Airport roof rainwater treatment monitoring system and method based on cloud computing

Abstract

The invention discloses an airport roof rainwater treatment monitoring system and method based on cloud computing, relates to the technical field of rainwater monitoring, and solves the technical problems that under extreme weather conditions such as rainstorm, a traditional drainage system is difficult to drain roof accumulated water quickly, accumulated water flooding may be caused, and normal operation of an airport is affected. The rainfall of the target area is predicted; determining a drainage pipeline combination according to the rainfall of the target area; obtaining the content of each element in the rainwater, and analyzing the water quality index of the rainwater; evaluating the pollution level of the rainwater based on the water quality index; based on the pollution level of the rainwater, different water qualities are conveyed to the corresponding reservoirs; based on the pollution level of the rainwater, different water quality is conveyed to the corresponding filter tanks; the device can quickly and effectively disperse and drain accumulated water on the roof, so that the pressure of the accumulated water on an airport building structure is reduced, and the service life of a building is prolonged.

Description

Technical Field

[0001] The present invention belongs to the field of rainwater monitoring, and in particular relates to an airport roof rainwater treatment monitoring system and method based on cloud computing. Background Art

[0002] With the intensification of global climate change and the rapid advancement of urbanization, airports, as important transportation hubs connecting the world, are facing unprecedented challenges in the safety and sustainability of their infrastructure, especially the airport's roof drainage and rainwater treatment systems. As a key link to ensure the normal operation of the airport, the optimization and upgrading of its performance is particularly important.

[0003] Traditional rainwater treatment systems, limited by technical level and design concepts, often have the problem of low drainage efficiency. Under extreme weather conditions such as heavy rain, traditional drainage systems are difficult to quickly drain water from the roof, which may cause flooding, affecting the normal operation of the airport and even causing damage to the airport building structure. In addition, due to limited monitoring methods, traditional systems often cannot capture abnormal conditions in the rainwater treatment process in a timely manner, such as water quality deterioration and pipe blockage, which further increases the risk of airport operations.

[0004] Therefore, the present invention provides an airport roof rainwater treatment monitoring system and method based on cloud computing. 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 airport roof rainwater treatment monitoring system and method based on cloud computing, which is used to solve the technical problem that under extreme weather conditions such as heavy rain, the traditional drainage system is difficult to quickly drain the roof water, which may cause flooding and thus affect the normal operation of the airport.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides an airport roof rainwater treatment monitoring system and method based on cloud computing, including a rainwater quality analysis module, and a rainfall prediction module and a rainwater treatment module connected thereto;

[0007] Rainfall prediction module: used to predict the rainfall in the target area; determine the drainage pipe combination according to the rainfall in the target area; the target area is the airport area where rainwater monitoring is carried out;

[0008] Rainwater quality analysis module: used to obtain the content of each element in rainwater, analyze the water quality index of rainwater; evaluate the pollution level of rainwater based on the water quality index;

[0009] Rainwater treatment module: used to transport different water qualities to corresponding reservoirs based on the pollution level of rainwater; and, to transport different water qualities to corresponding filtration tanks based on the pollution level of rainwater.

[0010] Preferably, the predicted airport rainfall conditions in the target area include:

[0011] Extract meteorological data and corresponding actual rainfall at different times of the target area from historical data to establish a rainfall database for the target area; the meteorological data is the input data of the neural network model, and the actual rainfall corresponding to the meteorological data is the output data of the neural network model;

[0012] The neural network model is trained through input data and output data to obtain a rainfall prediction model;

[0013] Collect future meteorological data of the target area, input the future meteorological data into the rainfall prediction model, and output the rainfall prediction value of the target area in the future time period.

[0014] The present invention collects and organizes the past meteorological data and rainfall of the target area to establish a rich database, which provides a solid foundation for the training of the neural network model, helps the model learn the complex relationship between meteorological data and rainfall, and thus improves the accuracy of the prediction; and the neural network model has a strong nonlinear fitting ability. By learning and training the input data, the model can capture the nonlinear relationship between meteorological data and rainfall, and thus achieve accurate prediction of future rainfall.

[0015] Preferably, the rainfall prediction value output by the neural network model and the corresponding actual rainfall are constructed into two sets of sequences with the same length, and the formula Calculate the mean square error (MSE) between the two sets of sequences; determine whether the mean square error is greater than the preset threshold; if yes, optimize the neural network model; if no, end the training of the neural network model; where j is the element number of the sequence, j = 0, 1, ..., M, M is a positive integer, y j is the actual rainfall, Forecast rainfall forecast value.

[0016] The present invention measures the gap between actual data and predicted data through mean square error, that is, the degree of deviation of the overall model predicted data relative to the overall actual data. Comparing MSE with a preset threshold can be used as an effective model optimization strategy; when MSE is greater than the threshold, it means that the model's prediction performance is poor and needs further optimization; the feedback mechanism based on MSE helps to ensure the accuracy and reliability of the model.

[0017] Preferably, determining the drainage pipe combination according to the rainfall in the target area includes:

[0018] Based on the predicted rainfall value of the target area in the future time period, the predicted rainfall value per unit time is calculated;

[0019] Obtain the cross-sectional area and maximum flow velocity of the drainage pipe and calculate the maximum flow rate of the pipe;

[0020] The standard delivery flow of the drainage pipe is compared with the predicted value of rainfall per unit time to obtain the required number of drainage pipes, which is marked as G; wherein, the standard delivery flow of the drainage pipe is the product of the standard opening of the drainage pipe and the maximum delivery flow of the drainage pipe; the maximum delivery flow of the drainage pipe is the product of the cross-sectional area of ​​the drainage pipe and the maximum flow velocity;

[0021] The average usage frequency PL of N drainage pipes with a degree greater than the standard opening is calculated by the formula PL=min[Σ(Rki / STi) / N]; the drainage pipe combination with the lowest usage frequency is the drainage pipe combination that needs to be opened; wherein k is the standard opening; i is the pipe number, i=0, 1,…, N, N is a positive integer; STi is the duration of use of pipe i from the beginning of use to the current time; Ri is the number of times pipe i uses the standard opening during the STi period.

[0022] The present invention can realize the reasonable allocation of drainage resources by calculating the predicted value of rainfall per unit time and determining the required number of drainage pipes accordingly. This method can ensure that there are enough drainage pipes in operation when the rainfall is large, and avoid unnecessary waste of resources when the rainfall is small. This dynamic configuration strategy helps to improve the overall efficiency and economic benefits of the drainage system. The frequency of use and life of the drainage pipes are also taken into account; by calculating the average frequency of use of the drainage pipes greater than the standard opening, the pipe combination with the lowest frequency of use and the longest life can be identified as the drainage pipe that needs to be opened first. This strategy helps to extend the service life of the drainage pipes, reduce the cost of maintenance and replacement, and ensure the stability and reliability of the drainage system.

[0023] Preferably, each roof of the airport is provided with a number of drainage pipes of the same specification, and the number of drainage pipes on each roof of the airport is set based on the standard delivery flow of the drainage pipes and the maximum rainfall in the airport's historical data.

[0024] Preferably, the standard opening of the drainage pipe includes:

[0025] A digital twin model of the airport drainage pipes was established, and several groups of different rainfalls were set. Each group of rainfall was transported by drainage pipes with different openings. After repeated experiments, the service life of the drainage pipes under different rainfalls and openings was obtained. The service life of the drainage pipes under different rainfalls with the same opening was averaged to obtain the average service life of the drainage pipes at this opening.

[0026] The average usage time of each opening is compared, and the opening corresponding to the largest average usage time is the standard opening of the drainage pipe; among which, the usage time of the drainage pipe under different openings at different rainfall amounts is the time from the beginning of the drainage pipe's work to the time when it stops working normally.

[0027] The present invention can accurately simulate the working state of the drainage pipe under different rainfall and openings by constructing a digital twin model that corresponds to the physical drainage pipe system, which helps to understand the actual working conditions of the drainage pipe and provide strong support for subsequent optimization decisions; and through repeated experiments and data analysis, the use time of the drainage pipe under different conditions can be obtained, and then the standard opening can be determined. This process fully considers the impact of rainfall and pipe opening on the working state of the drainage pipe, ensures the rationality of the standard opening, and makes the drainage pipe work longer.

[0028] Preferably, obtaining the content of each element in rainwater and analyzing the water quality index of rainwater includes:

[0029] Collect several rainwater samples, detect the content of each element in several rainwater samples, and perform mean processing to obtain the content of each element in the rainwater in the target area;

[0030] The content of each element in the rainwater is processed by the difference between the preset standard threshold of the corresponding element content, and the difference is processed by the ratio of the corresponding preset threshold to obtain the deviation rate of the element relative to the preset threshold, marked as Yr; through the formula SZ = e Σ(Yr-Br) The water quality index SZ of rainwater is calculated; wherein Br is the preset threshold, r is the number of each element contained in the rainwater, and Σ sums r.

[0031] The present invention compares the content of each element in rainwater with the corresponding preset standard threshold value, which can intuitively reflect the exceeding or reaching degree of the content of each element; through difference processing and ratio processing, the deviation rate of each element relative to the preset threshold value is obtained. This indicator can quantitatively express the degree of deviation of the content of each element, and the comprehensive influence of the water quality index is obtained through the analysis of the deviation rate of each element, so that the water quality index can comprehensively reflect the overall water quality of rainwater.

[0032] Preferably, the rainwater pollution level assessment based on the water quality index includes:

[0033] Compare the water quality index of rainwater with the preset range; if the water quality index is greater than the preset range, the rainwater pollution level is level one; if the water quality index is within the preset range, the rainwater pollution level is level two; if the water quality index is less than the preset range, the rainwater pollution level is level three; among which, pollution level one>level two>level three.

[0034] Preferably, the method of delivering different water qualities to corresponding filter pools based on the pollution level of rainwater includes:

[0035] The inlet valve of the corresponding filter pool is opened according to the pollution level of the rainwater, and the filter pool adjusts the filter medium and the corresponding ratio of the filter pool in real time according to the content of each element in the rainwater.

[0036] Preferably, the second aspect of the present invention proposes an airport roof rainwater treatment monitoring method based on cloud computing, comprising the following steps:

[0037] Step 1: Predict the rainfall in the target area; determine the drainage pipe combination according to the rainfall in the target area;

[0038] Step 2: Obtain the content of each element in rainwater and analyze the water quality index of rainwater; evaluate the pollution level of rainwater based on the water quality index;

[0039] Step 3: transporting different water qualities to corresponding water reservoirs based on the pollution level of rainwater; and transporting different water qualities to corresponding filtration tanks based on the pollution level of rainwater.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. The present invention accurately predicts the rainfall per unit time and reasonably allocates drainage resources to ensure that there are enough pipes in operation during the peak rainfall period to effectively meet the drainage needs; when the rainfall is less, it can avoid excessive use of pipes and achieve resource conservation and optimization; and considers the service life of drainage pipes, identifies those pipe combinations with relatively low usage frequency and long remaining life, and takes them as the priority objects to be opened, which not only helps to balance the use load of each pipe, but also prolongs the service life of the overall pipe system;

[0042] 2. The present invention simulates the operation of drainage pipes under different rainfall intensities and opening settings. After multiple experiments and detailed data analysis processes, the present invention can accurately measure the operation duration of drainage pipes under different combinations of rainfall intensities and opening degrees, and accordingly determine an optimal pipe opening degree, i.e., the standard opening degree. The present invention comprehensively considers the direct impact of rainfall changes and the pipe opening state on drainage efficiency, thereby ensuring the scientificity and rationality of the selected standard opening degree. With this standard opening degree, the drainage pipe can maintain a longer stable operation time under various conditions, effectively improving its working efficiency and service life.

[0043] 3. The present invention predicts the rainfall in the target area; determines the combination of drainage pipes according to the rainfall in the target area; obtains the content of each element in the rainwater and analyzes the water quality index of the rainwater; evaluates the pollution level of the rainwater based on the water quality index; transports different water qualities to corresponding reservoirs based on the pollution level of the rainwater; and, according to the pollution level of the rainwater, analyzes the filtration scheme of the filtration pool; the present invention not only improves the efficiency and response speed of the drainage system, effectively disperses and quickly removes roof water, reduces the structural load caused by water accumulation, thereby extending the service life of the airport building, but also realizes the rational use of rainwater and pollution control. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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.

[0045] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0046] Figure 2 A schematic diagram of a method for determining a combination of drainage pipes according to rainfall in a target area according to the present invention;

[0047] Figure 3 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0048] 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, not 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.

[0049] See also Figure 1 , the first aspect of the present invention provides an airport rooftop rainwater treatment monitoring system and method based on cloud computing, including a rainwater quality analysis module, and a rainfall prediction module and a rainwater treatment module connected thereto;

[0050] The rainfall prediction module predicts the rainfall in the target area; wherein the target area is the airport area where rainwater monitoring is performed;

[0051] Specifically, the meteorological data and the corresponding actual rainfall at several different times of the target area are extracted from the historical data to establish a rainfall database for the target area; wherein the meteorological data is the input data of the neural network model, and the actual rainfall corresponding to the meteorological data is the output data of the neural network model;

[0052] The neural network model is trained through input data and output data to obtain a rainfall prediction model;

[0053] Collect future meteorological data of the target area, input the future meteorological data into the rainfall prediction model, and output the rainfall prediction value of the target area in the future time period.

[0054] For example: obtain historical meteorological data of an airport from the meteorological department, including date, temperature, humidity, wind speed, wind direction, air pressure, cloud cover, etc.; at the same time, obtain the actual rainfall data corresponding to these dates; match the meteorological data and rainfall data according to the date to ensure that each meteorological data point has corresponding rainfall; fill in missing values ​​(such as using interpolation) or delete them to ensure data integrity.

[0055] Select a neural network model, such as a multi-layer perceptron (MLP); input layer: the dimensions of meteorological data, i.e., the number of features such as temperature, humidity, wind speed, wind direction, air pressure, and cloud cover; hidden layer: set one or more layers as needed, each layer contains a certain number of neurons, and uses activation functions such as ReLU; output layer: one neuron, used to output the predicted rainfall; train the neural network model with historical data to obtain a rainfall prediction model;

[0056] After the model is successfully trained, obtain future weather data: obtain Beijing's weather data for the next week from the weather forecast, including temperature, humidity, wind speed, wind direction, air pressure, cloud cover, etc. Precipitation prediction: input the weather data for the next week into the trained rainfall prediction model; the model outputs the predicted rainfall value for each day of the next week.

[0057] The rainfall prediction value output by the neural network model and the corresponding actual rainfall are constructed into two sequences of the same length, and the formula Calculate the mean square error (MSE) between the two sets of sequences; determine whether the mean square error is greater than the preset threshold; if yes, optimize the neural network model; if no, end the training of the neural network model; where j is the element number of the sequence, j = 0, 1, ..., M, M is a positive integer, y j is the actual rainfall, Forecast rainfall forecast value.

[0058] For example, if the actual rainfall data (unit: mm) at an airport over a period of time is: [10, 15, 20, 25, 30, 35, 40], the corresponding predicted rainfall data (unit: mm) is: [12, 13, 18, 27, 32, 36, 38];

[0059] MSE actual = (1 / 7) × [(10-12)2 + (15-13)2 + (20-18)2 + (25-27)2 + (30-32)2 + (35-36)2 + (40-38)2] ≈ 3.5;

[0060] Assume that the preset MSE threshold is 4 (this value can be adjusted according to actual conditions): Therefore, the difference between the predicted results and the actual results is within an acceptable range, and there is no need to optimize the neural network model.

[0061] and, determining the combination of drainage pipes based on the rainfall in the target area;

[0062] See also Figure 2 ,Specifically, based on the rainfall prediction value of the target area in the future time period, the rainfall prediction value per unit time is calculated;

[0063] Obtain the cross-sectional area and maximum flow rate of the drainage pipe and calculate the maximum flow rate of the pipe; the cross-sectional area and maximum flow rate can be obtained from the specification of the drainage pipe;

[0064] The standard delivery flow of the drainage pipe is compared with the predicted value of rainfall per unit time to obtain the required number of drainage pipes, which is marked as N; wherein, the standard delivery flow of the drainage pipe is the product of the standard opening of the drainage pipe and the maximum delivery flow of the drainage pipe; the maximum delivery flow of the drainage pipe is the product of the cross-sectional area of ​​the drainage pipe and the maximum flow velocity;

[0065] Among them, a digital twin model of the airport drainage pipe is established, and several groups of different rainfalls are set. Each group of rainfall is transported by drainage pipes with different openings. After repeated experiments, the usage time of the drainage pipes under different rainfalls and different openings is obtained, and the usage time under the same opening and different rainfalls is averaged to obtain the average usage time of the drainage pipe at this opening. The mean usage time of each opening is compared, and the opening corresponding to the largest mean usage time is the standard opening of the drainage pipe; among them, the usage time of the drainage pipe under different rainfalls and different openings is the time from the beginning of the drainage pipe working to the time when it cannot work normally.

[0066] The present invention installs sensors on the drainage pipes to collect real-time data such as water level, flow, and water quality in the pipes. The information from sensors, historical databases, and other relevant data sources is integrated to build a unified data platform. According to the characteristics of the drainage pipes and the collected data, a high-precision three-dimensional model or simulation model is constructed. The model should be able to simulate the behavior and state of water flow in the pipe under different rainfall amounts. By comparing the actual data with the model prediction results, the model parameters are continuously adjusted and optimized to improve the model accuracy;

[0067] Set up the experiment and collect data: Set several different sets of rainfall, each set of rainfall represents a different rainfall intensity;

[0068] Adjust the pipe opening: for each group of rainfall, set different drainage pipe openings for transportation;

[0069] The average working time under different rainfall conditions is selected, and the longest working opening is the standard opening of the drainage pipe, that is, the opening that can meet the drainage demand and cause less damage to the drainage pipe.

[0070] The average usage frequency PL of N drainage pipes with a degree greater than the standard opening is calculated by the formula PL=min[Σ(Rki / STi) / N]; the drainage pipe combination with the lowest usage frequency is the drainage pipe combination that needs to be opened; wherein k is the standard opening; i is the pipe number, i=0, 1,…, N, N is a positive integer; STi is the duration of use of pipe i from the beginning of use to the current time; Ri is the number of times pipe i uses the standard opening during the STi period.

[0071] The optimal solution for the frequency of use of drainage pipes is obtained through an iterative algorithm.

[0072] The present invention determines the number of drainage pipes to be opened according to the standard delivery flow of the drainage pipe and the predicted value of rainfall per unit time. It is assumed that X drainage pipes are needed for a certain prediction; X drainage pipes are randomly selected from N drainage pipes to obtain a plurality of drainage pipe combination schemes; the use frequency of each drainage pipe combination is analyzed; the number of times the standard opening is used for each drainage pipe in the combination within the use time is counted, and the number of times the standard opening is used is averaged with the use time to obtain the use frequency of each drainage pipe, and then divided by X to obtain the average use frequency of the standard opening of each pipe in the drainage pipe combination;

[0073] The smaller the average frequency of using the standard opening, the lower the frequency of using the drainage pipes at a larger opening than the standard, which causes less wear on the drainage pipes and thus a longer service life, and they can continue to be used; the larger the average frequency of using the standard opening, the higher the frequency of using the standard opening, the higher the frequency of using the drainage pipes at a smaller opening than the standard, which causes more wear on the drainage pipes and thus a shorter service life, and they cannot be used frequently and require regular maintenance.

[0074] It should be noted that each roof of the airport is equipped with several drainage pipes of the same specifications, and the number of drainage pipes on each roof of the airport is set based on the standard delivery flow of the drainage pipes and the maximum rainfall in the airport's historical data.

[0075] The rainwater quality analysis module obtains the content of each element in the rainwater and analyzes the water quality index of the rainwater; based on the water quality index, the pollution level of the rainwater is evaluated;

[0076] Among them, the elements of rainwater include pH value, trace elements (such as lead, copper, zinc, etc.), dissolved gases (such as CO2, SO2, etc.), etc.

[0077] Specifically, a number of rainwater samples are collected, the content of each element in the rainwater samples is detected, and mean processing is performed to obtain the content of each element in the rainwater in the target area;

[0078] The content of each element in the rainwater is processed by the difference between the preset standard threshold of the corresponding element content, and the difference is processed by the ratio of the corresponding preset threshold to obtain the deviation rate of the element relative to the preset threshold, marked as Yr; through the formula SZ = e Σ(Yr-Br) The water quality index SZ of rainwater is calculated; wherein Br is the preset threshold, r is the number of each element contained in the rainwater, and Σ sums r.

[0079] Compare the water quality index of rainwater with the preset range; if the water quality index is greater than the preset range, the rainwater pollution level is level one; if the water quality index is within the preset range, the rainwater pollution level is level two; if the water quality index is less than the preset range, the rainwater pollution level is level three; among which, pollution level one>level two>level three.

[0080] The present invention evaluates the pollution degree of rainwater through the water quality index; the pollution degree of rainwater is mainly closely related to the deviation rate of the content of each element in the rainwater relative to the preset standard threshold value. When there are more elements in the rainwater and the deviation rate is larger, it indicates that there are a large number of elements exceeding the standard in the rainwater, the rainwater is seriously polluted, and the water quality is poor, that is, the water quality index of the rainwater is larger.

[0081] The rainwater treatment module delivers different water qualities to corresponding water reservoirs based on the pollution level of the rainwater; and delivers different water qualities to corresponding filtration tanks based on the pollution level of the rainwater;

[0082] Specifically, the inlet valve of the corresponding filter pool is opened according to the pollution level of the rainwater, and the filter pool adjusts the filter medium and the corresponding ratio of the filter pool in real time according to the content of each element in the rainwater.

[0083] During the filtration process, the system will automatically select the most suitable filtration media according to the real-time content of each element in the rainwater. These media may include activated carbon, sand, quartz sand, resin, special alloys, etc., each of which has different removal effects on different pollutants.

[0084] In addition to selecting the media, the system will also adjust the ratio of the media according to the specific composition of the rainwater. For example, if the rainwater contains a high content of heavy metals, the system may increase the proportion of media that has a stronger adsorption capacity for heavy metals.

[0085] As the composition of rainwater changes, the type and ratio of filter media will also change accordingly to ensure the best filtration effect.

[0086] See also Figure 3 The second aspect of the present invention provides an airport roof rainwater treatment monitoring method based on cloud computing, comprising the following steps:

[0087] Step 1: Predict the rainfall in the target area; determine the drainage pipe combination according to the rainfall in the target area;

[0088] Step 2: Obtain the content of each element in rainwater and analyze the water quality index of rainwater; evaluate the pollution level of rainwater based on the water quality index;

[0089] Step 3: transporting different water qualities to corresponding water reservoirs based on the pollution level of rainwater; and transporting different water qualities to corresponding filtration tanks based on the pollution level of rainwater.

[0090] 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.

[0091] 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. The airport roof rainwater treatment monitoring system based on cloud computing is characterized by: It includes a rainwater quality analysis module, as well as a rainfall prediction module and a rainwater processing module connected thereto; Rainfall prediction module: used to predict the rainfall in the target area; determine the drainage pipe combination according to the rainfall in the target area; the target area is the airport area where rainwater monitoring is carried out; Rainwater quality analysis module: used to obtain the content of each element in rainwater, analyze the water quality index of rainwater; evaluate the pollution level of rainwater based on the water quality index; Rainwater treatment module: used to transport different water qualities to corresponding reservoirs based on the pollution level of rainwater; and, to transport different water qualities to corresponding filtration tanks based on the pollution level of rainwater.

2. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 1 is characterized in that: The airport rainfall conditions in the predicted target area include: Extract meteorological data and corresponding actual rainfall at different times of the target area from historical data to establish a rainfall database for the target area; the meteorological data is the input data of the neural network model, and the actual rainfall corresponding to the meteorological data is the output data of the neural network model; The neural network model is trained through input data and output data to obtain a rainfall prediction model; Collect future meteorological data of the target area, input the future meteorological data into the rainfall prediction model, and output the rainfall prediction value of the target area in the future time period.

3. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 2 is characterized in that: The rainfall prediction value output by the neural network model and the corresponding actual rainfall are constructed into two sequences of the same length, and the formula Calculate the mean square error (MSE) between the two sets of sequences; determine whether the mean square error is greater than a preset threshold; if so, optimize the neural network model; If not, the neural network model training ends; where j is the element number of the sequence, j = 0, 1, ..., M, M is a positive integer, y j is the actual rainfall, Forecast rainfall forecast value.

4. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 2 is characterized in that: The method of determining the combination of drainage pipes according to the rainfall in the target area includes: Based on the predicted rainfall value of the target area in the future time period, the predicted rainfall value per unit time is calculated; Obtain the cross-sectional area and maximum flow velocity of the drainage pipe and calculate the maximum flow rate of the pipe; The standard delivery flow of the drainage pipe is compared with the predicted value of rainfall per unit time to obtain the required number of drainage pipes, which is marked as G; wherein, the standard delivery flow of the drainage pipe is the product of the standard opening of the drainage pipe and the maximum delivery flow of the drainage pipe; the maximum delivery flow of the drainage pipe is the product of the cross-sectional area of ​​the drainage pipe and the maximum flow velocity; The average usage frequency PL of N drainage pipes with a degree greater than the standard opening is calculated by the formula PL=min[Σ(Rki / STi) / N]; the drainage pipe combination with the lowest usage frequency is the drainage pipe combination that needs to be opened; wherein k is the standard opening; i is the pipe number, i=0, 1,…, N, N is a positive integer; STi is the duration of use of pipe i from the beginning of use to the current time; Ri is the number of times pipe i uses the standard opening during the STi period.

5. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 4 is characterized in that: Each roof of the airport is equipped with several drainage pipes of the same specifications. The number of drainage pipes on each roof of the airport is set based on the standard delivery flow of the drainage pipes and the maximum rainfall in the airport's historical data.

6. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 4 is characterized in that: The standard opening of the drainage pipe includes: A digital twin model of the airport drainage pipes was established, and several groups of different rainfalls were set. Each group of rainfall was transported by drainage pipes with different openings. After repeated experiments, the service life of the drainage pipes under different rainfalls and openings was obtained. The service life of the drainage pipes under different rainfalls with the same opening was averaged to obtain the average service life of the drainage pipes at this opening. The average usage time of each opening is compared, and the opening corresponding to the largest average usage time is the standard opening of the drainage pipe; among which, the usage time of the drainage pipe under different openings at different rainfall amounts is the time from the beginning of the drainage pipe's work to the time when it stops working normally.

7. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 1 is characterized in that: The method of obtaining the content of each element in rainwater and analyzing the water quality index of rainwater includes: Collect several rainwater samples, detect the content of each element in several rainwater samples, and perform mean processing to obtain the content of each element in the rainwater in the target area; The content of each element in the rainwater is processed by the difference between the preset standard threshold of the corresponding element content, and the difference is processed by the ratio of the corresponding preset threshold to obtain the deviation rate of the element relative to the preset threshold, marked as Yr; through the formula SZ = e Σ(Yr-Br) The water quality index SZ of rainwater is calculated; wherein Br is the preset threshold, r is the number of each element contained in the rainwater, and Σ sums r.

8. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 7 is characterized in that: The pollution level of rainwater is assessed based on the water quality index, including: Compare the water quality index of rainwater with the preset range; if the water quality index is greater than the preset range, the rainwater pollution level is level one; if the water quality index is within the preset range, the rainwater pollution level is level two; if the water quality index is less than the preset range, the rainwater pollution level is level three; among which, pollution level one>level two>level three.

9. The cloud computing-based airport roof rainwater treatment monitoring system according to claim 8, characterized in that: The method of delivering different water qualities to corresponding filter pools based on the pollution level of rainwater includes: The inlet valve of the corresponding filter pool is opened according to the pollution level of the rainwater, and the filter pool adjusts the filter medium and the corresponding ratio of the filter pool in real time according to the content of each element in the rainwater.

10. A cloud computing-based airport roof rainwater treatment monitoring method, based on the cloud computing-based airport roof rainwater treatment monitoring system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Predict the rainfall in the target area; determine the drainage pipe combination according to the rainfall in the target area; Step 2: Obtain the content of each element in rainwater and analyze the water quality index of rainwater; evaluate the pollution level of rainwater based on the water quality index; Step 3: transporting different water qualities to corresponding water reservoirs based on the pollution level of rainwater; and transporting different water qualities to corresponding filtration tanks based on the pollution level of rainwater.

Images