Smart city construction flood disaster real-time online monitoring and early warning management system

Abstract

The present invention relates to a real-time online monitoring and early warning management system for flood disasters in smart city construction, which belongs to the field of smart cities. The system includes: an information downloading mechanism, which is used to download the average rainfall of the smart city in the next time segment after the current moment from the big data server of the meteorological forecast center closest to the smart city; an identification prediction mechanism, which is used to intelligently analyze whether the water level in the set water storage area will overflow in the next time segment after the current moment based on the average rainfall, the set water storage area in the smart city, and the configuration data of the drainage outlets connected thereto. Through the present invention, in view of the technical problem that urban flood disasters are difficult to accurately predict in the prior art, a corresponding intelligent prediction body can be designed for each set water storage area in the construction of a smart city, which is used to intelligently analyze whether the water level in the set water storage area will overflow in the future time segment.

Description

Technical Field

[0001] The present invention relates to the field of smart cities, and in particular to a real-time online monitoring and early warning management system for flood disasters in smart city construction. Background Art

[0002] Smart City originated from the field of media. It refers to the application of intelligent computing technologies such as the Internet of Things, cloud computing, big data, and spatial geographic information integration in the fields of urban planning, design, construction, management, and operation. The key infrastructure components and services of cities such as urban management, education, medical care, real estate, transportation, public utilities, and public safety are made more interconnected, efficient, and intelligent, thereby providing citizens with better living and working services, creating a more favorable business development environment for enterprises, and enabling more efficient operation and management mechanisms for the government.

[0003] For example, Chinese invention patent publication CN106971509A proposes a smart city flood warning management system, in which the core sensing device of the flood warning management system is installed in a protective cover, and the lower end of the protective cover is connected to the drainage pipe through a trapezoidal clamp. The core sensing device is composed of a base plate and a magnetic cover to form a magnetic field. The base plate is a multi-layered disc structure. An electric field power supply is connected to the bottom of the base plate, and an alarm is connected to the base plate, which is more in line with market demand and has broader prospects for use.

[0004] For example, the Chinese invention patent publication CN113554236A proposes a real-time online monitoring and early warning management cloud platform for flood disasters in smart city construction. The present invention monitors the water level of each water storage area in the city to be monitored, analyzes the remaining safe water level in each water storage area in the city to be monitored, obtains the expected rainfall in each water storage area in the future time period, estimates the flood disaster occurrence proportion coefficient in each water storage area, and simultaneously detects the drainage speed per unit time of each drainage outlet in each sub-area in the city to be monitored, compares and obtains the drainage volume per unit time difference of each drainage outlet in each sub-area, monitors the real-time rainfall in each sub-area, analyzes the flood disaster occurrence impact proportion coefficient of each sub-area, and comprehensively calculates the comprehensive flood disaster occurrence prediction coefficient of the city to be monitored. If it is greater than the set threshold, an early warning reminder is issued, thereby ensuring that the urban flood disaster situation can be truly reflected, disaster prevention and mitigation measures can be formulated in advance, and property losses can be reduced and casualties can be avoided.

[0005] Obviously, the flood disaster warning mode of smart city construction in the above-mentioned prior art is based on either real-time data or forecast data obtained based on a rough evaluation model. The former is difficult to effectively implement due to the time difference between the detection data time and the flood occurrence time, and the latter is prone to false alarms or missed alarms due to the rough evaluation model. Therefore, there is a need for an intelligent prediction mechanism that can accurately predict urban flood disasters, so as to enhance the city's emergency response capabilities and improve the intelligent level of urban construction. Summary of the invention

[0006] In order to solve the technical problems in the prior art, the present invention provides a real-time online monitoring and early warning management system for flood disasters in smart city construction, which can design a corresponding intelligent prediction body for each set water storage area in the smart city construction, and is used to intelligently analyze whether the set water storage area in the future time segment will have a water level overflow mark based on the average rainfall in the smart city in the future time segment, multiple regional parameters of the set water storage area, and various configuration data of each drainage outlet connected thereto, thereby improving the prediction accuracy of urban flood disasters, and enhancing the intelligence level of urban construction while enhancing the city's emergency response capabilities.

[0007] According to a first aspect of the present invention, a real-time online monitoring and early warning management system for flood disasters in smart city construction is provided, the system comprising:

[0008] An information downloading mechanism connected to a big data server network of a meteorological forecast center closest to the smart city, for downloading the average rainfall of the smart city in the next time segment after the current moment;

[0009] A regional analysis unit, for obtaining a water storage area, an overflow water level, and a total number of connected drains of a set water storage area in the smart city, and outputting the data as a plurality of regional parameters of the set water storage area;

[0010] A data detection mechanism, used to obtain multiple pieces of setting information of each drain outlet connected to the set water storage area, wherein the multiple pieces of setting information of each drain outlet include the water outlet opening area, water level difference and drainage channel length of the drain outlet;

[0011] A sequential construction mechanism is used to perform each learning action on the BP neural network to obtain the BP neural network after completing each learning action, and output it as an intelligent prediction body, wherein the number of learning times of the BP neural network is monotonically positively correlated with the water storage area of ​​the set water storage area;

[0012] An identification prediction mechanism is connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism respectively, and is used to synchronously input the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area and multiple setting information of each drain outlet connected to the set water storage area into the intelligent prediction body and execute the intelligent prediction body to obtain an identification output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment;

[0013] Among them, multiple items of setting information of each drain outlet connected to the set water storage area are obtained, and the multiple items of setting information of each drain outlet include the water outlet opening area, water level difference and drainage channel length of the drain outlet, including: the water level difference of the drain outlet is the difference obtained by subtracting the height of the position where the water inlet opening of the drain outlet is located from the height of the position where the water outlet opening of the drain outlet is located.

[0014] According to a second aspect of the present invention, a real-time online monitoring and early warning management system for flood disasters in smart city construction is provided, the system comprising a memory and one or more processors, the memory storing a computer program, the computer program being configured to be executed by the one or more processors to complete the following steps:

[0015] Download the average rainfall of the smart city in the next time segment after the current moment from the big data server of the meteorological forecast center closest to the smart city;

[0016] Obtaining the water storage area, overflow water level, and total number of connected drain outlets of a set water storage area in the smart city, and outputting them as multiple regional parameters of the set water storage area;

[0017] Acquire multiple pieces of setting information of each drain outlet connected to the set water storage area, wherein the multiple pieces of setting information of each drain outlet include the water outlet opening area, water level difference and drainage channel length of the drain outlet;

[0018] Performing each learning action on the BP neural network to obtain the BP neural network after completing each learning action, and outputting it as an intelligent prediction body, wherein the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area;

[0019] The average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are synchronously input into the intelligent prediction body and the intelligent prediction body is executed to obtain an indicator output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment;

[0020] Among them, multiple items of setting information of each drain outlet connected to the set water storage area are obtained, and the multiple items of setting information of each drain outlet include the water outlet opening area, water level difference and drainage channel length of the drain outlet, including: the water level difference of the drain outlet is the difference obtained by subtracting the height of the position where the water inlet opening of the drain outlet is located from the height of the position where the water outlet opening of the drain outlet is located.

[0021] It can be seen that the present invention has at least the following important inventive concepts:

[0022] Inventive concept A: Establishing an intelligent prediction body for a set water storage area of ​​a smart city, for completing intelligent prediction processing of whether the set water storage area will overflow in the next time segment after the current moment as the future time segment, thereby providing sufficient response time for the distributed control and response of the smart city;

[0023] Inventive concept B: Execute each learning action on the BP neural network to obtain the BP neural network after each learning action is completed, and output it as an intelligent prediction body, wherein the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, thereby completing the customization of the structure of different intelligent prediction bodies for different water storage areas;

[0024] Inventive concept C: selecting the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drainage outlet connected to the set water storage area as multiple input data of the intelligent prediction body, thereby ensuring that the basic data of the intelligent prediction is sufficient and comprehensive;

[0025] Inventive concept D: Create a targeted learning mechanism to ensure the learning effect of each learning of the BP neural network, wherein each learning action of the BP neural network corresponds to each historical moment, and in a certain learning action executed on the BP neural network, a known value of an identifier indicating whether a water level overflow will occur in a set water storage area within the next historical time segment after a certain historical moment is used as the output content of the BP neural network, and the average rainfall of the smart city within the next historical time segment after the certain historical moment, the duration of the time segment, the water level of the set water storage area at the certain historical moment, multiple area parameters of the set water storage area, and multiple setting information of each drain outlet connected to the set water storage area are used as the input content of the BP neural network. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0027] Figure 1 This is a technical flow chart of the real-time online monitoring and early warning management system for flood disasters in smart cities according to the present invention.

[0028] Figure 2 The figure is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to the first embodiment of the present invention.

[0029] Figure 3 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to the second embodiment of the present invention.

[0030] Figure 4 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 3 of the present invention.

[0031] Figure 5 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 4 of the present invention.

[0032] Figure 6 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 5 of the present invention.

[0033] Figure 7 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 6 of the present invention. DETAILED DESCRIPTION

[0034] like Figure 1As shown, a technical flow chart of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to the present invention is given.

[0035] like Figure 1 As shown, the specific technical process of the present invention is as follows:

[0036] Technical process A: Establish an intelligent prediction body for the set water storage area of ​​the smart city, which is used to complete the intelligent prediction processing of whether the set water storage area will overflow in the next time segment after the current moment as the future time segment, so as to provide sufficient response time for the distributed control and response of the smart city;

[0037] For example, different water storage areas have different corresponding intelligent prediction body structures, which are specifically shown as follows:

[0038] First, the intelligent prediction body is a BP neural network obtained by executing each learning action on the BP neural network after completing each learning action, and the number of learning times of the BP neural network is monotonically positively correlated with the water storage area of ​​the set water storage area;

[0039] Secondly, each learning action of the BP neural network corresponds to each historical moment. In a certain learning action executed on the BP neural network, a known value of an identifier indicating whether a water level overflow will occur in a set water storage area in the next historical time segment after a certain historical moment is used as the output content of the BP neural network, and the average rainfall of the smart city in the next historical time segment after the certain historical moment, the duration of the time segment, the water level of the set water storage area at the certain historical moment, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are used as the input content of the BP neural network, thereby ensuring the learning effect of each learning action of the BP neural network;

[0040] Technical process B: Targeted screening of comprehensive and effective basic information for intelligent prediction of water level overflow to ensure the reliability and stability of intelligent prediction results;

[0041] Specifically, the multiple basic information includes the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drainage outlet connected to the set water storage area;

[0042] Furthermore, setting multiple regional parameters of the water storage area includes setting the water storage area, overflow water level and the total number of connected drains of the water storage area, and multiple setting information of each drain includes the water outlet opening area, water level drop and drainage channel length of the drain;

[0043] and downloading the average rainfall of the smart city in the next time segment after the current moment from the big data server of the meteorological forecast center closest to the smart city;

[0044] Technical process C: The intelligent prediction body with customized structure design of technical process A completes the intelligent prediction processing of whether the water level overflow will occur in the set water storage area in the next time segment after the current moment based on multiple basic information targeted by technical process B;

[0045] Technical process D: Based on the results of the intelligent prediction processing of technical process C, decide whether to execute the water level overflow alarm for the set water storage area in the next time segment after the current moment, thereby providing reliable reference data for the intelligent monitoring and early warning of flood disasters in smart city construction, and providing sufficient response time for the early transfer of personnel and the adoption of corresponding response measures.

[0046] It can be seen that through the above-mentioned intelligent processing and response, the phenomenon of false alarms or missed alarms in flood disaster warnings can be avoided, accurate prediction of urban flood disasters can be achieved, the city’s emergency response capabilities can be enhanced, and the intelligence level of urban construction can be improved.

[0047] The key points of the present invention are: customization of intelligent prediction bodies with different structures in different water storage areas within the smart city, targeted screening of comprehensive and effective multiple basic information used in intelligent prediction processing, design of each learning action of the intelligent prediction body to ensure learning effect, and early response to flood disasters in smart city construction based on intelligent prediction results.

[0048] Next, the real-time online monitoring and early warning management system for flood disasters in smart city construction of the present invention will be specifically described in the form of an embodiment.

[0049] Embodiment 1

[0050] Figure 2 The figure is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to the first embodiment of the present invention.

[0051] like Figure 2 As shown, the real-time online monitoring and early warning management system for flood disasters in smart cities includes the following components:

[0052] An information downloading mechanism connected to a big data server network of a meteorological forecast center closest to the smart city, for downloading the average rainfall of the smart city in the next time segment after the current moment;

[0053] For example, a cloud computing server or a blockchain server may be selected to replace the big data server to provide the average rainfall of the smart city in the next time segment after the current moment for downloading;

[0054] A regional analysis unit, for obtaining a water storage area, an overflow water level, and a total number of connected drains of a set water storage area in the smart city, and outputting the data as a plurality of regional parameters of the set water storage area;

[0055] Specifically, multiple content collection components may be selected to respectively obtain the water storage area, overflow water level, and total number of connected drainage outlets of a set water storage area in the smart city;

[0056] For example, a first content collection component may be selected to obtain the water storage area of ​​a set water storage area in a smart city, a second content collection component may be selected to obtain the overflow water level of a set water storage area in a smart city, and a third content collection component may be selected to obtain the total number of drainage outlets connected to the set water storage area in the smart city;

[0057] A data detection mechanism, used to obtain multiple pieces of setting information of each drain outlet connected to the set water storage area, wherein the multiple pieces of setting information of each drain outlet include the water outlet opening area, water level difference and drainage channel length of the drain outlet;

[0058] A sequential construction mechanism is used to perform each learning action on the BP neural network to obtain the BP neural network after completing each learning action, and output it as an intelligent prediction body, wherein the number of learning times of the BP neural network is monotonically positively correlated with the water storage area of ​​the set water storage area;

[0059] For example, the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, including: the water storage area of ​​the set water storage area is 1000 square meters, the number of times the BP neural network is learned is 200, the water storage area of ​​the set water storage area is 1500 square meters, the number of times the BP neural network is learned is 300, the water storage area of ​​the set water storage area is 2000 square meters, the number of times the BP neural network is learned is 400, the water storage area of ​​the set water storage area is 2500 square meters, the number of times the BP neural network is learned is 500, and so on;

[0060] An identification prediction mechanism is connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism respectively, and is used to synchronously input the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area and multiple setting information of each drain outlet connected to the set water storage area into the intelligent prediction body and execute the intelligent prediction body to obtain an identification output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment;

[0061] For example, a numerical simulation mode may be selected to implement the simulation and test of a data processing process of synchronously inputting the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area into the intelligent prediction body and executing the intelligent prediction body to obtain an indication output by the intelligent prediction body indicating whether the set water storage area will overflow the water level in the next time segment after the current moment;

[0062] Wherein, obtaining multiple pieces of setting information of each drain outlet connected to the set water storage area, the multiple pieces of setting information of each drain outlet including the water outlet opening area, the water level drop and the length of the drainage channel of the drain outlet includes: the water level drop of the drain outlet is the difference obtained by subtracting the height of the water inlet opening of the drain outlet from the height of the water outlet opening of the drain outlet;

[0063] For example, the water level difference of the drain outlet is the difference between the height of the water inlet opening of the drain outlet and the height of the water outlet opening of the drain outlet, including: when the height of the water inlet opening of the drain outlet is 100 meters above sea level, and the height of the water outlet opening of the drain outlet is 80 meters above sea level, the water level difference of the drain outlet is the difference between the height of the water inlet opening of the drain outlet and the height of the water outlet opening of the drain outlet, that is, 20 meters;

[0064] The BP neural network is subjected to each learning action to obtain the BP neural network after each learning action is completed, and the BP neural network is output as an intelligent prediction body, and the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, including: each learning action of the BP neural network corresponds to each historical moment;

[0065] Among them, each learning action is performed on the BP neural network to obtain the BP neural network after each learning action is completed, and the BP neural network is output as an intelligent prediction body. The number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area. It also includes: in a certain learning action performed on the BP neural network, the known value of the identifier indicating whether the set water storage area will overflow in the next historical time segment after a certain historical moment is used as the output content of the BP neural network, the average rainfall of the smart city in the next historical time segment after the certain historical moment, the duration of the time segment, the water level of the set water storage area at the certain historical moment, multiple regional parameters of the set water storage area, and multiple setting information of each drain outlet connected to the set water storage area are used as the input content of the BP neural network to perform this learning action.

[0066] Embodiment 2

[0067] Figure 3 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to the second embodiment of the present invention.

[0068] like Figure 3 As shown, Figure 2 Different from the embodiments in the above, the real-time online monitoring and early warning management system for flood disasters in smart cities also includes the following components:

[0069] A big data server is arranged at a weather forecast center closest to the smart city and is connected to the information downloading agency through a network, and is used to provide the information downloading agency with the average rainfall of the smart city in the next time segment after the current moment;

[0070] For example, a big data service node or a big data service network element can be selected to implement the big data server, which is set up in the weather forecast center closest to the smart city and connected to the information download agency network, and is used to provide the information download agency with the average rainfall in the smart city in the next time segment after the current moment.

[0071] Embodiment 3

[0072] Figure 4 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 3 of the present invention.

[0073] like Figure 4 As shown, Figure 3 Different from the embodiments in the above, the real-time online monitoring and early warning management system for flood disasters in smart cities also includes the following components:

[0074] A real-time display mechanism is arranged in the management control room of the smart city and is connected to the identification prediction mechanism network, and is used to perform synchronous display of the area number of the set water storage area and the water level overflow alarm information when the identification output by the received intelligent prediction body indicates that the water level overflow will occur in the set water storage area in the next time segment after the current moment;

[0075] Specifically, a liquid crystal display screen, an LED display array or an LCD display array can be selected to implement the real-time display mechanism, which is arranged in the management control room of the smart city and connected to the identification prediction mechanism network, and is used to execute the synchronous display of the area number of the set water storage area and the water level overflow alarm information when the identification output by the received intelligent prediction body indicates that the water level overflow will occur in the set water storage area within the next time segment after the current moment.

[0076] Embodiment 4

[0077] Figure 5 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 4 of the present invention.

[0078] like Figure 5 As shown, Figure 3 Different from the embodiments in the above, the real-time online monitoring and early warning management system for flood disasters in smart cities also includes the following components:

[0079] A mobile communication interface connected to the identification prediction mechanism, for packaging the area number of the set water storage area and water level overflow alarm information into a network data packet and sending it to the nearest mobile communication terminal of the city management personnel when the identification output by the received intelligent prediction body indicates that the water level overflow will occur in the set water storage area within the next time segment after the current moment;

[0080] Specifically, the mobile communication interface is based on a time division duplex communication mode or a frequency division duplex communication mode, and is used to package the area number of the set water storage area and the water level overflow alarm information into a network data packet and then wirelessly send it to the mobile communication terminal of the nearest urban management personnel through a time division duplex communication link or a frequency division duplex communication link;

[0081] The step of packaging the area number of the set water storage area and the water level overflow alarm information into a network data packet and sending the packet to the nearest mobile communication terminal of the city management personnel includes: the network data packet is an IP data packet.

[0082] Embodiment 5

[0083] Figure 6This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 5 of the present invention.

[0084] like Figure 6 As shown, Figure 3 Different from the embodiments in the above, the real-time online monitoring and early warning management system for flood disasters in smart cities also includes the following components:

[0085] A parameter storage chip, connected to the successive construction mechanism, for completing the model storage of the intelligent prediction body by storing various model parameters of the intelligent prediction body;

[0086] Specifically, a parameter storage chip is connected to the successive construction mechanism and is used to complete the model storage of the intelligent prediction body by storing various model parameters of the intelligent prediction body. The parameter storage chip can be implemented by using a TF storage device, a CF storage device or an MMC storage device, and is connected to the successive construction mechanism and is used to complete the model storage of the intelligent prediction body by storing various model parameters of the intelligent prediction body.

[0087] Next, various embodiments of the present invention will be described in detail.

[0088] In the real-time online monitoring and early warning management system for flood disasters in smart city construction according to various embodiments of the present invention:

[0089] The average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are synchronously input into the intelligent prediction body and the intelligent prediction body is executed to obtain an identifier output by the intelligent prediction body indicating whether the set water storage area will overflow in the next time segment after the current moment, including: when the value of the identifier is 0B11, it indicates that the set water storage area will overflow in the next time segment after the current moment;

[0090] Among them, the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are synchronously input into the intelligent prediction body and the intelligent prediction body is executed to obtain the identifier output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment, which also includes: when the value of the identifier is 0B10, it indicates that the water level in the set water storage area will not overflow in the next time segment after the current moment;

[0091] Among them, the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain outlet connected to the set water storage area are synchronously input into the intelligent prediction body and the intelligent prediction body is executed to obtain the indicator output by the intelligent prediction body indicating whether the water level overflow will occur in the set water storage area in the next time segment after the current moment, which also includes: the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, multiple regional parameters of the set water storage area, and multiple setting information of each drain outlet connected to the set water storage area are respectively converted into binary values ​​and then synchronously input into the intelligent prediction body;

[0092] In this way, by subjecting the input content and output content of the intelligent prediction body to binary value conversion and numerical normalization processing, the construction and effective operation of the mathematical model of the intelligent prediction body are guaranteed.

[0093] In the real-time online monitoring and early warning management system for flood disasters in smart city construction according to various embodiments of the present invention:

[0094] Obtain multiple items of setting information for each drain outlet connected to the set water storage area, wherein the multiple items of setting information for each drain outlet include the outlet opening area, water level difference and drainage channel length of the drain outlet, and also include: the drainage channel length of the drain outlet is the overall length of the drainage channel where the drain outlet is located.

[0095] And in the real-time online monitoring and early warning management system for flood disasters in smart city construction according to various embodiments of the present invention:

[0096] Executing each learning action on the BP neural network to obtain the BP neural network after completing each learning action, and outputting it as an intelligent prediction body, wherein the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, further comprising: using a numerical conversion formula to represent the numerical conversion relationship of the number of times the BP neural network is learned and monotonically positively correlated with the water storage area of ​​the set water storage area;

[0097] Among them, the numerical conversion relationship that uses a numerical conversion formula to express the monotonically positive correlation between the number of times the BP neural network is learned and the water storage area of ​​the set water storage area also includes: in the numerical conversion formula, the input data is the water storage area of ​​the set water storage area, and the output data is the number of times the BP neural network is learned.

[0098] Embodiment 6

[0099] Figure 7 This is a structural diagram of a real-time online monitoring and early warning management system for flood disasters in smart city construction according to Embodiment 6 of the present invention.

[0100] like Figure 7 As shown, the real-time online monitoring and early warning management system for flood disasters in smart city construction shown in Embodiment 6 of the present invention specifically includes a memory and one or more processors, wherein the memory stores a computer program, and the computer program is configured to be executed by the one or more processors to complete the following steps:

[0101] Download the average rainfall of the smart city in the next time segment after the current moment from the big data server of the meteorological forecast center closest to the smart city;

[0102] For example, a cloud computing server or a blockchain server may be selected to replace the big data server to provide the average rainfall of the smart city in the next time segment after the current moment for downloading;

[0103] Obtaining the water storage area, overflow water level, and total number of connected drain outlets of a set water storage area in the smart city, and outputting them as multiple regional parameters of the set water storage area;

[0104] Specifically, multiple content collection components may be selected to respectively obtain the water storage area, overflow water level, and total number of connected drainage outlets of a set water storage area in the smart city;

[0105] For example, a first content collection component may be selected to obtain the water storage area of ​​a set water storage area in a smart city, a second content collection component may be selected to obtain the overflow water level of a set water storage area in a smart city, and a third content collection component may be selected to obtain the total number of drainage outlets connected to the set water storage area in the smart city;

[0106] Acquire multiple pieces of setting information of each drain outlet connected to the set water storage area, wherein the multiple pieces of setting information of each drain outlet include the water outlet opening area, water level difference and drainage channel length of the drain outlet;

[0107] Performing each learning action on the BP neural network to obtain the BP neural network after completing each learning action, and outputting it as an intelligent prediction body, wherein the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area;

[0108] For example, the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, including: the water storage area of ​​the set water storage area is 1000 square meters, the number of times the BP neural network is learned is 200, the water storage area of ​​the set water storage area is 1500 square meters, the number of times the BP neural network is learned is 300, the water storage area of ​​the set water storage area is 2000 square meters, the number of times the BP neural network is learned is 400, the water storage area of ​​the set water storage area is 2500 square meters, the number of times the BP neural network is learned is 500, and so on;

[0109] The average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are synchronously input into the intelligent prediction body and the intelligent prediction body is executed to obtain an indicator output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment;

[0110] For example, a numerical simulation mode may be selected to implement the simulation and test of a data processing process of synchronously inputting the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area into the intelligent prediction body and executing the intelligent prediction body to obtain an indication output by the intelligent prediction body indicating whether the set water storage area will overflow the water level in the next time segment after the current moment;

[0111] Wherein, obtaining multiple pieces of setting information of each drain outlet connected to the set water storage area, the multiple pieces of setting information of each drain outlet including the water outlet opening area, the water level drop and the length of the drainage channel of the drain outlet includes: the water level drop of the drain outlet is the difference obtained by subtracting the height of the water inlet opening of the drain outlet from the height of the water outlet opening of the drain outlet;

[0112] For example, the water level difference of the drain outlet is the difference between the height of the water inlet opening of the drain outlet and the height of the water outlet opening of the drain outlet, including: when the height of the water inlet opening of the drain outlet is 100 meters above sea level, and the height of the water outlet opening of the drain outlet is 80 meters above sea level, the water level difference of the drain outlet is the difference between the height of the water inlet opening of the drain outlet and the height of the water outlet opening of the drain outlet, that is, 20 meters;

[0113] The BP neural network is subjected to each learning action to obtain the BP neural network after each learning action is completed, and the BP neural network is output as an intelligent prediction body, and the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, including: each learning action of the BP neural network corresponds to each historical moment;

[0114] And wherein, each learning action is performed on the BP neural network to obtain the BP neural network after each learning action is completed, and the BP neural network is output as an intelligent prediction body, and the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, and further includes: in a certain learning action performed on the BP neural network, the known value of the identifier indicating whether the set water storage area will overflow in the next historical time segment after a certain historical moment is used as the output content of the BP neural network, and the average rainfall of the smart city in the next historical time segment after the certain historical moment, the duration of the time segment, the water level of the set water storage area at the certain historical moment, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are used as the input content of the BP neural network to perform this learning action;

[0115] like Figure 7 As shown, N processors are provided, exemplarily, where N is a natural number greater than or equal to 1.

[0116] In addition, the present invention may also cite the following technical contents to further demonstrate the outstanding essential features of the present invention:

[0117] The identification prediction mechanism is connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism respectively, and is used to synchronously input the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area and multiple setting information of each drain connected to the set water storage area into the intelligent prediction body and execute the intelligent prediction body to obtain the identification output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment, including: using a synchronous driving mechanism connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism respectively, to realize the synchronous control of the actions of each mechanism of the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism;

[0118] An identification prediction mechanism is connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism respectively, and is used to synchronously input the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area and multiple setting information of each drain connected to the set water storage area into the intelligent prediction body and execute the intelligent prediction body to obtain the identification output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment. It also includes: using a serial configuration interface connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism respectively, to realize the configuration of the working parameters of each mechanism of the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism;

[0119] For example, a serial configuration interface connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the successive construction mechanism, respectively, is used to configure the working parameters of each mechanism of the information download mechanism, the regional analysis mechanism, the data detection mechanism and the successive construction mechanism, including: the serial configuration interface is an IIC interface and the information download mechanism, the regional analysis mechanism, the data detection mechanism and the successive construction mechanism have different configuration addresses respectively.

[0120] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A real-time online monitoring and early warning management system for flood disasters in smart city construction, characterized in that: The system comprises: An information downloading mechanism connected to a big data server network of a meteorological forecast center closest to the smart city, for downloading the average rainfall of the smart city in the next time segment after the current moment; A regional analysis unit, for obtaining a water storage area, an overflow water level, and a total number of connected drains of a set water storage area in the smart city, and outputting the data as a plurality of regional parameters of the set water storage area; A data detection mechanism, used to obtain multiple pieces of setting information of each drain outlet connected to the set water storage area, wherein the multiple pieces of setting information of each drain outlet include the water outlet opening area, water level difference and drainage channel length of the drain outlet; A sequential construction mechanism is used to perform each learning action on the BP neural network to obtain the BP neural network after completing each learning action, and output it as an intelligent prediction body, wherein the number of learning times of the BP neural network is monotonically positively correlated with the water storage area of ​​the set water storage area; An identification prediction mechanism is connected to the information download mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism respectively, and is used to synchronously input the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area and multiple setting information of each drain outlet connected to the set water storage area into the intelligent prediction body and execute the intelligent prediction body to obtain an identification output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment; Wherein, obtaining multiple pieces of setting information of each drain outlet connected to the set water storage area, the multiple pieces of setting information of each drain outlet including the water outlet opening area, the water level drop and the length of the drainage channel of the drain outlet includes: the water level drop of the drain outlet is the difference obtained by subtracting the height of the water inlet opening of the drain outlet from the height of the water outlet opening of the drain outlet; The BP neural network is subjected to each learning action to obtain the BP neural network after each learning action is completed, and the BP neural network is output as an intelligent prediction body, and the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, including: each learning action of the BP neural network corresponds to each historical moment; Among them, each learning action is performed on the BP neural network to obtain the BP neural network after each learning action is completed, and the BP neural network is output as an intelligent prediction body, and the number of times the BP neural network is learned is monotonically positively correlated with the water storage area of ​​the set water storage area, and it also includes: in a certain learning action performed on the BP neural network, the known value of the identifier indicating whether the set water storage area will overflow in the next historical time segment after a certain historical moment is used as the output content of the BP neural network, and the average rainfall of the smart city in the next historical time segment after the certain historical moment, the duration of the time segment, the water level of the set water storage area at the certain historical moment, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are used as the input content of the BP neural network to perform this learning action; Wherein, a synchronous driving mechanism connected to the information downloading mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism is used to realize synchronous control of the actions of each mechanism of the information downloading mechanism, the regional analysis mechanism, the data detection mechanism and the sequential construction mechanism; Among them, a serial configuration interface connected to the information downloading mechanism, the regional analysis mechanism, the data detection mechanism and the successive construction mechanism is used to configure the working parameters of each mechanism of the information downloading mechanism, the regional analysis mechanism, the data detection mechanism and the successive construction mechanism.

2. The real-time online monitoring and early warning management system for flood disasters in smart city construction as claimed in claim 1, characterized in that: The system further comprises: The big data server is arranged at the weather forecast center closest to the smart city and is connected to the information downloading agency network, and is used to provide the information downloading agency with the average rainfall of the smart city in the next time segment after the current moment.

3. The real-time online monitoring and early warning management system for flood disasters in smart city construction as claimed in claim 1, characterized in that: The system further comprises: A real-time display mechanism is arranged in the management control room of the smart city and is connected to the identification prediction mechanism network. It is used to perform synchronous display of the area number of the set water storage area and the water level overflow alarm information when the identification output by the received intelligent prediction body indicates that the water level overflow will occur in the set water storage area within the next time segment after the current moment.

4. The real-time online monitoring and early warning management system for flood disasters in smart city construction as claimed in claim 1, characterized in that: The system further comprises: A mobile communication interface connected to the identification prediction mechanism, for packaging the area number of the set water storage area and water level overflow alarm information into a network data packet and sending it to the nearest mobile communication terminal of the city management personnel when the identification output by the received intelligent prediction body indicates that the water level overflow will occur in the set water storage area within the next time segment after the current moment; The step of packaging the area number of the set water storage area and the water level overflow alarm information into a network data packet and sending the packet to the nearest mobile communication terminal of the city management personnel includes: the network data packet is an IP data packet.

5. The real-time online monitoring and early warning management system for flood disasters in smart city construction as claimed in claim 1, characterized in that: The system further comprises: A parameter storage chip is connected to the successive construction mechanism and is used to complete the model storage of the intelligent prediction body by storing various model parameters of the intelligent prediction body.

6. The real-time online monitoring and early warning management system for flood disasters in smart city construction as claimed in any one of claims 1 to 5, characterized in that: The average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are synchronously input into the intelligent prediction body and the intelligent prediction body is executed to obtain an identifier output by the intelligent prediction body indicating whether the set water storage area will overflow in the next time segment after the current moment, including: when the value of the identifier is 0B11, it indicates that the set water storage area will overflow in the next time segment after the current moment; Among them, the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain connected to the set water storage area are synchronously input into the intelligent prediction body and the intelligent prediction body is executed to obtain the identifier output by the intelligent prediction body indicating whether the water level in the set water storage area will overflow in the next time segment after the current moment, which also includes: when the value of the identifier is 0B10, it indicates that the water level in the set water storage area will not overflow in the next time segment after the current moment; Among them, the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, the current water level of the set water storage area, multiple regional parameters of the set water storage area, and multiple setting information of each drain outlet connected to the set water storage area are synchronously input into the intelligent prediction body and executed to obtain the output of the intelligent prediction body, indicating whether the water level overflow will occur in the set water storage area in the next time segment after the current moment. The identification also includes: the average rainfall of the smart city in the next time segment after the current moment, the duration of the time segment, multiple regional parameters of the set water storage area, and multiple setting information of each drain outlet connected to the set water storage area are converted into binary values ​​respectively and then synchronously input into the intelligent prediction body.

7. The real-time online monitoring and early warning management system for flood disasters in smart city construction as claimed in any one of claims 1 to 5, characterized in that: Obtain multiple items of setting information for each drain outlet connected to the set water storage area, wherein the multiple items of setting information for each drain outlet include the outlet opening area, water level difference and drainage channel length of the drain outlet, and also include: the drainage channel length of the drain outlet is the overall length of the drainage channel where the drain outlet is located.

8. The real-time online monitoring and early warning management system for flood disasters in smart city construction as claimed in any one of claims 1 to 5, characterized in that: Executing each learning action on the BP neural network to obtain the BP neural network after completing each learning action, and outputting it as an intelligent prediction body, wherein the number of learning times of the BP neural network is monotonically positively correlated with the water storage area of ​​the set water storage area further comprises: using a numerical conversion formula to represent the numerical conversion relationship of the number of learning times of the BP neural network and the water storage area of ​​the set water storage area being monotonically positively correlated; Among them, the numerical conversion relationship that uses a numerical conversion formula to express the monotonically positive correlation between the number of times the BP neural network is learned and the water storage area of ​​the set water storage area also includes: in the numerical conversion formula, the input data is the water storage area of ​​the set water storage area, and the output data is the number of times the BP neural network is learned.

Images