Urban road accumulated water monitoring and drainage system

Abstract

The invention provides an urban road ponding monitoring and drainage system. The urban road ponding monitoring and drainage system comprises a monitoring module which collects ponding depth, water velocity, rainfall intensity and field image data in real time; the initialization configuration module sets parameters such as an accumulated water depth threshold value; the data transmission module encrypts and transmits data to the central control module; the model algorithm optimization module constructs a three-dimensional ponding diffusion model and outputs a predicted ponding depth and an optimized drainage strategy; the central control module generates a drainage pump rotating speed instruction and the like; the drainage execution module dynamically adjusts drainage pump power and a drainage path; the self-checking and fault-tolerant module calculates a health index of drainage equipment and switches redundant equipment; the early warning module sends risk level information; and the interaction module displays information such as a real-time accumulated water thermodynamic diagram. The urban road drainage efficiency can be improved, the water accumulation risk is reduced, and smooth urban traffic and public travel safety are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of urban infrastructure, and more specifically, to a monitoring and drainage system for urban road waterlogging. Background Art

[0002] With the acceleration of the urbanization process, the problem of urban road waterlogging has become increasingly prominent, bringing many inconveniences to traffic travel and residents' lives. Most of the existing drainage systems rely on traditional drainage pipes and pumping stations, and these systems have certain limitations in design and operation. For example, the layout and capacity of drainage pipes are usually designed based on historical rainfall data and experience, and it is difficult to cope with heavy rain events under extreme weather conditions. In addition, the existing drainage systems lack real-time monitoring and dynamic regulation capabilities, and cannot flexibly adjust drainage strategies according to real-time rainfall intensity and waterlogging conditions. During the operation of drainage equipment, there is also a lack of effective health monitoring and fault warning mechanisms. Once the equipment fails, it may lead to poor drainage and further exacerbate the waterlogging problem.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: The existing drainage systems cannot monitor key parameters such as the depth of road waterlogging, water flow velocity, and rainfall intensity in real time, cannot accurately predict the trend of waterlogging spread, and it is difficult to achieve precise drainage regulation; the operating status of drainage equipment lacks real-time monitoring, and when the equipment fails, it cannot be switched to standby equipment in time, affecting drainage efficiency; at the same time, the existing systems lack an effective interaction mechanism with municipal management departments and the public, and cannot issue waterlogging warning information in time, resulting in the public lacking effective countermeasures when facing road waterlogging. Summary of the Invention

[0004] The present invention provides a monitoring and drainage system for urban road waterlogging, including:

[0005] A monitoring module for real-time collecting the depth of road waterlogging, water flow velocity, rainfall intensity, and on-site image data;

[0006] An initialization configuration module for setting the waterlogging depth threshold, rainfall intensity threshold, sensor calibration parameters, and drainage equipment operation parameters of the road area;

[0007] A data transmission module for encrypting and transmitting the depth of road waterlogging, water flow velocity, rainfall intensity, and on-site image data to a central control module through a wireless communication network;

[0008] A model algorithm optimization module for constructing a three-dimensional waterlogging diffusion model based on the depth of road waterlogging, terrain elevation, and drainage pipe network topology data, and outputting the predicted waterlogging depth and optimized drainage strategy;

[0009] The central control module generates a drainage pump speed command, a valve control command, and a multi-level warning signal according to the predicted waterlogging depth;

[0010] The drainage execution module dynamically adjusts the power of the drainage pump and the drainage path according to the speed command and the valve control command;

[0011] The self-check and fault tolerance module calculates the health index of the drainage equipment in real time and switches to redundant equipment when the index is abnormal;

[0012] The warning module sends risk level information to the municipal management terminal and the public mobile terminal according to the multi-level warning signal;

[0013] The interaction module is used to display the real-time waterlogging heat map, the status of the drainage equipment, and the predicted waterlogging range.

[0014] Furthermore, the initialization configuration module includes:

[0015] The parameter adaptive unit dynamically adjusts the waterlogging depth threshold, and its threshold calculation formula is:

[0016] D th =μD max +σR avg

[0017] Where D th represents the waterlogging depth threshold, v represents the depth correction coefficient, D max represents the historical maximum waterlogging depth, σ represents the rainfall weight coefficient, and R avg represents the regional average rainfall intensity;

[0018] The sensor calibration unit corrects the waterlogging depth data through the temperature compensation formula, and its calibration formula is:

[0019] D 校准 =D 原始 (1 + ∈ΔT)

[0020] Where D 校准 represents the calibrated waterlogging depth, D 原始 represents the original waterlogging depth measurement value, ∈ represents the temperature compensation coefficient, and ΔT represents the ambient temperature change.

[0021] Furthermore, the model algorithm optimization module performs the following steps:

[0022] S1. Input the real-time road waterlogging depth, terrain elevation, and the upper limit of the drainage pipe network flow rate, and construct a three-dimensional waterlogging diffusion partial differential equation:

[0023]

[0024] Where D represents the depth of accumulated water, t represents time, α represents the diffusion coefficient, represents the Laplace operator, β represents the rainfall absorption rate, R(t) represents the rainfall intensity function varying with time, γ represents the drainage attenuation factor, Q(D, H) represents the drainage flow function, and H represents the current water level elevation;

[0025] S2. Based on the partial differential equation, use a spatio-temporal convolutional neural network to predict the depth of accumulated water in the future Δt period and output the predicted value D 预测 , and the input features of the spatio-temporal convolutional neural network include the depth of accumulated water D, rainfall intensity R(t), and drainage flow Q(D, H) in the partial differential equation;

[0026] S3. When the predicted value exceeds the threshold of the depth of accumulated water, adjust the drainage attenuation factor, and the update formula is:

[0027]

[0028] where γ 新 represents the new drainage attenuation factor, γ 旧 represents the old drainage attenuation factor, λ represents the feedback gain coefficient, D 预测 represents the predicted depth of accumulated water, and D th represents the threshold of the depth of accumulated water.

[0029] Furthermore, the drainage flow function Q(D, H) is defined as:

[0030] Q = K1D 2 sinθ + K2(H0 - H)D

[0031] where Q represents the drainage flow, K1 represents the water flow inertia coefficient, D represents the depth of accumulated water, θ represents the road slope angle, K2 represents the gravity drainage coefficient, H0 represents the reference elevation of the drainage outlet, and H represents the current water level elevation.

[0032] Furthermore, the drainage execution module includes:

[0033] A multi-level linkage unit that calculates the drainage priority according to the real-time depth of accumulated water and the rate of change of accumulated water, and allocates the power of the drainage pump. Its priority formula is:

[0034]

[0035] where P represents the drainage priority, ω1 and ω2 represent weight coefficients, D represents the depth of accumulated water, represents the rate of change of the depth of accumulated water;

[0036] A self-cleaning unit that triggers the reverse water flow to clean the pump body when the cumulative working time exceeds the preset threshold. Its cleaning intensity formula is:

[0037]

[0038] Among them, B represents the cleaning intensity, κ represents the fouling adhesion coefficient, T represents the cumulative working time, and D(t) represents the accumulated water depth function that changes with time.

[0039] Furthermore, the self-checking and fault-tolerant module performs the following operations:

[0040] Calculate the efficiency of the drainage pump in real time, and its efficiency formula is:

[0041]

[0042] Among them, η represents the efficiency of the drainage pump, I represents the current, U represents the voltage, φ represents the power factor angle, and P 额定 represents the rated power of the drainage pump;

[0043] When the efficiency is lower than the preset threshold, generate a device degradation curve, and its formula is:

[0044] L = 1e kT

[0045] Among them, L represents the degree of device degradation, k represents the degradation rate constant, and T represents the running time;

[0046] If the degree of degradation exceeds the threshold, switch to the standby pump.

[0047] Furthermore, the grading logic of the warning module is as follows:

[0048] First-level warning: When the real-time accumulated water depth reaches 70% of the threshold and the water accumulation rate continues to rise, send a preparatory instruction to the municipal terminal;

[0049] Second-level warning: When the real-time accumulated water depth exceeds the threshold and the rainfall intensity reaches the threshold, push avoidance information to the public;

[0050] Third-level warning: When the real-time accumulated water depth exceeds 130% of the threshold and the drainage efficiency is lower than 50%, activate the emergency pumping vehicle dispatch.

[0051] Furthermore, the interaction module includes:

[0052] A dynamic visualization unit that generates a heat map of accumulated water with a color gradient mapping, and its color mapping formula is:

[0053]

[0054] Among them, C represents the color value, D represents the accumulated water depth, D max represents the maximum accumulated water depth, and n represents the non-linear enhancement index;

[0055] The prediction and deduction unit calculates the future water accumulation range based on the assumed rainfall, and its calculation formula is:

[0056] where S represents the future water accumulation range, β represents the rainfall absorption rate, R 假设 represents the assumed rainfall, γ represents the drainage attenuation factor, Q(D, H) represents the drainage flow function, and T represents time.

[0057] Furthermore, the data transmission module adopts a hybrid communication protocol:

[0058] In the normal mode, encrypted data packets are transmitted, and its data packet structure is:

[0059] Frame = {ID, D, R, I img , T}

[0060] where ID represents the sensor number, D represents the water accumulation depth, R represents the rainfall intensity, I img represents the image data, and T represents the timestamp;

[0061] When the signal strength is lower than the threshold, it switches to the standby communication network, and its switching condition is:

[0062]

[0063] where S rssi represents the signal strength, S min represents the minimum signal strength threshold, τ represents the link delay, τ max represents the maximum link delay threshold.

[0064] Furthermore, the monitoring module includes:

[0065] The multi-spectral imaging unit identifies foreign objects on the water surface through the reflection intensity ratio, and its foreign object probability formula is:

[0066]

[0067] where P 异物 represents the probability of the existence of foreign objects, w λ represents the weights of different bands, I λ represents the reflection intensity of the current band, I λ0 represents the reference reflection intensity of the clean water surface in this band.

[0068] The above embodiments of the present invention have at least the following beneficial effects: The urban road waterlogging monitoring and drainage system of the present invention can collect real-time road waterlogging depth, water flow velocity, rainfall intensity and on-site image data, and encrypt and transmit them to the central control module through a wireless communication network. The system can build a three-dimensional waterlogging diffusion model based on these data, predict the waterlogging depth and optimize the drainage strategy, so as to dynamically adjust the power of drainage pumps and the drainage path. This intelligent monitoring and control method can improve the operation efficiency of the urban road drainage system, effectively reduce the waterlogging risk, and ensure the smoothness of urban traffic and the safety of residents' travel.

[0069] In addition, the system also has self-checking and fault-tolerant functions, can calculate the health index of drainage equipment in real time, and automatically switch to redundant equipment when the equipment fails, ensuring the stable operation of the drainage system. The early warning module can generate multi-level warning signals according to the waterlogging depth and rainfall intensity, and timely release risk information to the municipal management department and the public, further enhancing the city's emergency response ability to extreme weather. The interaction module can display the real-time waterlogging heat map and the status of drainage equipment, providing an intuitive reference for municipal management and public travel. The comprehensive application of these functions can effectively improve the intelligent management level of urban infrastructure and provide strong support for the sustainable development of the city. Brief Description of the Drawings

[0070] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, wherein:

[0071] Figure 1 It is a schematic structural diagram of the urban road waterlogging monitoring and drainage system provided by an embodiment of the present invention. Detailed Embodiments

[0072] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and then implement the present invention, and do not limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to be able to fully convey the scope of the present invention to those skilled in the art.

[0073] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, equipment, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: completely hardware, completely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0074] It should be noted that any number of elements in the accompanying drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0075] The following refers to Figure 1 , Figure 1 which is a schematic structural diagram of a urban road waterlogging monitoring and drainage system provided by an embodiment of the present invention. As Figure 1 shown, a urban road waterlogging monitoring and drainage system 100 includes:

[0076] A monitoring module 101 for real-time collecting road waterlogging depth, water flow velocity, rainfall intensity and on-site image data;

[0077] An initialization configuration module 102 for setting waterlogging depth thresholds, rainfall intensity thresholds, sensor calibration parameters and drainage equipment operation parameters for the road area;

[0078] A data transmission module 103 for encrypting and transmitting the road waterlogging depth, water flow velocity, rainfall intensity and on-site image data to a central control module through a wireless communication network;

[0079] A model algorithm optimization module 104 for constructing a three-dimensional waterlogging diffusion model based on the road waterlogging depth, terrain elevation and drainage pipe network topology data, and outputting predicted waterlogging depth and optimized drainage strategies;

[0080] A central control module 105 for generating drainage pump speed commands, valve control commands and multi-level warning signals according to the predicted waterlogging depth;

[0081] A drainage execution module 106 for dynamically adjusting the drainage pump power and drainage path according to the speed command and valve control command;

[0082] A self-checking and fault tolerance module 107 for calculating the health index of the drainage equipment in real time and switching redundant equipment when the index is abnormal;

[0083] A warning module 108 for sending risk level information to the municipal management terminal and the public mobile terminal according to the multi-level warning signals;

[0084] An interaction module 109 for displaying real-time waterlogging heat maps, drainage equipment status and predicted waterlogging ranges.

[0085] It should be noted that this system includes a monitoring module for real-time collection of road waterlogging depth, water flow velocity, rainfall intensity, and on-site image data. The monitoring module is the foundation of the entire system, which obtains key data through various sensors and imaging devices. The waterlogging depth refers to the vertical height of the water accumulation on the road surface, the water flow velocity indicates the speed of the water accumulation flow, and the rainfall intensity is the amount of rainfall per unit time. The on-site image data is collected by cameras for visually displaying the waterlogging situation. The initialization configuration module is used to set the waterlogging depth threshold, rainfall intensity threshold, sensor calibration parameters, and drainage equipment operation parameters for the road area. The waterlogging depth threshold is a reference value for judging whether the waterlogging reaches a dangerous level, and the rainfall intensity threshold is used to evaluate the impact of rainfall on waterlogging. The sensor calibration parameters ensure the accuracy of the monitoring data, and the drainage equipment operation parameters control the working status of devices such as drainage pumps. The data transmission module encrypts and transmits the collected data to the central control module through a wireless communication network to ensure the security and real-time nature of the data. The central control module generates drainage pump speed commands, valve control commands, and multi-level warning signals based on the predicted waterlogging depth to achieve intelligent control of the drainage system. The drainage execution module dynamically adjusts the drainage pump power and drainage path according to the speed commands and valve control commands to adapt to different waterlogging situations. The self-check and fault tolerance module calculates the health index of the drainage equipment in real time and switches to redundant equipment when the index is abnormal to ensure the reliability of the system. The warning module sends risk level information to the municipal management terminal and the public mobile terminal according to the multi-level warning signals to notify relevant personnel and the public in a timely manner. The interaction module is used to display the real-time waterlogging heat map, the status of the drainage equipment, and the predicted waterlogging range to provide intuitive information display for users.

[0086] Specifically, the sensors in the monitoring module can include ultrasonic sensors, radar sensors, or water level gauges, etc., which are used to accurately measure the depth of accumulated water. The water flow velocity can be measured by Doppler radar or flow velocity sensors, and the rainfall intensity can be obtained through rain gauges. The on-site image data is collected by a high-definition camera, and the resolution can be set to 1920×1080 pixels or higher to ensure image clarity. The threshold of accumulated water depth in the initialization configuration module can be set according to historical data and experience. For example, a lower threshold, such as 10 cm, can be set in areas prone to water accumulation, while a higher threshold, such as 20 cm, can be set in areas with good drainage. The rainfall intensity threshold can be set according to local meteorological data, such as 30 mm / hour. The sensor calibration parameters include temperature compensation coefficients and depth correction coefficients, etc., and these parameters can be adjusted according to the characteristics of the sensors and environmental conditions. The operating parameters of the drainage equipment include the rated power and speed range of the drainage pump, etc., and these parameters need to be configured according to the specific design of the drainage system. The wireless communication network adopted by the data transmission module can be 4G, 5G, or NB-IoT, etc., and the encryption method can adopt advanced encryption standards such as AES-256 to ensure the security and confidentiality of data during transmission. The central control module can calculate the optimal rotation speed of the drainage pump and the opening degree of the valve through algorithms according to the predicted accumulated water depth to achieve efficient drainage. The drainage pump in the drainage execution module can adjust its power according to the instruction. For example, it can increase the power when the accumulated water depth is high and decrease the power when the accumulated water depth is low to save energy. The self-check and fault tolerance module calculates the health index by real-time monitoring parameters such as the current and voltage of the drainage pump. When the health index is lower than the set threshold, it automatically switches to the standby device. The warning module can generate warning signals of different levels according to the accumulated water depth and rainfall intensity. For example, the first-level warning signal can be that the accumulated water depth reaches 70% of the threshold, and the second-level warning signal can be that the accumulated water depth exceeds the threshold and the rainfall intensity reaches the threshold, etc. The interaction module can display the real-time accumulated water heat map in the form of a color gradient on the electronic map. Green indicates shallower accumulated water, and red indicates deeper accumulated water. At the same time, it shows the operating status of the drainage equipment and the predicted accumulated water range.

[0087] Preferably, the multispectral imaging unit in the monitoring module can identify foreign objects on the water surface, such as floating garbage or branches, etc., through the reflection intensity ratio, improving the comprehensiveness of monitoring. The parameter adaptive unit in the initialization configuration module can dynamically adjust the water accumulation depth threshold according to the real-time rainfall intensity and historical water accumulation data, enabling the system to better adapt to different rainfall conditions. The data transmission module can automatically switch to the standby communication network when the signal strength is lower than the threshold, such as switching from 4G to 5G, ensuring the stability of data transmission. The spatio-temporal convolutional neural network in the model algorithm optimization module can predict the water accumulation depth in the future period based on real-time data, providing a basis for optimizing the drainage strategy. The multi-level linkage unit in the drainage execution module can calculate the drainage priority according to the real-time water accumulation depth and its change rate, and give priority to areas with high water accumulation depth and fast change rate. The self-check and fault tolerance module can regularly conduct self-checks on the drainage equipment, generate equipment deterioration curves, predict the service life of the equipment in advance, and facilitate timely maintenance. The grading logic of the early warning module can push corresponding early warning information to the municipal terminal and the public according to different water accumulation situations and rainfall intensities, improving the pertinence and effectiveness of early warning. The prediction and deduction unit of the interaction module can calculate the future water accumulation range according to the assumed rainfall amount, providing a scientific basis for municipal management and public travel.

[0088] In some embodiments, the initialization configuration module includes:

[0089] A parameter adaptive unit that dynamically adjusts the water accumulation depth threshold, and its threshold calculation formula is:

[0090] D th =μD max +σR avg

[0091] where D th represents the water accumulation depth threshold, v represents the depth correction coefficient, D max represents the historical maximum water accumulation depth, σ represents the rainfall weight coefficient, and R avg represents the regional average rainfall intensity;

[0092] A sensor calibration unit that corrects the water accumulation depth data through the temperature compensation formula, and its calibration formula is:

[0093] D 校准 =D 原始 (1 + ∈ΔT)

[0094] where D 校准 represents the calibrated water accumulation depth, D 原始 represents the original water accumulation depth measurement value, ∈ represents the temperature compensation coefficient, and ΔT represents the environmental temperature change.

[0095] It should be noted that the initialization configuration module includes a parameter adaptation unit and a sensor calibration unit. The parameter adaptation unit can dynamically adjust the water accumulation depth threshold to adapt to different rainfall conditions and road conditions. The water accumulation depth threshold is a key parameter for judging whether the water accumulation reaches a dangerous level. By dynamically adjusting it, the adaptability and accuracy of the system can be improved. The sensor calibration unit corrects the water accumulation depth data through a temperature compensation formula to ensure the accuracy of the monitoring data. The temperature compensation coefficient is used to correct the measurement error of the sensor caused by the change in environmental temperature. The environmental temperature change amount refers to the difference between the current environmental temperature and the sensor calibration reference temperature. Through these functions, the initialization configuration module can effectively improve the reliability and accuracy of the system under different environmental conditions.

[0096] Specifically, in the formula for calculating the water accumulation depth threshold of the parameter adaptation unit, the depth correction coefficient is an empirical parameter used to adjust the influence degree of the historical maximum water accumulation depth on the current threshold. The historical maximum water accumulation depth refers to the highest water accumulation depth recorded in the past in this area. The rainfall weight coefficient reflects the influence degree of rainfall intensity on the water accumulation depth, and the regional average rainfall intensity is the average value statistically obtained based on the long-term rainfall data in this area. The temperature compensation coefficient of the sensor calibration unit is a parameter related to the sensor characteristics and is used to correct the measurement deviation of the sensor at different temperatures. For example, when the environmental temperature rises, the sensor may have a higher measurement value due to factors such as thermal expansion. Through the temperature compensation formula, the original measurement value can be corrected to a calibration value closer to the true value. In practical applications, the depth correction coefficient can be set between 0.5 and 1.5 according to historical data and experience, the rainfall weight coefficient can be set between 0.1 and 0.5 according to the intensity of rainfall's influence on water accumulation, and the temperature compensation coefficient can be set between -0.01 and 0.01 according to the temperature characteristics of the sensor.

[0097] Preferably, the parameter adaptation unit can dynamically adjust the water accumulation depth threshold according to the real-time rainfall intensity and historical water accumulation data. For example, when the rainfall intensity suddenly increases, the system can automatically lower the water accumulation depth threshold to give an early warning of possible water accumulation risks. The sensor calibration unit can be automatically calibrated regularly, for example, once every 24 hours, to ensure the long-term accuracy of the monitoring data. In addition, the sensor calibration unit can also combine other environmental parameters, such as humidity and air pressure, to further improve the calibration accuracy. For example, in a high-humidity environment, the sensor may be affected by water vapor. By comprehensively considering humidity and temperature factors, the measurement error can be corrected more accurately. In practical applications, the system can flexibly adjust these parameters and calibration strategies according to the climate characteristics and road conditions of different regions to achieve the best monitoring effect.

[0098] In some embodiments, the model algorithm optimization module performs the following steps:

[0099] S1. Input the real-time road waterlogging depth, terrain elevation, and the upper limit of the drainage pipe network flow rate, and construct a three-dimensional waterlogging diffusion partial differential equation:

[0100]

[0101] where D represents the waterlogging depth, t represents time, α represents the diffusion coefficient, represents the Laplace operator, β represents the rainfall absorption rate, R(t) represents the rainfall intensity function varying with time, γ represents the drainage attenuation factor, Q(D, H) represents the drainage flow function, and H represents the current water level elevation;

[0102] S2. Based on the partial differential equation, use a spatio-temporal convolutional neural network to predict the waterlogging depth in the future Δt period, and output the predicted value D 预测 , and the input features of the spatio-temporal convolutional neural network include the waterlogging depth D, rainfall intensity R(t), and drainage flow Q(D, H) in the partial differential equation;

[0103] S3. When the predicted value exceeds the waterlogging depth threshold, adjust the drainage attenuation factor, and the update formula is:

[0104]

[0105] where γ 新 represents the new drainage attenuation factor, γ 旧 represents the old drainage attenuation factor, λ represents the feedback gain coefficient, D 预测 represents the predicted waterlogging depth, and D th represents the waterlogging depth threshold.

[0106] It should be noted that the model algorithm optimization module executes a series of steps to construct a three-dimensional waterlogging diffusion model and optimize the drainage strategy. This module first inputs the real-time road waterlogging depth, terrain elevation, and the upper limit of the drainage pipe network flow rate, and constructs a three-dimensional waterlogging diffusion partial differential equation. The waterlogging depth refers to the height of the water accumulation on the road surface, the terrain elevation is the altitude of different positions of the road, and the upper limit of the drainage pipe network flow rate is the maximum flow rate that the drainage pipe can withstand. Through these data, the partial differential equation can describe the diffusion process of waterlogging in time and space. Then, a spatio-temporal convolutional neural network (STCNN) is used to predict the waterlogging depth in the future period. This network can process data features in time and space, and the input features include waterlogging depth, rainfall intensity, and drainage flow. When the predicted waterlogging depth exceeds the set threshold, the system will adjust the drainage attenuation factor to optimize the drainage strategy. The drainage attenuation factor is a parameter used to adjust the drainage efficiency and is dynamically updated through a feedback mechanism to ensure that the drainage system can effectively handle the waterlogging situation.

[0107] Specifically, when constructing the three-dimensional partial differential equation for ponding water diffusion, the diffusion coefficient is a parameter related to the diffusion speed of ponding water, which is usually set according to the physical properties of the ponding water (such as viscosity) and the roughness of the road surface. The rainfall absorption rate reflects the degree to which rainfall is absorbed by the road surface and is related to road materials and soil properties. The drainage attenuation factor is related to the efficiency of the drainage system and the complexity of the drainage path. In the spatio-temporal convolutional neural network, the selection of input features is crucial. The ponding depth can be measured in real time by sensors, the rainfall intensity can be obtained by rain gauges, and the drainage flow can be measured by flow sensors. These data are preprocessed and then input into the network. The network learns the patterns of historical data and real-time data to predict the ponding depth in future time periods. When the predicted ponding depth exceeds the threshold, in the adjustment formula of the drainage attenuation factor, the feedback gain coefficient is a parameter used to adjust the change rate of the drainage attenuation factor, which is usually set according to the response speed and stability requirements of the system. For example, the feedback gain coefficient can be set between 0.1 and 0.5 to ensure that the system is neither too aggressive nor too conservative when adjusting the drainage strategy.

[0108] Preferably, the model algorithm optimization module can be further refined. For example, when constructing the three-dimensional partial differential equation for ponding water diffusion, more terrain feature parameters such as road slope and drainage outlet location can be introduced to improve the accuracy of the model. For the spatio-temporal convolutional neural network, more advanced network architectures such as Deep Residual Network (ResNet) or Transformer architecture can be adopted to improve the prediction accuracy and efficiency. When adjusting the drainage attenuation factor, in addition to the feedback gain coefficient, other dynamic adjustment parameters such as time decay factor can be introduced to consider the changing trend of ponding depth over time. In addition, the system can automatically select different drainage strategies according to different rainfall patterns (such as short-term heavy rainfall and continuous rainfall) to better adapt to complex rainfall conditions. For example, during short-term heavy rainfall, the system can quickly increase the power of the drainage pump, while during continuous rainfall, the system can optimize the drainage path to improve drainage efficiency. Through these optimization measures, the model algorithm optimization module can more effectively predict the ponding situation and optimize the drainage strategy, thereby improving the performance of the entire drainage system.

[0109] In some embodiments, the drainage flow function Q(D,H) is defined as:

[0110] Q = K1D 2 sinθ + K2(H0H)D

[0111] where Q represents the drainage flow, K1 represents the water flow inertia coefficient, D represents the ponding depth, θ represents the road slope angle, K2 represents the gravity drainage coefficient, H0 represents the drainage outlet reference elevation, and H represents the current water level elevation.

[0112] It should be noted that the drainage flow function is used to describe the drainage capacity of the drainage system under specific conditions. It comprehensively considers factors such as the water flow inertia coefficient, the depth of accumulated water, the road slope angle, the gravity drainage coefficient, the reference elevation of the drainage outlet, and the current water level elevation. The water flow inertia coefficient reflects the inertial effect of water flow in the pipeline. The depth of accumulated water is the height of the water accumulated on the road surface. The road slope angle is the inclination angle of the road. The gravity drainage coefficient is related to the drainage efficiency under the action of gravity. The reference elevation of the drainage outlet is the fixed height of the drainage outlet, and the current water level elevation is the water level height measured in real time. Through these parameters, the drainage flow function can accurately calculate the drainage flow of the drainage system, thus providing a basis for optimizing the drainage strategy.

[0113] Specifically, the water flow inertia coefficient in the drainage flow function can be set according to the material and diameter of the drainage pipeline. For example, for a large-diameter concrete pipeline, the water flow inertia coefficient can be set between 0.8 and 1.0; while for a small-diameter PVC pipeline, this coefficient can be set between 0.6 and 0.8. The depth of accumulated water is monitored in real time by a water level sensor, with the unit being meters. The road slope angle is usually in degrees and can be obtained from topographic survey data. The gravity drainage coefficient is related to the inclination angle of the pipeline and the water flow velocity, and is generally set between 0.5 and 0.9. The reference elevation of the drainage outlet is the fixed height of the drainage outlet, with the unit being meters, and is usually determined during the system design stage. The current water level elevation is measured in real time by a water level sensor, with the unit also being meters. The reasonable setting and real-time monitoring of these parameters enable the drainage flow function to accurately reflect the actual drainage capacity of the drainage system. In practical applications, the drainage flow function can be adjusted according to different drainage scenarios. For example, in urban road drainage, the settings of these coefficients can be optimized according to the specific slope of the road and the design parameters of the drainage pipeline to improve the drainage efficiency.

[0114] Preferably, the drainage flow function can be further optimized according to different drainage scenarios. For example, when the depth of accumulated water is relatively shallow, the water flow inertia coefficient can be appropriately reduced to reduce the inertial influence of the water flow; while when the depth of accumulated water is relatively deep, the gravity drainage coefficient can be appropriately increased to improve the drainage efficiency. In addition, the drainage flow function can also introduce a dynamic adjustment mechanism to automatically adjust the water flow inertia coefficient and the gravity drainage coefficient according to the depth of accumulated water and the water flow velocity monitored in real time. For example, when the water flow velocity exceeds a certain threshold, the system can automatically reduce the water flow inertia coefficient to avoid the negative impact of water flow inertia on the drainage efficiency. At the same time, the drainage flow function can also combine meteorological data, such as rainfall intensity and rainfall duration, to further optimize the drainage strategy. For example, when the rainfall intensity is relatively large, the system can automatically adjust the reference elevation of the drainage outlet to increase the drainage flow. Through these optimization measures, the drainage flow function can more accurately reflect the actual operating state of the drainage system, thus providing more effective support for the optimized operation of the drainage system.

[0115] In some embodiments, the drainage execution module includes:

[0116] A multi - level linkage unit that calculates the drainage priority based on the real - time water accumulation depth and the water accumulation change rate, and allocates the power of the drainage pump. The priority formula is:

[0117]

[0118] where P represents the drainage priority, ω1 and ω2 represent weight coefficients, D represents the water accumulation depth, represents the water accumulation depth change rate;

[0119] A self - cleaning unit that triggers a reverse water flow to clean the pump body when the cumulative working time exceeds a preset threshold. The cleaning intensity formula is:

[0120]

[0121] where B represents the cleaning intensity, κ represents the dirt adhesion coefficient, T represents the cumulative working time, and D(t) represents the water accumulation depth function that changes with time.

[0122] It should be noted that the drainage execution module includes a multi - level linkage unit and a self - cleaning unit. The multi - level linkage unit calculates the drainage priority according to the real - time water accumulation depth and the water accumulation change rate, and allocates the power of the drainage pump. The drainage priority is a parameter that measures the drainage requirements of different areas, used to optimize the power distribution of the drainage pump to ensure that areas with serious water accumulation are processed first. The self - cleaning unit triggers a reverse water flow to clean the pump body when the cumulative working time of the drainage pump exceeds the preset threshold to keep the equipment clean and extend its service life. The cleaning intensity is a parameter that measures the cleaning effect and is related to the dirt adhesion coefficient, the cumulative working time, and the change in water accumulation depth. These functions together ensure the efficient operation of the drainage system and the long - term stability of the equipment.

[0123] Specifically, in the drainage priority formula of the multi - level linkage unit, the weight coefficients ω1 and ω2 are used to balance the influence of the water accumulation depth and the water accumulation change rate on the priority. The water accumulation depth D directly reflects the current water accumulation situation, and the water accumulation change rate It represents the change rate of the accumulated water depth over time and is used to judge the dynamic trend of the accumulated water. The weight coefficients can be set according to actual needs. For example, in areas where the accumulated water depth changes rapidly, the value of ω2 can be appropriately increased to improve the drainage priority of that area. In the cleaning intensity formula of the self-cleaning unit, the fouling adhesion coefficient κ is a parameter related to the device material and usage environment and is used to describe the degree of fouling adhesion on the device surface. The cumulative working time T is the running time of the device since the last cleaning, and the function D(t) of the accumulated water depth changing with time reflects the change of the accumulated water depth during the operation of the device. The reasonable setting of these parameters can ensure that the self-cleaning unit starts at an appropriate time to maintain the good operation state of the device.

[0124] Preferably, the operation steps of the drainage execution module can be further refined. For example, the multi-level linkage unit can set different weight coefficients according to different accumulated water depth intervals. When the accumulated water depth is relatively shallow (such as less than 10 cm), the weight coefficients ω1 can be set to 0.3 and ω2 to 0.7 to give priority to areas with a higher rate of change of the accumulated water; while when the accumulated water depth is relatively deep (such as greater than 30 cm), the weight coefficients ω1 can be set to 0.7 and ω2 to 0.3 to give priority to areas with a higher accumulated water depth. In addition, the cleaning intensity of the self-cleaning unit can be dynamically adjusted according to the actual operation of the device. For example, when the device is operating at a high load, the cleaning intensity can be appropriately increased to prevent excessive accumulation of dirt. At the same time, the self-cleaning unit can also introduce an intelligent monitoring mechanism to monitor the dirt situation on the device surface in real time. When the degree of fouling adhesion exceeds a certain threshold, the cleaning program is automatically started to further improve the maintenance efficiency of the device. Through these optimization measures, the drainage execution module can more efficiently allocate the power of the drainage pump and ensure the long-term stable operation of the device.

[0125] In some embodiments, the self-checking and fault-tolerant module performs the following operations:

[0126] Calculate the efficiency of the drainage pump in real time, and its efficiency formula is:

[0127]

[0128] where η represents the efficiency of the drainage pump, I represents the current, U represents the voltage, φ represents the power factor angle, and P 额定 represents the rated power of the drainage pump;

[0129] When the efficiency is lower than the preset threshold, generate a device deterioration curve, and its formula is:

[0130] L = 1e kT

[0131] where L represents the degree of device deterioration, k represents the deterioration rate constant, and T represents the running time;

[0132] If the deterioration degree exceeds the threshold, switch to the standby pump.

[0133] It should be noted that the self-check and fault tolerance module is responsible for calculating the efficiency of the drainage pump in real time, and generating an equipment deterioration curve when the efficiency is lower than the preset threshold, so as to timely detect potential faults of the equipment and switch to the standby pump. The efficiency of the drainage pump refers to the ratio of the actual output power of the drainage pump to the rated power, which is calculated by monitoring parameters such as current, voltage and power factor angle. The equipment deterioration degree reflects the decline of equipment performance over time, which is calculated by the deterioration rate constant and the running time. These functions ensure that the drainage system can quickly switch to standby equipment when the equipment fails, thus improving the reliability and stability of the system.

[0134] Specifically, in the calculation formula of the drainage pump efficiency, the current I and voltage U are real-time monitoring parameters during the operation of the drainage pump, and the power factor angle φ reflects the power factor of the circuit. The rated power P 额定 is the nominal power at the time of drainage pump design. These parameters can be obtained in real time through sensors installed on the drainage pump. When the calculated efficiency of the drainage pump is lower than the preset threshold (such as 80%), the system will start to generate the equipment deterioration curve. The deterioration rate constant k is a parameter related to the equipment material and use environment, usually set through historical data and experience. The running time T is the cumulative time from the start of the equipment to the current time. Through these parameters, the system can monitor the health status of the drainage pump in real time and switch to the standby pump when necessary to ensure the continuous operation of the drainage system.

[0135] Preferably, the operation steps of the self-check and fault tolerance module can be further refined. For example, the monitoring of the drainage pump efficiency can be set to be carried out every 5 minutes to ensure timely detection of the efficiency decline. When the efficiency is lower than 80%, the system can automatically start the standby pump and conduct a detailed inspection of the current pump. The generation of the equipment deterioration curve can be adjusted in combination with external conditions such as environmental temperature and humidity, because these factors may affect the equipment deterioration rate. For example, in a high humidity environment, the deterioration rate constant can be appropriately increased. In addition, the system can introduce an intelligent diagnosis function. When the equipment efficiency drops, it can automatically analyze possible reasons such as blockage and wear, and provide corresponding maintenance suggestions. Through these optimization measures, the self-check and fault tolerance module can more effectively monitor the health status of the drainage pump, timely detect and handle potential faults, thereby improving the reliability and operation efficiency of the entire drainage system.

[0136] In some embodiments, the grading logic of the warning module is as follows:

[0137] First-level warning: When the real-time accumulated water depth reaches 70% of the threshold and the accumulated water rate continues to rise, send a preparatory instruction to the municipal terminal;

[0138] Secondary warning: When the real-time water accumulation depth exceeds the threshold and the rainfall intensity reaches the threshold, avoidance information is pushed to the public;

[0139] Tertiary warning: When the real-time water accumulation depth exceeds 130% of the threshold and the drainage efficiency is lower than 50%, activate the dispatching of emergency water pumping vehicles.

[0140] It should be noted that the grading logic of the warning module can generate corresponding warning signals according to different water accumulation depths and rainfall intensities to notify the municipal management department and the public to take corresponding countermeasures. The primary warning is triggered when the water accumulation depth reaches 70% of the threshold and the water accumulation rate continues to rise, notifying the municipal management department to get prepared; the secondary warning is triggered when the water accumulation depth exceeds the threshold and the rainfall intensity reaches the threshold, pushing avoidance information to the public; the tertiary warning is triggered when the water accumulation depth exceeds 130% of the threshold and the drainage efficiency is lower than 50%, activating the dispatching of emergency water pumping vehicles. This grading warning mechanism can issue different levels of alarms in a timely manner according to the severity of water accumulation and the operating status of the drainage system, ensuring that the municipal management department and the public can take effective countermeasures in a timely manner.

[0141] Specifically, the water accumulation depth threshold in the warning module is set based on historical data and experience to judge whether the water accumulation reaches a dangerous level. For example, the water accumulation depth threshold can be set to 10 cm. When the water accumulation depth reaches 7 cm (70%) and the water accumulation rate continues to rise, the primary warning is triggered. The rainfall intensity threshold is set according to local meteorological data, such as 30 mm / h. When the water accumulation depth exceeds 10 cm and the rainfall intensity reaches 30 mm / h, the secondary warning is triggered. The drainage efficiency is calculated by the ratio of the actual output power of the drainage pump to the rated power. When the drainage efficiency is lower than 50%, it indicates that there may be a serious failure in the drainage system. The reasonable setting of these parameters can ensure that the warning module issues accurate warning signals in different situations.

[0142] Preferably, the operation steps of the warning module can be further refined. For example, the primary warning can be set to be triggered when the water accumulation depth reaches 70% of the threshold and continues to rise for more than 10 minutes to avoid false alarms due to short-term water accumulation fluctuations. The secondary warning can combine real-time traffic data to push avoidance information to the public in the affected area and at the same time notify the municipal management department to take temporary traffic control measures. The tertiary warning can be further refined to be triggered when the water accumulation depth exceeds 130% of the threshold and the drainage efficiency is lower than 50% for more than 30 minutes to ensure that the emergency water pumping vehicle has enough time to reach the scene. In addition, the warning module can introduce the Geographic Information System (GIS) to accurately push warning information to the residents and vehicles in the affected area according to the location and scope of the water accumulation. Through these optimization measures, the warning module can more effectively notify the municipal management department and the public and improve the emergency response ability to urban road waterlogging.

[0143] In some embodiments, the interaction module includes:

[0144] A dynamic visualization unit that generates a heat map of accumulated water with a color gradient mapping, and its color mapping formula is:

[0145]

[0146] where C represents the color value, D represents the depth of accumulated water, D max represents the maximum depth of accumulated water, and n represents the non-linear enhancement index;

[0147] A prediction and deduction unit that calculates the future accumulated water range based on the assumed rainfall amount, and its calculation formula is:

[0148]

[0149] where S represents the future accumulated water range, β represents the rainfall absorption rate, R 假设 represents the assumed rainfall amount, γ represents the drainage attenuation factor, Q(D, H) represents the drainage flow function, and T represents time.

[0150] It should be noted that the interaction module is used to display the real-time heat map of accumulated water, the status of drainage equipment, and the predicted accumulated water range, providing intuitive information for the municipal management department and the public. The real-time heat map of accumulated water is a visualization tool that intuitively shows the depth of accumulated water in different regions through color gradients. The status of drainage equipment shows the operating conditions of key equipment such as drainage pumps and valves, helping managers to timely understand whether the equipment is working properly. The predicted accumulated water range is based on current data and model algorithms to predict the areas where water may accumulate in the future, providing a basis for taking preventive measures in advance. The combination of these functions makes the interaction module an important communication bridge between the system and users, improving the transparency and operability of information.

[0151] Specifically, the generation of the real-time heat map of accumulated water depends on the color gradient mapping formula, which converts the depth of accumulated water into color values for intuitive display on the map. For example, light blue can represent areas with relatively shallow accumulated water, while dark red represents areas with relatively deep accumulated water. The non-linear enhancement index is used to adjust the sensitivity of color changes, making the heat map more intuitive and understandable. The status of drainage equipment can be monitored in real time through sensors for key parameters of the equipment, such as current, voltage, and rotational speed, to determine whether the equipment is operating normally. The calculation of the predicted accumulated water range is based on parameters such as the assumed rainfall amount, drainage attenuation factor, and drainage flow function, and predicts the spread of future accumulated water through model algorithms. The reasonable setting and real-time update of these parameters ensure that the interaction module can provide accurate and useful information.

[0152] Preferably, the operation steps of the interaction module can be further refined. For example, the real-time ponding heat map can be combined with a Geographic Information System (GIS) to accurately display the ponding location and depth on an electronic map. The non-linear enhancement index in the color gradient mapping formula can be adjusted according to actual needs to highlight areas with deeper ponding. The display of the drainage equipment status can be enhanced with real-time updates of the equipment health index to provide more comprehensive equipment information for management personnel. The calculation of the predicted ponding range can incorporate more meteorological data, such as wind speed and direction, to more accurately predict the spreading direction of the ponding. In addition, the interaction module can provide a user-defined function that allows the municipal management department to set warning thresholds and display parameters according to different scenarios to meet the needs of different users. Through these optimization measures, the interaction module can more effectively provide decision support for the municipal management department and the public, improving the efficiency and accuracy in dealing with urban road ponding.

[0153] In some embodiments, the data transmission module adopts a hybrid communication protocol:

[0154] In the normal mode, encrypted data packets are transmitted, and the data packet structure is:

[0155] Frame={ID,D,R,I img ,T}

[0156] where ID represents the sensor number, D represents the ponding depth, R represents the rainfall intensity, I img represents the image data, and T represents the timestamp;

[0157] When the signal strength is lower than the threshold, it switches to the backup communication network, and the switching condition is:

[0158]

[0159] where S rssi represents the signal strength, S min represents the minimum signal strength threshold, τ represents the link delay, and τ max represents the maximum link delay threshold.

[0160] It should be noted that the data transmission module adopts a hybrid communication protocol to ensure the stable transmission of data in different network environments. In the normal mode, the data transmission module transmits the monitoring data to the central control module through encrypted data packets to ensure the security and integrity of the data. The encrypted data packets contain key information such as the sensor number, ponding depth, rainfall intensity, image data, and timestamp. When the signal strength is lower than the preset threshold, the data transmission module will automatically switch to the backup communication network to ensure the continuity of data transmission. This hybrid communication mechanism can effectively cope with the complex network conditions in the urban environment, improving the reliability and stability of the system.

[0161] Specifically, in the encrypted data packet structure of the data transmission module, the sensor ID is used to identify different monitoring devices, the water accumulation depth (D) and rainfall intensity (R) are the key data for monitoring, the image data (I) provides visual information of the site, and the timestamp (T) records the data acquisition time. These data are encrypted through an encryption algorithm (such as AES-256) to prevent the data from being stolen or tampered with during transmission. In terms of signal strength monitoring, the signal strength threshold (RSSI min ) and the link delay threshold (Latency max ) are two key parameters. The signal strength threshold is used to determine whether the current network signal is strong enough, and the link delay threshold is used to evaluate the network response speed. For example, the signal strength threshold can be set to -80 dBm, and the link delay threshold can be set to 100 ms. When the signal strength is lower than -80 dBm or the link delay exceeds 100 ms, the system will trigger the network switching mechanism.

[0162] Preferably, the operation steps of the data transmission module can be further refined. For example, the encryption algorithm of the encrypted data packet can be updated according to the latest security standards to cope with the ever-changing network security threats. In terms of signal strength monitoring, more advanced signal quality evaluation algorithms can be introduced, such as comprehensively evaluating by combining signal strength and bit error rate (BER), to more accurately judge the network quality. The selection of the backup communication network can be more flexible. For example, when the 4G signal is poor, it can automatically switch to the 5G network, or when the wireless network is unavailable, it can switch to the wired network. In addition, the data transmission module can add a data redundancy mechanism, such as sending a check code to detect and correct transmission errors, further improving the reliability of data transmission. Through these optimization measures, the data transmission module can more effectively cope with complex network environments, ensure the stable transmission of monitoring data, and provide a solid guarantee for the normal operation of the entire system.

[0163] In some embodiments, the monitoring module includes:

[0164] A multi-spectral imaging unit that identifies foreign objects on the water surface through the reflection intensity ratio, and its foreign object probability formula is:

[0165]

[0166] where P 异物 represents the probability of the presence of foreign objects, w λ represents the weights of different bands, I λ represents the reflection intensity of the current band, and I λ0 represents the reference reflection intensity of the clean water surface in this band.

[0167] It should be noted that the multispectral imaging unit in the monitoring module is used to identify foreign objects on the water surface by the reflection intensity ratio, thereby improving the comprehensiveness and accuracy of monitoring. The multispectral imaging unit is an advanced imaging technology that differentiates and identifies objects based on the reflection intensities of light in different bands. Foreign objects on the water surface refer to any objects floating on the water surface, such as garbage, branches, etc. These foreign objects may affect the normal operation of the drainage system. The reflection intensity ratio refers to the proportional relationship between the reflection intensities of light in different bands. By analyzing this ratio, the nature of the object can be determined. This technology can help the system detect and handle potential drainage obstacles in a timely manner, ensuring the efficient operation of the drainage system.

[0168] Specifically, the working principle of the multispectral imaging unit is based on the reflection characteristics of light in different bands for different substances. For example, the reflection intensity of a clean water surface is relatively low in some bands (such as the near-infrared band), while that of foreign objects (such as plastic garbage or leaves) is relatively high in these bands. By setting the weights w λ of different bands, and measuring the reflection intensity I λ of the current band, the probability P 异物 of the presence of foreign objects can be calculated. The weight w λ can be adjusted according to the actual application scenario to improve the accuracy of identification. For example, in an urban environment, the weight of the visible light band can be increased because urban garbage usually has a strong reflection in these bands. The reference reflection intensity I λ0 is the reflection intensity of a clean water surface in different bands, which is obtained through experiments or historical data. When the calculated probability of the presence of foreign objects exceeds a certain threshold (such as 0.7), the system can determine that there are foreign objects in this area and issue an alarm or take corresponding cleaning measures.

[0169] Preferably, the operation steps of the multispectral imaging unit can be further refined. For example, more bands can be added for monitoring to improve the accuracy of foreign object identification. In addition to the common visible light and near-infrared bands, the ultraviolet band or the thermal infrared band can also be introduced to identify different types of foreign objects. Furthermore, machine learning algorithms can be combined to automatically identify and classify foreign object types through training models, thereby improving the intelligence level of the system. For example, using a convolutional neural network (CNN) to analyze multispectral images can more accurately identify the shape and material of foreign objects. At the same time, the foreign object database can be updated regularly to adapt to the changes in foreign objects in different seasons and environments. Through these optimization measures, the multispectral imaging unit can more effectively identify foreign objects on the water surface and provide a more reliable guarantee for the normal operation of the drainage system.

[0170] The above embodiments of the present invention have the following beneficial effects: The urban road waterlogging monitoring and drainage system of the present invention can collect road waterlogging depth, water flow velocity, rainfall intensity and on-site image data in real time, and encrypt and transmit them to the central control module through a wireless communication network. The system can build a three-dimensional waterlogging diffusion model based on these data, predict the waterlogging depth and optimize the drainage strategy, so as to dynamically adjust the power of the drainage pump and the drainage path. This intelligent monitoring and control method can improve the operation efficiency of the urban road drainage system, reduce the waterlogging risk, and ensure the smoothness of urban traffic and the safety of residents' travel.

[0171] In addition, the system also has self-checking and fault-tolerant functions, can calculate the health index of drainage equipment in real time, and automatically switch to redundant equipment when the equipment fails, ensuring the stable operation of the drainage system. The early warning module can generate multi-level warning signals according to the waterlogging depth and rainfall intensity, and timely release risk information to the municipal management department and the public, further enhancing the city's emergency response ability to extreme weather. The interaction module can display the real-time waterlogging heat map and the status of drainage equipment, providing an intuitive reference for municipal management and public travel. The comprehensive application of these functions can effectively improve the intelligent management level of urban infrastructure and provide strong support for the sustainable development of the city.

[0172] The initialization configuration module can dynamically adjust the waterlogging depth threshold to meet the waterlogging monitoring requirements under different rainfall conditions. At the same time, it corrects the waterlogging depth data through the temperature compensation formula to improve the monitoring accuracy. The model algorithm optimization module uses a spatio-temporal convolutional neural network to predict the waterlogging depth in the future period. When the predicted value exceeds the threshold, it can automatically adjust the drainage attenuation factor to optimize the drainage strategy. The drainage execution module can calculate the drainage priority according to the real-time waterlogging depth and its change rate, reasonably allocate the power of the drainage pump, and has a self-cleaning function to extend the service life of the equipment. The self-check and fault tolerance module can calculate the efficiency of the drainage pump in real time and generate a device deterioration curve. When the degree of deterioration exceeds the threshold, it will switch to the standby pump in time to ensure the reliability of the drainage system. The grading logic of the early warning module can push corresponding early warning information to the municipal terminal and the public according to different waterlogging conditions and rainfall intensities, improving the pertinence and effectiveness of the early warning. The dynamic visualization unit of the interaction module can generate a waterlogging heat map with color gradient mapping to intuitively display the waterlogging distribution. The prediction and deduction unit can calculate the future waterlogging range according to the assumed rainfall amount, providing a scientific basis for municipal management and public travel. The data transmission module uses a hybrid communication protocol and automatically switches to the standby communication network when the signal strength is low to ensure the stability and reliability of data transmission. The multi-spectral imaging unit of the monitoring module can identify foreign objects on the water surface through the reflection intensity ratio, further improving the comprehensiveness and accuracy of the monitoring. These specific technical improvements and optimization measures can jointly improve the overall performance and practicality of the system, enabling it to better cope with the urban road waterlogging problem and ensuring the safety and convenience of urban traffic and residents' lives.

[0173] Furthermore, the storage medium of the embodiment of the present application stores program instructions capable of implementing all the above methods. Among them, the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0174] The above description is only some preferred embodiments of the present invention and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the embodiments of the present invention.

Claims

1. An urban road waterlogging monitoring and drainage system, characterized in that, Including: A monitoring module for real-time collection of road waterlogging depth, water flow velocity, rainfall intensity, and on-site image data; An initialization configuration module for setting the waterlogging depth threshold, rainfall intensity threshold, sensor calibration parameters, and drainage equipment operation parameters of the road area; A data transmission module for encrypting and transmitting the road waterlogging depth, water flow velocity, rainfall intensity, and on-site image data to the central control module through a wireless communication network; A model algorithm optimization module for constructing a three-dimensional waterlogging diffusion model based on the road waterlogging depth, terrain elevation, and drainage pipe network topology data, and outputting the predicted waterlogging depth and optimized drainage strategy; A central control module for generating drainage pump speed commands, valve control commands, and multi-level warning signals based on the predicted waterlogging depth; A drainage execution module for dynamically adjusting the drainage pump power and drainage path according to the speed command and valve control command; A self-check and fault tolerance module for calculating the health index of drainage equipment in real time and switching redundant equipment when the index is abnormal; A warning module for sending risk level information to the municipal management terminal and public mobile terminals according to the multi-level warning signals; An interaction module for displaying real-time waterlogging heat maps, drainage equipment status, and predicted waterlogging ranges.

2. The urban road waterlogging monitoring and drainage system according to claim 1, characterized in that The initialization configuration module includes: A parameter adaptive unit for dynamically adjusting the waterlogging depth threshold, and its threshold calculation formula is: D th = μD max + σR avg Among them, D th represents the accumulated water depth threshold, μ represents the depth correction coefficient, D max represents the historical maximum accumulated water depth, σ represents the rainfall weight coefficient, R avg represents the regional average rainfall intensity; A sensor calibration unit for correcting the waterlogging depth data through a temperature compensation formula, and its calibration formula is: D 校准 = D 原始 (1 + ∈ΔT) Among them, D 校准 represents the calibrated accumulated water depth, D 原始 represents the original measured value of the accumulated water depth, ∈ represents the temperature compensation coefficient, and ΔT represents the change in ambient temperature.

3. The urban road waterlogging monitoring and drainage system according to claim 1, characterized in that, The model algorithm optimization module performs the following steps: S1. Input the real-time road waterlogging depth, terrain elevation, and drainage pipe network flow upper limit, and construct a three-dimensional waterlogging diffusion partial differential equation: where D represents the depth of accumulated water, t represents time, α represents the diffusion coefficient, represents the Laplace operator, β represents the rainfall absorption rate, R(t) represents the rainfall intensity function varying with time, γ represents the drainage attenuation factor, Q(D,H) represents the drainage flow function, and H represents the current water level elevation; S2. Based on the partial differential equation, use a spatio-temporal convolutional neural network to predict the water accumulation depth in the future Δt period and output the predicted value D 预测 , and the input features of the spatio-temporal convolutional neural network include the water accumulation depth D, rainfall intensity R(t), and drainage flow Q(D, H) in the partial differential equation; S3. When the predicted value exceeds the waterlogging depth threshold, adjust the drainage attenuation factor, and the update formula is: Among them, γ 新 represents the new drainage attenuation factor, γ 旧 represents the old drainage attenuation factor, λ represents the feedback gain coefficient, D 预测 represents the predicted ponding depth, D th represents the ponding depth threshold.

4. The urban road waterlogging monitoring and drainage system according to claim 3, characterized in that, The drainage flow function Q(D,H) is defined as: Q = K1D 2 sinθ + K2(H0 - H)D Where Q represents the drainage flow, K1 represents the water flow inertia coefficient, D represents the waterlogging depth, θ represents the road slope angle, K2 represents the gravity drainage coefficient, H0 represents the drainage outlet reference elevation, and H represents the current water level elevation.

5. The urban road waterlogging monitoring and drainage system according to claim 1, characterized in that, The drainage execution module includes: A multi-level linkage unit for calculating the drainage priority according to the real-time waterlogging depth and waterlogging change rate, and allocating the drainage pump power, and its priority formula is: Wherein, P represents the drainage priority, ω1 and ω2 represent weight coefficients, D represents the depth of accumulated water, represents the change rate of the depth of accumulated water; A self-cleaning unit for triggering reverse water flow to clean the pump body when the cumulative working time exceeds a preset threshold, and its cleaning intensity formula is: Where B represents the cleaning intensity, κ represents the dirt adhesion coefficient, T represents the cumulative working time, and D(t) represents the waterlogging depth function that changes with time.

6. The urban road waterlogging monitoring and drainage system according to claim 1, characterized in that, The self-check and fault tolerance module performs the following operations: Calculate the drainage pump efficiency in real time, and its efficiency formula is: Among them, η represents the drainage pump efficiency, I represents the current, U represents the voltage, φ represents the power factor angle, and P 额定 represents the rated power of the drainage pump; When the efficiency is lower than the preset threshold, generate an equipment deterioration curve, and its formula is: L = 1e kT Where L represents the equipment deterioration degree, k represents the deterioration rate constant, and T represents the operation time; If the deterioration degree exceeds the threshold, switch to the standby pump.

7. The urban road waterlogging monitoring and drainage system according to claim 1, characterized in that, The grading logic of the warning module is: Level 1 warning: When the real-time waterlogging depth reaches 70% of the threshold and the waterlogging rate continues to rise, send a preparatory command to the municipal terminal; Level 2 warning: When the real-time waterlogging depth exceeds the threshold and the rainfall intensity reaches the threshold, push avoidance information to the public; Level 3 Early Warning: When the real-time water accumulation depth exceeds 130% of the threshold and the drainage efficiency is lower than 50%, activate the emergency pumping vehicle scheduling.

8. The urban road waterlogging monitoring and drainage system according to claim 1, characterized in that, The interaction module includes: A dynamic visualization unit that generates a heat map of water accumulation with a color gradient mapping, and its color mapping formula is: Among them, C represents the color value, D represents the water accumulation depth, D max represents the maximum water accumulation depth, and n represents the non-linear enhancement index; The prediction and deduction unit calculates the future waterlogging range based on the assumed rainfall, and its calculation formula is: Among them, S represents the future waterlogging range, β represents the rainfall absorption rate, R 假设 represents the assumed rainfall, γ represents the drainage attenuation factor, Q(D, H) represents the drainage flow function, and T represents time.

9. The urban road waterlogging monitoring and drainage system according to claim 1, characterized in that, The data transmission module uses a hybrid communication protocol: Transmit encrypted data packets in the normal mode, and its data packet structure is: Frame={ID,D,R,I img ,T} Among them, ID represents the sensor number, D represents the accumulated water depth, R represents the rainfall intensity, I img represents the image data, and T represents the timestamp; When the signal strength is lower than the threshold, switch to the backup communication network, and its switching condition is: Among them, S rssi represents the signal strength, S min represents the minimum signal strength threshold, τ represents the link delay, τ max represents the maximum link delay threshold.

10. The urban road waterlogging monitoring and drainage system according to claim 1, wherein The monitoring module includes: A multi-spectral imaging unit that identifies foreign objects on the water surface through the reflection intensity ratio, and its foreign object probability formula is: Among them, P 异物 represents the probability of foreign object presence, w λ represents the weights of different bands, I λ represents the reflection intensity of the current band, and I λ0 represents the reference reflection intensity of the clean water surface in this band.

Images