whether to issue a waterlogging warning by comparing the prediction result with a preset threshold and a preset drainage threshold, which is beneficial for urban management personnel to know the development trend of urban waterlogging in advance and take measures at the first time.

[0044] Preferably, the determining whether to issue a waterlogging warning based on the prediction result, the drainage assessment coefficient and the preset drainage threshold value includes:

[0045] Determine whether the rainfall at the predicted time within the preset time period is greater than the drainage at the predicted time; if yes, generate warning information; if no, continue monitoring and judgment;

[0046] Determine whether the accumulated water level at the predicted time is greater than the preset water level threshold; if yes, generate warning information; if no, continue monitoring and judgment;

[0047] Determine whether the drainage assessment coefficient is greater than the preset drainage threshold; if yes, generate early warning information; if no, continue monitoring and judgment;

[0048] Determine whether the predicted drainage assessment coefficient is greater than the preset drainage threshold; if yes, produce early warning information; if not, continue to monitor and judge; among which, the preset drainage threshold is set according to the drainage capacity of the actual flood-prone area.

[0049] Preferably, the predicted drainage assessment coefficient includes:

[0050] The predicted drainage assessment coefficient is calculated based on the predicted results;

[0051] The drainage velocity at the prediction time is marked as V1, the drainage volume at the prediction time is marked as N1, and the sediment concentration in the accumulated water at the prediction time is marked as C1;

[0052] The predicted drainage assessment coefficient is calculated through the waterlogging assessment calculation formula: P1=X / ln(V1+1)+Y / e^(N1+1)+Z×(e^C1) / ln(C1+1); where P1 is the predicted drainage assessment coefficient.

[0053] Preferably, the step of providing an alarm prompt through an early warning device based on the early warning information includes:

[0054] The warning information is sent to the client of the urban waterlogging management personnel through wireless transmission technology; the wireless transmission technology includes: 4G / 5G or WIFI; the client includes: mobile phone or computer;

[0055] Based on the warning information, the warning equipment is used to alert people passing by; the warning equipment includes: warning lights, language announcers and LED display screens.

[0056] A second aspect of the present invention provides an urban waterlogging risk early warning method, comprising:

[0057] Step 1: Obtain water accumulation data in the target area in real time;

[0058] Step 2: Determine whether to issue a waterlogging warning based on the waterlogging data and the preset threshold; if yes, send the warning information to the waterlogging warning module; if no, continue monitoring and judging;

[0059] Step 3: Calculate the drainage assessment coefficient based on the water accumulation data;

[0060] Step 4: training an artificial intelligence model based on historical waterlogging data to obtain a waterlogging prediction model; and predicting waterlogging data in a target area based on the waterlogging prediction model to obtain a prediction result;

[0061] Step 5: Determine whether to issue a waterlogging warning based on the prediction results, drainage assessment coefficient and preset drainage threshold; if yes, send a warning message; if not, continue monitoring and judging; and, issue an alarm through the warning device based on the warning message.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] 1. The prior art does not take into account that stagnant water often contains a large amount of silt and debris. The accumulation of silt will not only reduce the effective cross-sectional area of ​​the pipeline, reduce the flow rate of water, and lead to a decrease in the drainage capacity of the stagnant water area, causing aggravated waterlogging, but also lead to increased wear of the pipeline and shorten its service life. The present invention collects the waterlogging data of the target area in real time, calculates the drainage assessment coefficient based on the waterlogging data, and determines whether to issue a waterlogging warning based on the drainage assessment coefficient and the preset drainage threshold. This is conducive to real-time monitoring of the drainage situation in the flood-prone area and preventing the accumulation of silt and debris. It solves the problem of the prior art that the accumulation of silt and debris leads to a decrease in the drainage capacity of the stagnant water area, aggravates waterlogging, and aggravates pipe wear, shortening its service life.

[0064] 2. The present invention trains an artificial intelligence model through historical waterlogging data to obtain a waterlogging prediction model; and, based on the waterlogging prediction model, predicts the waterlogging data of the target area to obtain a prediction result; by comparing the prediction result with a preset threshold and a preset drainage threshold, it is determined whether to issue a waterlogging warning, which is beneficial for urban management personnel to know the development trend of urban waterlogging in advance, so as to take measures at the first time, and solves the problem that the prior art does not predict the drainage status of future flood-prone areas and cannot know in advance whether the drainage function is normal, thereby causing the losses caused by waterlogging to increase. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 A schematic diagram of a system module according to an embodiment of the present invention;

[0067] Figure 2 A schematic diagram of a specific process of an embodiment of the present invention;

[0068] Figure 3 Schematic diagram of the method steps of an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] See also Figure 1-Figure 2 , the first aspect of the present invention provides an urban waterlogging risk warning system, including: a data collection module, a data analysis module, a waterlogging prediction module and a waterlogging warning module;

[0071] Data acquisition module: used to obtain water accumulation data in the target area;

[0072] Data analysis module: determines whether to issue a waterlogging warning based on waterlogging data and preset thresholds; if yes, sends warning information to the waterlogging warning module; if no, continues monitoring and judgment;

[0073] Obtain waterlogging data for the target area, including:

[0074] The water accumulation data of the target area is collected in real time through data acquisition equipment; the water accumulation data includes: rainfall, water level, drainage flow rate, drainage volume and sediment concentration in the water accumulation.

[0075] Determine whether to issue a waterlogging warning based on waterlogging data and preset thresholds, including:

[0076] Determine whether the rainfall in the preset time period is greater than the drainage volume; if yes, generate warning information; if no, continue monitoring and judgment; the preset time period is set according to the time period that needs to be monitored for actual urban waterlogging;

[0077] Determine whether the accumulated water level is greater than the preset water level threshold; if yes, generate an early warning message; if no, continue to monitor and judge; the preset water level threshold is set according to the actual urban waterlogging safety standards.

[0078] For example, suppose the target area is a low-lying area in a city, including several main streets and an underground passage, where water easily accumulates during heavy rainfall. The specific warning process is as follows:

[0079] Data collection;

[0080] 1. Rainfall;

[0081] Collection equipment: automatic rain gauge;

[0082] Location: Installed at multiple key points in the target area, such as street intersections and underpass entrances.

[0083] 2. Water level;

[0084] Collection equipment: ultrasonic liquid level sensor;

[0085] Location: Deployed in streets and tunnels prone to water accumulation, usually a few centimeters below the road surface.

[0086] 3. Drainage flow rate;

[0087] Collection equipment: Doppler flowmeter;

[0088] Location: Installed near sewer inlets and outlets to monitor water flow velocity.

[0089] 4. Displacement;

[0090] Collection equipment: flow meter;

[0091] Location: Installed at key points in the sewer pipe to record the amount of water passing through.

[0092] 5. Sediment concentration;

[0093] Collection equipment: turbidity sensor;

[0094] Location: Deployed in areas with accumulated water to monitor the content of suspended solids in the water.

[0095] 6. Preset threshold;

[0096] Comparison of rainfall and drainage: Assuming the preset time period is 30 minutes, if the total rainfall during this period exceeds 120% of the total drainage recorded in the same time, the system considers that there is a risk of waterlogging.

[0097] Water level threshold: If the water level reaches 20 cm, it is considered beyond the safety range and triggers an early warning.

[0098] Example description;

[0099] Assume that on a rainy night, the system detects the following:

[0100] In the past 30 minutes, the rainfall accumulated in a street reached 40 mm, while the drainage volume in the area in the same time period was 30 mm.

[0101] Ultrasonic level sensors on the same street showed that the water level had risen to 22 cm.

[0102] System response;

[0103] Based on the above data, the data analysis module determines that the current situation meets the warning conditions (the rainfall is greater than the drainage volume, and the accumulated water level exceeds the preset threshold), so the system generates a warning message and sends it to the waterlogging warning module.

[0104] The drainage assessment coefficient is calculated based on the water accumulation data;

[0105] Waterlogging prediction module: train the artificial intelligence model based on historical waterlogging data to obtain the waterlogging prediction model; predict the waterlogging data of the target area based on the waterlogging prediction model to obtain the prediction result;

[0106] Waterlogging warning module: Determine whether to issue a waterlogging warning based on the prediction results, drainage assessment coefficient and preset drainage threshold; if yes, send a warning message; if not, continue to monitor and judge; and, based on the warning message, issue an alarm through the warning device.

[0107] The drainage assessment coefficient is calculated based on the water accumulation data, including:

[0108] The drainage velocity is marked as V, the drainage volume is marked as N, and the sediment concentration in the accumulated water is marked as C;

[0109] The drainage assessment coefficient is calculated through the waterlogging assessment formula: P = X / ln(V+1)+Y / e^(N+1)+Z×(e^C) / ln(C+1); where P is the drainage assessment coefficient, X, Y, and Z are proportional coefficients, and ln(*) is a logarithmic function with the natural number e as the base.

[0110] The artificial intelligence model is trained based on historical waterlogging data to obtain a waterlogging prediction model, including:

[0111] S1: Obtain the corresponding relationship between waterlogging data by analyzing historical waterlogging data and urban hydrological data; wherein the corresponding relationship between waterlogging data includes: the corresponding relationship between rainfall and waterlogging level, the corresponding relationship between drainage volume and waterlogging level, the corresponding relationship between drainage velocity and drainage volume, and the corresponding relationship between sediment concentration in waterlogging and drainage velocity;

[0112] S2: Obtain the rainfall at the historical prediction time from the historical water accumulation data;

[0113] S3: based on the correspondence between the rainfall at the time of historical prediction and the waterlogging data, the waterlogging data at the time of prediction is obtained; wherein the waterlogging data at the time of prediction includes: the water level at the time of prediction, the drainage velocity at the time of prediction, the drainage volume at the time of prediction, and the sediment concentration in the waterlogging at the time of prediction;

[0114] S4: Integrate historical waterlogging data and rainfall at the time of historical prediction as standard input data; integrate waterlogging data at the time of prediction as standard output data;

[0115] S5: Train an artificial intelligence model based on standard input data and standard output data to obtain a waterlogging prediction model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0116] Based on the correspondence between rainfall and waterlogging data at the time of historical forecast, the waterlogging data at the time of forecast is obtained, including:

[0117] S1: Obtain the accumulated water level at the predicted time based on the rainfall at the historical predicted time and the corresponding relationship between the rainfall and the accumulated water level;

[0118] S2: obtaining the discharge volume at the prediction time based on the corresponding relationship between the accumulated water level at the prediction time and the discharge volume and the accumulated water level;

[0119] S3: obtaining the drainage flow rate at the prediction time based on the drainage volume at the prediction time and the corresponding relationship between the drainage flow rate and the drainage volume;

[0120] S4: Obtaining the sediment concentration in the accumulated water at the prediction time based on the drainage flow rate at the prediction time and the corresponding relationship between the sediment concentration in the accumulated water and the drainage flow rate.

[0121] Based on the waterlogging prediction model, the waterlogging data of the target area is predicted to obtain the prediction results, including:

[0122] Obtain the rainfall at the predicted time through the weather forecast platform;

[0123] The real-time waterlogging data of the target area and the rainfall at the prediction time are input into the waterlogging prediction model to obtain the prediction result; wherein the prediction result refers to the waterlogging data at the prediction time corresponding to the real-time waterlogging data of the target area.

[0124] Determine whether to issue a waterlogging warning based on the prediction results, drainage assessment coefficient and preset drainage threshold, including:

[0125] Determine whether the rainfall at the predicted time within the preset time period is greater than the drainage at the predicted time; if yes, generate warning information; if not, continue monitoring and judgment;

[0126] Determine whether the accumulated water level at the predicted time is greater than the preset water level threshold; if yes, generate warning information; if no, continue monitoring and judgment;

[0127] Determine whether the drainage assessment coefficient is greater than the preset drainage threshold; if yes, generate early warning information; if no, continue monitoring and judgment;

[0128] Determine whether the predicted drainage assessment coefficient is greater than the preset drainage threshold; if yes, produce early warning information; if not, continue to monitor and judge; among which, the preset drainage threshold is set according to the drainage capacity of the actual flood-prone area.

[0129] Predicted drainage assessment factors, including:

[0130] The predicted drainage assessment coefficient is calculated based on the predicted results;

[0131] The drainage velocity at the prediction time is marked as V1, the drainage volume at the prediction time is marked as N1, and the sediment concentration in the accumulated water at the prediction time is marked as C1;

[0132] The predicted drainage assessment coefficient is calculated through the waterlogging assessment calculation formula: P1=X / ln(V1+1)+Y / e^(N1+1)+Z×(e^C1) / ln(C1+1); where P1 is the predicted drainage assessment coefficient.

[0133] Based on the early warning information, the early warning device issues an alarm prompt, including:

[0134] The warning information is sent to the client of the urban waterlogging management personnel through wireless transmission technology; the wireless transmission technology includes: 4G / 5G or WIFI; the client includes: mobile phone or computer;

[0135] Based on the warning information, the warning equipment is used to alert people passing by; the warning equipment includes: warning lights, language announcers and LED display screens.

[0136] For example: Consider a low-lying area in the center of a city, consisting of two main streets and an underpass.

[0137] The specific early warning process is as follows:

[0138] 1. Historical waterlogging data: Data from every heavy rainfall event in the past five years, including rainfall, waterlogging level, drainage flow rate, drainage volume, and sediment concentration.

[0139] 2. Preset threshold:

[0140] Preset drainage threshold: 0.5 (a drainage assessment coefficient higher than this value may cause waterlogging);

[0141] Preset water level threshold: 25 cm;

[0142] Preset time period: within 60 minutes;

[0143] 3. Real-time water accumulation data:

[0144] Rainfall: 30mm / h;

[0145] Water level: 18cm;

[0146] Drainage flow rate: 0.5m / s;

[0147] Displacement: 1000 cubic meters / h;

[0148] Sediment concentration: 0.005kg / L;

[0149] 4. Calculate the drainage assessment coefficient;

[0150] Assume the scale factor: X = 0.6, Y = 0.5, Z = 0.8;

[0151] The drainage assessment coefficient is calculated using the waterlogging assessment formula: P = X / ln(V+1)+Y / e^(N+1)+Z×(e^C) / ln(C+1);

[0152] P=0.6 / ln(0.5+1)+0.5 / e^(1000+1)+0.8×(e^0.005) / ln(0.005+1)≈0.6;

[0153] 5. Prediction model and evaluation;

[0154] Data preparation:

[0155] Obtain the correspondence between historical rainfall and water level from urban hydrological data.

[0156] Analyze historical waterlogging data and establish the corresponding relationships between drainage volume and waterlogging level, drainage flow rate and drainage volume, and sediment concentration in the accumulated water and drainage flow rate.

[0157] Obtain the rainfall forecast for the next 24 hours (forecast time) through the weather forecast platform.

[0158] Prediction model training:

[0159] Assume that a convolutional neural network (CNN) is used as the artificial intelligence model.

[0160] The historical waterlogging data and the rainfall at the prediction time are used as standard input data, and the corresponding waterlogging data (water level, drainage flow rate, drainage volume, and sediment concentration) at the prediction time are used as standard output data.

[0161] Use these data to train the CNN model until the model performance reaches the predetermined standard and obtain the waterlogging prediction model.

[0162] Assume that the prediction data obtained is:

[0163] Predicted rainfall at the time: 40mm / h;

[0164] Predicted water level: 22cm;

[0165] Predicted drainage velocity: 0.4m / s;

[0166] Predicted displacement: 900 cubic meters / h;

[0167] Predicted sediment concentration: 0.006kg / L;

[0168] 6. Predicted drainage assessment coefficient;

[0169] The predicted drainage assessment coefficient is calculated through the waterlogging assessment calculation formula: P1 = X / ln(V1+1)+Y / e^(N1+1)+Z×(e^C1) / ln(C1+1);

[0170] P1=0.6 / ln(0.4+1)+0.5 / e^(900+1)+0.8×(e^0.006) / ln(0.006+1)≈1.79;

[0171] 7. Decision-making process;

[0172] Comparison of rainfall and drainage during the forecast period;

[0173] During the forecast period, the expected rainfall is 40 mm / h, while the drainage capacity of the area during this period, i.e. the drainage volume, is 900 m3 / h.

[0174] Rainfall conversion: 40 mm / h is equal to 0.04 m / h. Considering that the precipitation on 1 square meter is converted into volume, it is equivalent to 0.04 cubic meters / square meter·hour. Assuming the area of ​​the target area is 10,000 square meters, the rainfall of 40 mm / h is converted into volume as 400 cubic meters / hour.

[0175] Therefore, the rainfall in the forecast period, after conversion into volume (400 m3 / h), is less than the drainage volume (900 m3 / h), so no early warning is required and continuous monitoring is required.

[0176] Comparison of predicted water level with preset water level threshold;

[0177] Since the predicted water level (22cm) is lower than the preset water level threshold (25cm), no warning is required;

[0178] Comparison of drainage assessment coefficient with preset drainage threshold;

[0179] Since the drainage assessment coefficient (0.6) is greater than the preset drainage threshold (0.5), this indicates that the current drainage condition is poor and there is a high risk of waterlogging, and an early warning message needs to be sent.

[0180] Comparison of predicted drainage assessment coefficients with preset drainage thresholds;

[0181] The predicted drainage assessment coefficient (1.79) is greater than the preset drainage threshold (0.5), and is also significantly higher than the preset drainage threshold. This indicates that the drainage situation will further deteriorate in the future, increasing the possibility of waterlogging.

[0182] Early warning and response;

[0183] 1. Generation of early warning information;

[0184] Given that the drainage assessment coefficient and its predicted value both exceed the preset threshold, and the relationship between rainfall and drainage during the forecast period shows potential risks, the system automatically generates a warning message.

[0185] 2. Application of wireless transmission technology;

[0186] The warning information is transmitted to mobile terminals such as mobile phones or computers of urban waterlogging management personnel via 4G / 5G wireless networks, ensuring that managers can quickly receive warning notifications so that they can take timely response measures.

[0187] 3. Activate early warning equipment;

[0188] Through a series of early warning equipment, including warning lights, voice announcers and LED display screens, alarms are issued to surrounding pedestrians and vehicles, reminding them to pay attention to safety and avoid entering areas where flooding may occur.

[0189] Through the above-mentioned early warning and response mechanism, urban management departments can more effectively monitor and manage urban flooding risks, reduce losses caused by urban flooding, and protect people’s lives and property.

[0190] See also Figure 3 The second aspect of the present invention provides an urban waterlogging risk early warning method, comprising:

[0191] Step 1: Obtain water accumulation data in the target area in real time;

[0192] Step 2: Determine whether to issue a waterlogging warning based on the waterlogging data and the preset threshold; if yes, send the warning information to the waterlogging warning module; if no, continue monitoring and judging;

[0193] Step 3: Calculate the drainage assessment coefficient based on the water accumulation data;

[0194] Step 4: training an artificial intelligence model based on historical waterlogging data to obtain a waterlogging prediction model; and predicting waterlogging data in a target area based on the waterlogging prediction model to obtain a prediction result;

[0195] Step 5: Determine whether to issue a waterlogging warning based on the prediction results, drainage assessment coefficient and preset drainage threshold; if yes, send a warning message; if not, continue monitoring and judging; and, issue an alarm through the warning device based on the warning message.

[0196] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0197] Working principle of the present invention:

[0198] The present invention obtains waterlogging data of a target area in real time; determines whether to issue a waterlogging warning based on the waterlogging data and a preset threshold value; if yes, sends a warning message to a waterlogging warning module; if no, continuously monitors and determines; calculates a drainage assessment coefficient based on the waterlogging data; trains an artificial intelligence model based on historical waterlogging data to obtain a waterlogging prediction model; and, based on the waterlogging prediction model, predicts the waterlogging data of the target area to obtain a prediction result; determines whether to issue a waterlogging warning based on the prediction result, the drainage assessment coefficient and a preset drainage threshold value; if yes, sends a warning message; if no, continuously monitors and determines; and, based on the warning message, issues an alarm prompt through a warning device; the prior art solves the technical problem that the prior art does not take into account that accumulated water often contains a large amount of silt and debris, and the accumulation of silt will not only reduce the effective cross-sectional area of ​​the pipeline, reduce the water flow rate, and result in a decrease in the drainage capacity of the waterlogged area, causing aggravated waterlogging, but also cause aggravated pipe wear and shorten its service life.

[0199] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. Urban flood risk early warning system, characterized by: include: Data collection module, data analysis module, waterlogging prediction module and waterlogging warning module; Data acquisition module: used to obtain water accumulation data in the target area; Data analysis module: determines whether to issue a waterlogging warning based on waterlogging data and preset thresholds; If yes, then send warning information to the waterlogging warning module; If not, continue to monitor and judge; as well as, The drainage assessment coefficient is calculated based on the water accumulation data; Waterlogging prediction module: train the artificial intelligence model based on historical waterlogging data to obtain the waterlogging prediction model; predict the waterlogging data of the target area based on the waterlogging prediction model to obtain the prediction result; Waterlogging warning module: determines whether to issue a waterlogging warning based on the prediction results, drainage assessment coefficient and preset drainage threshold; If yes, a warning message will be sent; If not, continue to monitor and judge; as well as, Based on the warning information, an alarm is issued through the early warning device.

2. The urban flood risk early warning system according to claim 1 is characterized in that: The step of obtaining water accumulation data of the target area includes: The water accumulation data of the target area is collected in real time through data acquisition equipment; the water accumulation data includes: rainfall, water level, drainage flow rate, drainage volume and sediment concentration in the water accumulation.

3. The urban flood risk early warning system according to claim 1 is characterized in that: The determining whether to issue a waterlogging warning based on waterlogging data and a preset threshold value includes: Determine whether the rainfall in the preset time period is greater than the drainage volume; if yes, generate warning information; if no, continue monitoring and judgment; the preset time period is set according to the time period that needs to be monitored for actual urban waterlogging; Determine whether the accumulated water level is greater than the preset water level threshold; if yes, generate an early warning message; if no, continue to monitor and judge; the preset water level threshold is set according to the actual urban waterlogging safety standards.

4. The urban flood risk early warning system according to claim 1 is characterized in that: The drainage assessment coefficient is calculated based on the water accumulation data, including: The drainage velocity is marked as V, the drainage volume is marked as N, and the sediment concentration in the accumulated water is marked as C; The drainage assessment coefficient is calculated through the waterlogging assessment formula: P = X / ln(V+1)+Y / e^(N+1)+Z×(e^C) / ln(C+1); where P is the drainage assessment coefficient, X, Y, and Z are proportional coefficients, and ln(*) is a logarithmic function with the natural number e as the base.

5. The urban flood risk early warning system according to claim 1 is characterized in that: The artificial intelligence model is trained based on historical waterlogging data to obtain a waterlogging prediction model, including: S1: Obtain the corresponding relationship between waterlogging data by analyzing historical waterlogging data and urban hydrological data; wherein the corresponding relationship between waterlogging data includes: the corresponding relationship between rainfall and waterlogging level, the corresponding relationship between drainage volume and waterlogging level, the corresponding relationship between drainage velocity and drainage volume, and the corresponding relationship between sediment concentration in waterlogging and drainage velocity; S2: Obtain the rainfall at the historical prediction time from the historical water accumulation data; S3: based on the correspondence between the rainfall at the time of historical prediction and the waterlogging data, the waterlogging data at the time of prediction is obtained; wherein the waterlogging data at the time of prediction includes: the water level at the time of prediction, the drainage velocity at the time of prediction, the drainage volume at the time of prediction, and the sediment concentration in the waterlogging at the time of prediction; S4: Integrate historical waterlogging data and rainfall at the time of historical prediction as standard input data; integrate waterlogging data at the time of prediction as standard output data; S5: Train an artificial intelligence model based on standard input data and standard output data to obtain a waterlogging prediction model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

6. The urban flood risk early warning system according to claim 5 is characterized in that: The method of obtaining waterlogging data at the prediction time based on the correspondence between rainfall and water accumulation data at the historical prediction time includes: S1: Obtain the accumulated water level at the predicted time based on the rainfall at the historical predicted time and the corresponding relationship between the rainfall and the accumulated water level; S2: obtaining the discharge volume at the prediction time based on the corresponding relationship between the accumulated water level at the prediction time and the discharge volume and the accumulated water level; S3: obtaining the drainage flow rate at the prediction time based on the drainage volume at the prediction time and the corresponding relationship between the drainage flow rate and the drainage volume; S4: Obtaining the sediment concentration in the accumulated water at the prediction time based on the drainage flow rate at the prediction time and the corresponding relationship between the sediment concentration in the accumulated water and the drainage flow rate.

7. The urban flood risk early warning system according to claim 1 is characterized in that: The waterlogging prediction model is used to predict the waterlogging data of the target area to obtain the prediction results, including: Obtain the rainfall at the predicted time through the weather forecast platform; The real-time waterlogging data of the target area and the rainfall at the prediction time are input into the waterlogging prediction model to obtain the prediction result; wherein the prediction result refers to the waterlogging data at the prediction time corresponding to the real-time waterlogging data of the target area.

8. The urban flood risk early warning system according to claim 1 is characterized in that: The determining whether to issue a waterlogging warning based on the prediction result, the drainage assessment coefficient and the preset drainage threshold value includes: Determine whether the rainfall at the predicted time within the preset time period is greater than the drainage at the predicted time; if yes, generate warning information; if not, continue monitoring and judgment; Determine whether the accumulated water level at the predicted time is greater than the preset water level threshold; if yes, generate warning information; if no, continue monitoring and judgment; Determine whether the drainage assessment coefficient is greater than the preset drainage threshold; if yes, generate early warning information; if no, continue monitoring and judgment; Determine whether the predicted drainage assessment coefficient is greater than the preset drainage threshold; if yes, produce early warning information; if not, continue to monitor and judge; among which, the preset drainage threshold is set according to the drainage capacity of the actual flood-prone area.

9. The urban waterlogging risk early warning system according to claim 8, characterized in that: The predicted drainage assessment coefficient includes: The predicted drainage assessment coefficient is calculated based on the predicted results; The drainage velocity at the prediction time is marked as V1, the drainage volume at the prediction time is marked as N1, and the sediment concentration in the accumulated water at the prediction time is marked as C1; The predicted drainage assessment coefficient is calculated through the waterlogging assessment calculation formula: P1=X / ln(V1+1)+Y / e^(N1+1)+Z×(e^C1) / ln(C1+1); where P1 is the predicted drainage assessment coefficient.

10. An urban waterlogging risk early warning method, applied to an urban waterlogging risk early warning system according to any one of claims 1 to 9, characterized in that: include: Step 1: Obtain water accumulation data in the target area in real time; Step 2: Determine whether to issue a waterlogging warning based on waterlogging data and preset thresholds; If yes, then send warning information to the waterlogging warning module; If not, continue to monitor and judge; Step 3: Calculate the drainage assessment coefficient based on the water accumulation data; Step 4: training an artificial intelligence model based on historical waterlogging data to obtain a waterlogging prediction model; and predicting waterlogging data in a target area based on the waterlogging prediction model to obtain a prediction result; Step 5: Determine whether to issue a waterlogging warning based on the prediction results, drainage assessment coefficient and preset drainage threshold; If yes, a warning message will be sent; If not, continue to monitor and judge; and, issue an alarm prompt through the early warning device based on the early warning information.

Images