Method, device and equipment for early warning of drainage capacity of rainwater pipe network based on GNSS

Abstract

The application belongs to the technical field of urban emergency, and discloses a rainwater pipe network drainage capacity early warning method, device and equipment based on GNSS, which predicts whether rainfall will occur in the future based on the real-time troposphere delay error observation value, real-time temperature observation value and pressure observation value of the AI model based on GNSS; if it is predicted that rainfall will occur in the future, the weather and water level fullness set in which rainfall will occur in the future are obtained; the rainwater pipe network drainage capacity is early warned based on the weather and water level fullness set in which rainfall will occur in the future, the algorithm process is simplified, the work efficiency is increased, the real-time advantage is higher, climate change and rapid land use and cover change can be coped with, the method can be more flexibly used, and the construction and operation and maintenance cost is low.

Description

Technical Field

[0001] This invention relates to the field of urban emergency technology, and in particular to a GNSS-based method, device, and equipment for early warning of rainwater drainage capacity in pipe networks. Background Technology

[0002] In recent years, to address climate change and rapid land use and cover shifts, traditional rainfall forecasts and contingency plans have been unable to adapt to real-time urban changes, resulting in unsatisfactory warnings regarding stormwater drainage capacity after a period of time. This leads to delayed responses to events such as overflowing pipe networks and urban flooding. With the maturation and improvement of satellite remote sensing, artificial intelligence models, and edge computing hardware, these technologies can be leveraged to advance the dissemination of stormwater drainage capacity warnings. This will help minimize or reduce natural disaster losses, enable early prevention, and achieve digitalized scenarios, intelligent simulations, and precise early warnings of stormwater drainage capacity impacts on short-term rainfall.

[0003] Currently, there are four main directions in the development of related technologies. The first direction estimates precipitable water vapor (PWV) or rainfall based on GNSS signal delay. However, this technology only generates rainfall information and does not provide subsequent application and early warning information dissemination. The second direction estimates PWV or rainfall based on GNSS signal delay and provides related application and early warning information dissemination, but the process is lengthy and inefficient. The third direction uses GNSS satellite navigation and positioning functions to conduct disaster early warning based on positioning differences between different time periods. The fourth direction uses traditional rainfall observation methods to analyze the drainage capacity and fullness of rainwater pipe networks using water environment models. Traditional rainfall observation methods, such as rain gauges, have poor real-time performance; radar echo observation is expensive.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a GNSS-based method, device, and equipment for early warning of rainwater drainage capacity in pipe networks, aiming to solve the technical problems of existing technologies, such as lack of early warning assessment, long process, low efficiency, and poor real-time measurement.

[0006] To achieve the above objectives, the present invention provides a GNSS-based method for early warning of stormwater drainage capacity, the method comprising the following steps:

[0007] The system acquires real-time tropospheric delay error observations of ground-based GNSS, real-time temperature and air pressure observations from multiple ground meteorological stations, and real-time water level filling observations from multiple key nodes of the rainwater pipe network.

[0008] Using an AI model based on the real-time tropospheric delay error observations of the GNSS, the real-time temperature observations, and the air pressure observations, it is predicted whether rainfall will occur in the future;

[0009] If future rainfall is predicted, then obtain the set of weather conditions and water level fullness for the future rainfall.

[0010] The system provides early warnings about the drainage capacity of rainwater pipe networks based on the set of meteorological data and water level fullness for future rainfall.

[0011] In some embodiments, obtaining the set of weather and water level fullness data indicating future rainfall includes:

[0012] After using an AI model to identify all key nodes in the stormwater pipe network, a rainfall classification set is obtained, and based on the identification results, data on key nodes in the stormwater pipe network that will experience future rainfall is obtained.

[0013] The meteorological and water level fullness sets corresponding to the rainfall classification set and the key node data of the stormwater pipe network where rainfall will occur in the future are used to obtain the meteorological and water level fullness sets for future rainfall.

[0014] In some embodiments, the method further includes:

[0015] The historical tropospheric delay error observations of the ground-based GNSS and the historical temperature and pressure observations of multiple ground meteorological stations are input into the AI ​​model to be trained, and the rainfall prediction results output by the AI ​​model to be trained are obtained.

[0016] The rainfall prediction results output by the AI ​​model to be trained are compared with the historical rainfall results corresponding to the historical tropospheric delay error observations, the historical temperature observations, and the historical air pressure observations.

[0017] The AI ​​model to be trained is trained based on the comparison results to obtain the trained AI model.

[0018] In some embodiments, the early warning of stormwater drainage capacity based on the set of meteorological and water level fullness data indicating future rainfall includes:

[0019] Based on the set of meteorological and water level fullness values ​​for future rainfall, determine the number of solutions dominated by the first objective corresponding to the tropospheric delay error observations for future rainfall, the number of solutions dominated by the second objective corresponding to the temperature observations for future rainfall, the number of solutions dominated by the third objective corresponding to the air pressure observations for future rainfall, and the number of solutions dominated by the fourth objective corresponding to the water level fullness observations for future rainfall.

[0020] The drainage capacity of the rainwater pipe network is given an early warning based on the number of solutions controlled by the first objective, the second objective, the third objective, and the fourth objective.

[0021] In some embodiments, determining the number of solutions dominated by a first objective for future tropospheric delay error observations, the number of solutions dominated by a second objective for future temperature observations, the number of solutions dominated by a third objective for future air pressure observations, and the number of solutions dominated by a fourth objective for future water level fullness observations based on the set of meteorological and water level fullness observations for future rainfall, includes:

[0022] Arbitrarily select a parameter value from the set of meteorological and water level fullness values ​​for future rainfall, wherein the parameter value is any one of the following: the tropospheric delay error observation value for future rainfall, the temperature observation value for future rainfall, and the air pressure observation value for future rainfall;

[0023] The parameter value is compared with other parameter values ​​of the same type in turn.

[0024] Based on the comparison results, the available parameter values ​​corresponding to the parameter values ​​are determined, and the number of solutions corresponding to the target is calculated. Among them, the comparison result corresponding to the tropospheric delay error observation value that will cause future rainfall is greater than other tropospheric delay error observation values ​​that will cause future rainfall; the comparison result corresponding to the water level fullness observation value that will cause future rainfall is greater than other water level fullness observation values ​​that will cause future rainfall; the comparison result corresponding to the temperature observation value that will cause future rainfall is less than other temperature observation values ​​that will cause future rainfall; and the comparison result corresponding to the air pressure observation value that will cause future rainfall is less than other air pressure observation values ​​that will cause future rainfall.

[0025] In some embodiments, providing an early warning of stormwater drainage capacity based on the number of solutions dominated by the first objective, the second objective, the third objective, and the fourth objective includes:

[0026] The fitness score of each critical node in the stormwater pipe network is calculated based on the number of solutions dominated by the first objective, the second objective, the third objective, and the fourth objective.

[0027] The drainage capacity of the stormwater pipe network is evaluated based on the fitness score, and the fitness score is negatively correlated with the drainage capacity of each key node of the stormwater pipe network.

[0028] Furthermore, to achieve the above objectives, the present invention also proposes a GNSS-based early warning device for rainwater drainage capacity of a pipe network, the GNSS-based early warning device for rainwater drainage capacity of a pipe network comprising:

[0029] The acquisition module is used to acquire real-time tropospheric delay error observations of ground-based GNSS, real-time temperature and air pressure observations of multiple ground meteorological stations, and real-time water level filling observations of multiple key nodes of the rainwater pipe network.

[0030] The processing module is used to construct a meteorological and water level fullness set based on the real-time tropospheric delay error observation, the real-time temperature and air pressure observation, and the real-time water level fullness observation.

[0031] The identification module is used to predict whether rainfall will occur in the future based on the real-time tropospheric delay error observations of the GNSS, the real-time temperature observations, and the air pressure observations using an AI model.

[0032] If the processing module predicts that rainfall will occur in the future, it obtains a set of weather conditions and water level fullness for the future rainfall.

[0033] The early warning module is used to provide early warnings about the drainage capacity of the rainwater pipe network based on the set of weather conditions and water level fullness that indicate future rainfall.

[0034] In some embodiments, the processing module is configured to obtain a rainfall classification set after identifying all key nodes of the stormwater pipe network using an AI model, and obtain data on key nodes of the stormwater pipe network that will experience future rainfall based on the identification results.

[0035] The meteorological and water level fullness sets corresponding to the rainfall classification set and the key node data of the stormwater pipe network where rainfall will occur in the future are used to obtain the meteorological and water level fullness sets for future rainfall.

[0036] In some embodiments, the apparatus further includes a construction module;

[0037] The construction module is used to input the historical tropospheric delay error observations of the ground-based GNSS and the historical temperature and pressure observations of multiple ground meteorological stations into the AI ​​model to be trained, so as to obtain the rainfall prediction results output by the AI ​​model to be trained.

[0038] The rainfall prediction results output by the AI ​​model to be trained are compared with the historical rainfall results corresponding to the historical tropospheric delay error observations, the historical temperature observations, and the historical air pressure observations.

[0039] The AI ​​model to be trained is trained based on the comparison results to obtain the trained AI model.

[0040] Furthermore, to achieve the above objectives, the present invention also proposes a GNSS-based rainwater drainage capacity early warning device, the GNSS-based rainwater drainage capacity early warning device comprising: a memory, a processor, and a GNSS-based rainwater drainage capacity early warning program stored in the memory and executable on the processor, the GNSS-based rainwater drainage capacity early warning program being configured to implement the steps of the GNSS-based rainwater drainage capacity early warning method described above.

[0041] This invention uses an AI model to predict whether rainfall will occur in the future based on real-time tropospheric delay error observations, real-time temperature observations, and air pressure observations from GNSS. If rainfall is predicted, a set of meteorological and water level fullness data for the future rainfall is obtained. Based on this set of meteorological and water level fullness data for the future rainfall, an early warning is given to the drainage capacity of the stormwater pipe network. This method simplifies the algorithm process, increases work efficiency, and has the advantage of being more real-time. It can also cope with climate change and rapid land use and cover changes, allowing for more flexible application and low construction and operation costs. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating the first embodiment of the GNSS-based early warning method for rainwater pipe network drainage capacity according to the present invention.

[0043] Figure 2 This is a schematic diagram of the AI ​​model construction process in the GNSS-based early warning method for rainwater pipe network drainage capacity of the present invention;

[0044] Figure 3 This is a structural block diagram of the first embodiment of the GNSS-based rainwater pipe network drainage capacity early warning device of the present invention.

[0045] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0046] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0047] This invention provides a GNSS-based method for early warning of stormwater drainage capacity, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of a GNSS-based early warning method for rainwater drainage capacity of a pipe network according to the present invention.

[0048] In this embodiment, the GNSS-based early warning method for rainwater pipe network drainage capacity includes the following steps:

[0049] Step S10: Obtain real-time tropospheric delay error observations of ground-based GNSS, real-time temperature and air pressure observations of multiple ground meteorological stations, and real-time water level filling observations of multiple key nodes in the rainwater pipe network.

[0050] In this embodiment, the executing entity is a GNSS-based rainwater drainage capacity early warning device. This GNSS-based rainwater drainage capacity early warning device has functions such as data processing, data communication, and program execution. The GNSS-based rainwater drainage capacity early warning device can be a computer or other terminal data processing device, or other devices with similar functions. This embodiment does not limit the scope of the device.

[0051] It should be noted that the current development of related technologies mainly follows four directions. The first direction estimates precipitable water vapor (PWV) or rainfall using GNSS signal delay, but this technology only generates rainfall information and does not provide subsequent application-based early warning messages. The second direction estimates PWV or rainfall using GNSS signal delay and provides related application-based early warning messages, but the process is lengthy and inefficient. The third direction uses GNSS satellite navigation and positioning functions to provide disaster early warnings based on positioning differences between different time periods. The fourth direction uses traditional rainfall observation methods to analyze the drainage capacity and fullness of rainwater pipe networks using water environment models. Traditional rainfall observation methods, such as rain gauges, have poor real-time performance; radar echo observation is expensive.

[0052] To address the aforementioned technical issues, this embodiment acquires real-time tropospheric delay error observations from ground-based GNSS, real-time temperature and pressure observations from multiple ground meteorological stations, and real-time water level fullness observations from multiple key nodes of the stormwater drainage network. Based on these observations, a meteorological and water level fullness set is constructed. An AI model is used to predict whether future rainfall will occur based on the GNSS's real-time tropospheric delay error observations, temperature, and pressure. If rainfall is predicted, the meteorological and water level fullness set indicating future rainfall is obtained. Based on this set, an early warning is issued for the stormwater drainage network's drainage capacity. This approach simplifies the algorithm, increases efficiency, and provides more real-time performance. It also addresses climate change and rapid land use and cover changes, allowing for more flexible application and lower construction and maintenance costs. Specifically, it can be implemented as follows.

[0053] In this specific implementation, it is necessary to first acquire real-time tropospheric delay error observations from a ground-based GNSS receiver, real-time temperature and pressure observations from multiple ground-based meteorological stations, and real-time water level filling observations from multiple key nodes of the rainwater drainage network. The ground-based GNSS receiver is a single ground-based receiver capable of receiving GNSS signals from the Global Positioning System (GPS), BeiDou Navigation Satellite System (BDS), LONS, and Galileo. The real-time tropospheric delay error observations are obtained from the GNSS signals received by the receiver. The delay caused by the GNSS signal passing through the troposphere results in errors that vary depending on the moisture content of the weather; a larger tropospheric delay error indicates a higher likelihood of rainfall. Multiple ground-based GNSS receivers are used to obtain real-time tropospheric delay error observations by installing two or more receivers within a certain area, each capable of receiving different tropospheric delay error observations in real time. The ground-based meteorological station is a ground-based meteorological device containing a thermometer and a barometer. Real-time temperature and air pressure observations are meteorological data acquired through meteorological devices. Lower temperature and air pressure readings indicate a higher likelihood of rainfall. The aforementioned multiple ground meteorological stations are configured with at least two sets of meteorological devices installed within a specific area, each capable of receiving different real-time temperature and air pressure readings. Key nodes in the stormwater drainage network refer to the downstream nodes, confluence nodes, and previously disaster-prone nodes of a drainage zone's stormwater drainage network. Their selection as key nodes is determined based on human experience. Water level fullness refers to the ratio of pipe water depth to pipe inner diameter observed using instruments at key nodes in the stormwater drainage network; a higher ratio indicates a higher likelihood of disaster. The real-time water level fullness observations for multiple key stormwater drainage network nodes are obtained by selecting at least two key nodes within a specific area, with different water level fullness readings observed at each point in real-time. The geographical relationship between multiple key nodes of the rainwater pipe network and multiple ground-based GNSS receivers and multiple ground meteorological stations can be one or more GNSS receivers and one or more sets of ground meteorological devices corresponding to one or more adjacent key nodes of the rainwater pipe network, and can be a one-to-one, one-to-many or many-to-many mapping relationship.

[0054] Step S20: Using an AI model, predict whether rainfall will occur in the future based on the real-time tropospheric delay error observations of the GNSS, the real-time temperature observations, and the air pressure observations.

[0055] Based on the obtained real-time tropospheric delay error observations, real-time temperature and pressure observations, and real-time water level filling rate observations, a meteorological and water level filling rate set can be constructed, for example, X = {ZTD}. i ,TEM i PRE i ,DR i}i=1,2,…,n, where X is the set of meteorological data and water level fullness, ZTD i This represents the i-th tropospheric delay error observation; TEM i This is the temperature observation value for the i-th time; PRE i DR is the air pressure observation value of the i-th time; i is the water level filling observation value of the i-th record; n represents the number of key nodes in the rainwater pipe network.

[0056] The AI ​​model used in this embodiment is an AI classification model, including but not limited to support vector machines, K-nearest neighbors, multilayer perceptrons, and learned vector quantization. The AI ​​model is built through an AI modeling approach. The prediction results in this embodiment include whether rainfall will occur in the future and whether rainfall will not occur. It should also be noted that in this embodiment, "future" refers to the period from a few minutes to a few hours in the future.

[0057] Furthermore, C i Let f() be the result of identifying whether rainfall will occur in the near future for the i-th time, and after identifying all key nodes of the stormwater drainage network, a rainfall classification set C is formed; f() is the AI ​​model. The rainfall classification set C and the meteorological and flood level sets X are bijective. In this embodiment, the focus is on the scenario of rainfall occurring in the near future. The required data can be selected from the meteorological and water level fullness set X through the mapping relationship.

[0058]

[0059] X′={ZTD j ,TEM j PRE j ,DR j}j=1,2,…,m

[0060] C ′ Given a set of future short-term rainfall events, we can map the corresponding set of future short-term rainfall weather and water level fullness sets X′ to the set X representing the set of weather and water level fullness. j This represents the j-th tropospheric delay error observation; TEM j This is the temperature observation value for the j-th time; PRE j This represents the air pressure observation value for the j-th time; DR j is the water level filling value of the j-th record; m represents the key node data of the stormwater pipe network where rainfall is expected to occur in the near future.

[0061] In some embodiments, the AI ​​model construction process involves inputting historical tropospheric delay error observations from a ground-based GNSS and historical temperature and pressure observations from multiple ground meteorological stations into the AI ​​model to be trained, thereby obtaining the rainfall prediction results output by the AI ​​model; comparing the rainfall prediction results output by the AI ​​model with the historical rainfall results corresponding to the historical tropospheric delay error observations, the historical temperature observations, and the historical pressure observations; and training the AI ​​model based on the comparison results to obtain the trained AI model. The construction process includes, for example... Figure 2 As shown, Figure 2 First, historical tropospheric delay error observations from ground-based GNSS and historical temperature and pressure observations from surface meteorological stations are input into the AI ​​modeling system to simulate and analyze whether rainfall will occur in the near future. The results of analyzing historical rainfall observations from surface meteorological stations to predict the likelihood of near-term rainfall are compared to train and validate the AI ​​model. Training continues until the simulation results of the AI ​​model are stable or the accuracy meets requirements. The trained AI model parameters are then input into the AI ​​model for use.

[0062] Step S30: If rainfall is predicted to occur in the future, obtain the set of weather and water level fullness for the future rainfall.

[0063] If the AI ​​model predicts future rainfall, this embodiment will identify all key nodes in the stormwater drainage network to obtain a rainfall classification set and data on key nodes in the stormwater drainage network where future rainfall is expected. Furthermore, since the rainfall classification set C and the meteorological and flood level set X are bijective, Therefore, we can ultimately obtain the set of weather conditions and water level fullness for future rainfall.

[0064] Step S40: Provide an early warning of the drainage capacity of the rainwater pipe network based on the set of weather and water level fullness data indicating that rainfall will occur in the future.

[0065] In this embodiment, the process of providing early warning for the drainage capacity of the stormwater pipe network specifically includes determining, based on the set of meteorological and water level fullness data for future rainfall, the number of solutions dominated by a first objective for the tropospheric delay error observations for future rainfall, the number of solutions dominated by a second objective for the temperature observations for future rainfall, the number of solutions dominated by a third objective for the air pressure observations for future rainfall, and the number of solutions dominated by a fourth objective for the water level fullness observations for future rainfall; and providing early warning for the drainage capacity of the stormwater pipe network based on the number of solutions dominated by the first objective, the second objective, the third objective, and the fourth objective.

[0066] In some embodiments, tropospheric delay error observations, temperature observations, and air pressure observations for future rainfall can be obtained from the set of meteorological and water level fullness data for future rainfall events. Then, the number of solutions corresponding to the target dominance is obtained for each of these values. Specifically, a parameter value is arbitrarily selected from the set of meteorological and water level fullness data for future rainfall events, and the parameter value is compared with other parameter values ​​of the same type in sequence. Based on the comparison results, the dominance parameter value corresponding to the parameter value is determined, and the number of solutions corresponding to the target dominance is calculated.

[0067] For example, the process of obtaining the number of solutions dominated by the first objective is to take the tropospheric delay error observation ZTD of the j-th future short-term rainfall event. j Compare the tropospheric delay error observations for all tropospheric events that are expected to occur within the next short period. When the tropospheric delay error observation for the j-th tropospheric event that is expected to occur within the next short period is ZTD... j When the value is greater than the kth, it means that the jth element can control the kth element. The formula for the number of elements that can be controlled is as follows:

[0068] if ZTD j ZTD k then N ZTD,j =N ZTD,j +1,k=1,2,…,m

[0069] Where N ZTD,j The tropospheric delay error observation ZTD is the value of the precipitation event that is expected to occur within the j-th short-term future. j The number of solutions dominated by the objective. This includes all m tropospheric delay error observations (ZTD) for which rainfall is expected within the next short-term period. j The number of solutions dominated by the objective is N. ZTD,j j = 1, 2, ..., m.

[0070] For example, the process of obtaining the number of solutions dominated by the second objective is to obtain the temperature observation value TEM that will occur in the j-th future short-term period. j Compare all temperature observations indicating rainfall within the next short-term period. The temperature observation ZTD for the j-th temperature observation indicating rainfall within the next short-term period is... j When the value is less than the kth element, it means that the jth element can control the kth element. The formula for the number of elements that can be controlled is as follows:

[0071] if TEM j <TEM k then N TEM,j =N TEM,j +1,k=1,2,…,m

[0072] Where N TEM,jThe temperature TEM value at which rainfall is expected within the j-th short-term future. j The number of solutions dominated by the objective. The temperature TEM of all m future near-term rainfall events. j Calculate the number N of solutions dominated by the objective. TEM,j j = 1, 2, ..., m.

[0073] For example, the process of obtaining the number of solutions dominated by the third objective is to take the atmospheric pressure observation value PRE that will cause rainfall in the j-th future short-term period. j Compare all atmospheric pressure observations indicating that rainfall will occur within the next short period. When the j-th atmospheric pressure observation indicates that rainfall will occur within the next short period, PRE... j When the value is less than the kth, it means that the jth element can control the kth element. The formula for the number of elements that can be controlled is as follows.

[0074] if PRE j <PRE k then N ORE,j =N PRE,j +1,k=1,2,…,m

[0075] Where N PRE,j The PRE is the atmospheric pressure observation value for which rainfall will occur within the j-th short-term future. j The number of solutions dominated by the objective. This involves calculating the PRE values ​​of all m atmospheric pressure observations indicating that rainfall will occur within the next short-term period. j The number of solutions dominated by the objective is N. ORE,j j = 1, 2, ..., m.

[0076] For example, the process of obtaining the number of solutions dominated by the fourth objective is to take the water level filling value DR of the j-th future short-term rainfall event. j Compare all water level filling measurements for all future short-term rainfall events. When the j-th water level filling measurement for the future short-term rainfall event is DR... j When the value is greater than the kth, it means that the jth element can control the kth element. The formula for the number of elements that can be controlled is as follows:

[0077] if DR j >DR k then N DR,j =N DR,j +1,k=1,2,…,m

[0078] Where N DR,j The observed water level DR is the water level filling value that will be affected by rainfall within the j-th short-term future. j The number of solutions dominated by the objective. This involves calculating the water level fill rate (DR) of all m future near-term rainfall events. j Calculate the number of solutions dominated by the objective.

[0079] NDR,j j = 1, 2, ..., m

[0080] Furthermore, after obtaining the number of solutions dominated by the first objective, the second objective, the third objective, and the fourth objective, the fitness score of each key node in the stormwater network can be calculated, for example, GPSIFF(j) = -N. ZTD,j -N TEM,j -N PRE,j -N DR,j +m, where GPSIFF(j) represents the fitness score, N ZTD,j N represents the number of solutions dominated by the first objective. TEM,j N represents the number of solutions dominated by the second objective. PRE,j N represents the number of solutions dominated by the third objective. DR,j This indicates the number of solutions dominated by the fourth objective. It should be noted that the calculation of the real-time early warning drainage capacity of each key node in the stormwater network is based on a comparison of the fitness scores (GPSIFF) of all data points indicating impending rainfall in the near future. A higher GPSIFF score indicates a worse real-time early warning drainage capacity for key nodes in the stormwater network that are likely to experience rainfall in the near future, resulting in a more severe disaster. In other words, the fitness score is negatively correlated with the drainage capacity of each key node in the stormwater network.

[0081] This embodiment uses an AI model to predict whether rainfall will occur in the future based on real-time tropospheric delay error observations, real-time temperature observations, and air pressure observations from the GNSS. If rainfall is predicted, a set of meteorological and water level fullness data for the future rainfall is obtained. Based on this set of meteorological and water level fullness data for the future rainfall, an early warning is given to the drainage capacity of the stormwater pipe network. This method simplifies the algorithm process, increases work efficiency, and has the advantage of being more real-time. It can also cope with climate change and rapid land use and cover changes, making it more flexible to use, and has low construction and operation and maintenance costs.

[0082] Reference Figure 3 , Figure 3 This is a structural block diagram of the first embodiment of the GNSS-based rainwater pipe network drainage capacity early warning device of the present invention.

[0083] like Figure 3 As shown, the GNSS-based rainwater drainage capacity early warning device proposed in this embodiment of the invention includes:

[0084] The acquisition module 10 is used to acquire real-time tropospheric delay error observations of ground-based GNSS, real-time temperature and air pressure observations of multiple ground meteorological stations, and real-time water level filling observations of multiple key nodes of rainwater pipe network.

[0085] Processing module 20 is used to construct a meteorological and water level fullness set based on the real-time tropospheric delay error observation, the real-time temperature and air pressure observation, and the real-time water level fullness observation.

[0086] The identification module 30 is used to predict whether rainfall will occur in the future based on the real-time tropospheric delay error observation value of the GNSS, the real-time temperature observation value, and the air pressure observation value using an AI model.

[0087] If the processing module 10 predicts that rainfall will occur in the future, it will obtain a set of weather conditions and water level fullness for the future rainfall.

[0088] The early warning module 40 is used to provide early warning of the drainage capacity of the rainwater pipe network based on the set of weather and water level fullness data indicating that rainfall will occur in the future.

[0089] This embodiment uses an AI model to predict whether rainfall will occur in the future based on real-time tropospheric delay error observations, real-time temperature observations, and air pressure observations from the GNSS. If rainfall is predicted, a set of meteorological and water level fullness data for the future rainfall is obtained. Based on this set of meteorological and water level fullness data for the future rainfall, an early warning is given to the drainage capacity of the stormwater pipe network. This method simplifies the algorithm process, increases work efficiency, and has the advantage of being more real-time. It can also cope with climate change and rapid land use and cover changes, making it more flexible to use, and has low construction and operation and maintenance costs.

[0090] In some embodiments, the processing module 20 is used to obtain a rainfall classification set after identifying all key nodes of the rainwater pipe network using an AI model, and to obtain data on key nodes of the rainwater pipe network that will experience rainfall in the future based on the identification results.

[0091] The meteorological and water level fullness sets corresponding to the rainfall classification set and the key node data of the stormwater pipe network where rainfall will occur in the future are used to obtain the meteorological and water level fullness sets for future rainfall.

[0092] In some embodiments, the apparatus further includes a construction module;

[0093] The construction module is used to input the historical tropospheric delay error observations of the ground-based GNSS and the historical temperature and pressure observations of multiple ground meteorological stations into the AI ​​model to be trained, so as to obtain the rainfall prediction results output by the AI ​​model to be trained.

[0094] The rainfall prediction results output by the AI ​​model to be trained are compared with the historical rainfall results corresponding to the historical tropospheric delay error observations, the historical temperature observations, and the historical air pressure observations.

[0095] The AI ​​model to be trained is trained based on the comparison results to obtain the trained AI model.

[0096] In some embodiments, the early warning module 40 is used to determine, based on the meteorological and water level fullness set of future rainfall events, the number of solutions corresponding to the tropospheric delay error observations of future rainfall events, the number of solutions corresponding to the temperature observations of future rainfall events, the number of solutions corresponding to the air pressure observations of future rainfall events, and the number of solutions corresponding to the water level fullness observations of future rainfall events; and to provide early warning of the drainage capacity of the stormwater pipe network based on the number of solutions corresponding to the first, second, third, and fourth objectives.

[0097] In some embodiments, the early warning module 40 is configured to arbitrarily select a parameter value from the set of meteorological and water level fullness values ​​for future rainfall, wherein the parameter value is any one of the tropospheric delay error observation value, the temperature observation value, and the air pressure observation value for future rainfall; compare the parameter value with other parameter values ​​of the same type in sequence; determine the dominable parameter value corresponding to the parameter value based on the comparison results, and calculate the number of solutions corresponding to the target dominance, wherein the comparison result corresponding to the tropospheric delay error observation value for future rainfall is greater than other tropospheric delay error observation values ​​for future rainfall, the comparison result corresponding to the water level fullness observation value for future rainfall is greater than other water level fullness observation values ​​for future rainfall, the comparison result corresponding to the temperature observation value for future rainfall is less than other temperature observation values ​​for future rainfall, and the comparison result corresponding to the air pressure observation value for future rainfall is less than other air pressure observation values ​​for future rainfall.

[0098] In some embodiments, the early warning module 40 is configured to calculate the fitness score of each key node of the stormwater network based on the number of solutions dominated by the first objective, the number of solutions dominated by the second objective, the number of solutions dominated by the third objective, and the number of solutions dominated by the fourth objective; and evaluate the drainage capacity of the stormwater network based on the fitness score, wherein the fitness score is negatively correlated with the drainage capacity of each key node of the stormwater network.

[0099] This application embodiment also provides a GNSS-based rainwater drainage capacity early warning device, including a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other through the communication bus. The memory is used to store computer programs. When the processor executes the program stored in the memory, it implements the above-mentioned GNSS-based rainwater drainage capacity early warning method.

[0100] The communication bus mentioned in the aforementioned GNSS-based rainwater drainage capacity early warning device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc.

[0101] The communication interface is used for communication between the aforementioned GNSS-based rainwater drainage capacity early warning device and other devices.

[0102] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0103] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0104] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0105] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0106] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0108] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0109] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0110] In addition, for technical details not described in detail in this embodiment, please refer to the GNSS-based rainwater pipe network drainage capacity early warning method provided in any embodiment of the present invention, which will not be repeated here.

[0111] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0112] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0113] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0114] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

[0115] It is understood that the system provided in the embodiments of the present invention corresponds to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant content can be referred to the corresponding parts of the above methods.

Claims

1. A GNSS-based rainwater pipe network drainage capacity early warning method, characterized in that, The GNSS-based rainwater pipe network drainage capacity early warning method comprises: Obtaining real-time tropospheric delay error observation values of ground-based GNSS, real-time temperature observation values and pressure observation values of multiple ground meteorological stations, and real-time water level fullness observation values of multiple rainwater pipe network key nodes; predicting, using an AI model, whether rainfall will occur in the future based on real-time tropospheric delay error observations of the GNSS, the real-time temperature observations, and the barometric pressure observations, wherein , is the first pen tropospheric delay error observation, the temperature observation value of the pen, the temperature observation value of the pen, the temperature observation value of the pen, the air pressure observation value of the pen, the air pressure observation value of the pen, the recognition result of whether the future short-term weather of the pen will have rain, the rain classification set and the weather and fullness set belong to a bijective relationship, , , , The future short-term weather and water level fullness set that will occur within the event The future short-term weather and fullness set that will occur within the event , The first The tropospheric delay error observation value of the first The temperature observation value of the first The pressure observation value of the first The water level fullness observation value of the first ; The water level fullness observation value of the first ; The rainwater pipe network key node data of the first The rainwater pipe network key node data of the first If it is predicted that rainfall will occur in the future, a meteorological and water level fullness set in which rainfall will occur in the future is obtained; Based on the meteorological and water level fullness set in which rainfall will occur in the future, the drainage capacity of the rainwater pipe network is warned; The warning of the drainage capacity of the rainwater pipe network based on the meteorological and water level fullness set in which rainfall will occur in the future comprises: Based on the meteorological and water level fullness set in which rainfall will occur in the future, the first target dominated solution number corresponding to the tropospheric delay error observation value in which rainfall will occur in the future, the second target dominated solution number corresponding to the temperature observation value in which rainfall will occur in the future, the third target dominated solution number corresponding to the pressure observation value in which rainfall will occur in the future, and the fourth target dominated solution number corresponding to the water level fullness observation value in which rainfall will occur in the future are determined; The drainage capacity of the rainwater pipe network is warned according to the first target dominated solution number, the second target dominated solution number, the third target dominated solution number, and the fourth target dominated solution number; The warning of the drainage capacity of the rainwater pipe network according to the first target dominated solution number, the second target dominated solution number, the third target dominated solution number, and the fourth target dominated solution number comprises: The fitness score value of each key node of the rainwater pipe network is calculated according to the number of solutions dominated by the first target, the number of solutions dominated by the second target, the number of solutions dominated by the third target and the number of solutions dominated by the fourth target, wherein, , represents the fitness score, represents the number of solutions dominated by the first target, represents the number of solutions dominated by the second target, represents the number of solutions dominated by the third target, represents the number of solutions dominated by the fourth target; The drainage capacity of the rainwater pipe network is evaluated based on the fitness score value, and the fitness score value is negatively correlated with the drainage capacity of each rainwater pipe network key node. 2.The GNSS-based rainwater sewer network drainage capacity early warning method according to claim 1, wherein, The meteorological and water level fullness set in which rainfall will occur in the future comprises: After all rainwater pipe network key nodes are identified by using the AI model, a rainfall classification set is obtained, and rainwater pipe network key node data in which rainfall will occur in the future is obtained based on the identification result; The meteorological and water level fullness set in which rainfall will occur in the future is obtained according to the meteorological and water level fullness set corresponding to the rainfall classification set and the rainwater pipe network key node data in which rainfall will occur in the future. 3.The GNSS-based rainwater sewer network drainage capacity early warning method of claim 1, wherein, The method further comprises: The historical tropospheric delay error observation values of the ground-based GNSS and the historical temperature observation values and historical pressure observation values of the multiple ground meteorological stations are input into a to-be-trained AI model to obtain rainfall prediction results output by the to-be-trained AI model; The rainfall prediction results output by the to-be-trained AI model are compared with historical rainfall results corresponding to the historical tropospheric delay error observation values, the historical temperature observation values, and the historical pressure observation values; Based on the comparison result, the to-be-trained AI model is trained to obtain a trained AI model. 4.The GNSS-based rainwater sewer network drainage capacity early warning method of claim 1, wherein, The first target dominated solution number corresponding to the tropospheric delay error observation value of future rainfall, the second target dominated solution number corresponding to the temperature observation value of future rainfall, the third target dominated solution number corresponding to the barometric pressure observation value of future rainfall, and the fourth target dominated solution number corresponding to the water level fullness observation value of future rainfall are determined based on the future rainfall weather and water level fullness set, and the method comprises the following steps: Selecting a parameter value from the future rainfall weather and water level fullness set at random, wherein the parameter value is any one of the tropospheric delay error observation value of future rainfall, the temperature observation value of future rainfall, and the barometric pressure observation value of future rainfall; Comparing the parameter value with other parameter values of the same type in sequence; Based on the comparison result, the corresponding available parameter value is determined, and the corresponding target dominated solution number is calculated, wherein the comparison result corresponding to the tropospheric delay error observation value of future rainfall is greater than other tropospheric delay error observation values of future rainfall, the comparison result corresponding to the water level fullness observation value of future rainfall is greater than other water level fullness observation values of future rainfall, the comparison result corresponding to the temperature observation value of future rainfall is less than other temperature observation values of future rainfall, and the comparison result corresponding to the barometric pressure observation value of future rainfall is less than other barometric pressure observation values of future rainfall.

5. A GNSS-based rainwater sewer network drainage capacity early warning device, characterized in that, The GNSS-based rainwater pipe network drainage capacity early warning device comprises: An acquisition module is configured to acquire real-time tropospheric delay error observation values of ground-based GNSS, real-time temperature observation values and barometric pressure observation values of multiple ground meteorological stations, and real-time water level fullness observation values of multiple key nodes of a rainwater pipe network. A processing module is configured to construct a weather and water level fullness set according to the real-time tropospheric delay error observation values, the real-time temperature observation values and barometric pressure observation values, and the real-time water level fullness observation values. An identification module is configured to predict whether it will rain in the future based on the real-time tropospheric delay error observation values of the GNSS, the real-time temperature observation values, and the barometric pressure observation values by using an AI model. The processing module is configured to acquire a future rainfall weather and water level fullness set if it is predicted that it will rain in the future. An early warning module is configured to perform early warning on the drainage capacity of the rainwater pipe network based on the future rainfall weather and water level fullness set. The early warning module is further configured to determine the first target dominated solution number corresponding to the tropospheric delay error observation value of future rainfall, the second target dominated solution number corresponding to the temperature observation value of future rainfall, the third target dominated solution number corresponding to the barometric pressure observation value of future rainfall, and the fourth target dominated solution number corresponding to the water level fullness observation value of future rainfall based on the future rainfall weather and water level fullness set. The number of solutions dominated by the first target, the number of solutions dominated by the second target, the number of solutions dominated by the third target, and the number of solutions dominated by the fourth target are used to warn the drainage capacity of the rainwater pipe network.

6. The GNSS-based rainwater sewer network drainage capacity early warning device of claim 5, wherein, The processing module is configured to obtain a rainfall classification set after identifying all key nodes of the rainwater pipe network by using the AI model, and obtain key node data of the rainwater pipe network where rainfall will occur in the future based on the identification result; The meteorological and water level fullness set where rainfall will occur in the future is obtained based on the meteorological and water level fullness set corresponding to the rainfall classification set and the key node data of the rainwater pipe network where rainfall will occur in the future.

7. The GNSS-based rainwater sewer network drainage capacity early warning device of claim 5, wherein, The device further comprises a construction module. The construction module is configured to input historical tropospheric delay error observation values of the ground-based GNSS and historical temperature observation values and historical air pressure observation values of a plurality of ground meteorological stations into a to-be-trained AI model to obtain rainfall prediction results output by the to-be-trained AI model; The rainfall prediction results output by the to-be-trained AI model are compared with historical rainfall results corresponding to the historical tropospheric delay error observation values, the historical temperature observation values, and the historical air pressure observation values; The to-be-trained AI model is trained based on the comparison result to obtain a trained AI model.

8. A GNSS-based rainwater sewer network drainage capacity early warning device, characterized by, The GNSS-based rainwater pipe network drainage capacity warning device comprises a memory, a processor, and a GNSS-based rainwater pipe network drainage capacity warning program stored on the memory and executable on the processor, and the GNSS-based rainwater pipe network drainage capacity warning program is configured to implement the steps of the GNSS-based rainwater pipe network drainage capacity warning method according to any one of claims 1 to 5.

Images