An intelligent water conservancy early warning method and system based on digital twin

Abstract

The present invention discloses an intelligent water conservancy early warning method and system based on digital twins, which relates to the technical field of data processing. The method includes: preprocessing equipment maintenance data, flow data and environmental data; constructing a twin model and a deduction model based on the equipment maintenance data, flow data and environmental data; conducting a flood outbreak uncertainty analysis based on the flow data and environmental data; conducting a confluence evolution analysis based on the flow data and environmental data; determining the flood outbreak location based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, and determining the pressure that the water conservancy equipment needs to withstand; generating a compressive performance parameter based on stress analysis combined with a structural finite element model and the equipment maintenance data; determining the compressive performance parameter of the target area, comparing it with the pressure that needs to be borne, and judging whether to issue an early warning message. The present invention realizes timely early warning of water conservancy and the intelligence of water conservancy early warning, so that flood early warning can achieve a more ideal effect.

Description

Technical Field

[0001] The present invention mainly relates to the field of data processing technology, and in particular to an intelligent water conservancy early warning method and system based on digital twins. Background Art

[0002] Water conservancy facilities are an important part of economic infrastructure. They play an irreplaceable and important role in flood control safety, rational use of water resources, and ecological environmental protection. Therefore, early warning of water conservancy facilities is particularly important. Digital twin is a digital mapping technology that reflects the entire life cycle of an entity, which has gradually been applied to water conservancy early warning. In the existing water conservancy early warning methods, due to the randomness of flood outbreaks, uncertainty analysis is required. At present, uncertainty analysis is mainly carried out by non-statistical methods, but the error of this method is too large to obtain reliable flood outbreak uncertainty analysis results; at the same time, the current water conservancy early warning method lacks the evolution analysis of confluence, resulting in the inability to accurately determine the location of the flood outbreak, and the pressure that the water conservancy equipment needs to bear cannot be accurately determined, so that the reliability of the water conservancy early warning does not meet the expected requirements. At the same time, the compressive performance of existing water conservancy equipment is only analyzed by structural parameters, resulting in the obtained compressive performance being too deviated from the actual situation, which has a great impact on the judgment of water conservancy early warning. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides an intelligent water conservancy early warning method and system based on digital twins, which can realize timely early warning of water conservancy and intelligent water conservancy early warning, so that water conservancy early warning can achieve more ideal results.

[0004] In order to solve the above technical problems, the present invention provides an intelligent water conservancy early warning method based on digital twins, the method comprising:

[0005] Collecting equipment maintenance data, flow data and environmental data of water conservancy equipment, and preprocessing the equipment maintenance data, flow data and environmental data to obtain preprocessed equipment maintenance data, flow data and environmental data;

[0006] Build twin models and deduction models of water conservancy equipment based on pre-processed equipment maintenance data, flow data and environmental data;

[0007] Conduct flood outbreak uncertainty analysis based on preprocessed flow data and environmental data to obtain flood outbreak uncertainty analysis results;

[0008] Based on the pre-processed flow data and environmental data combined with the twin model and the deduction model, a confluence evolution analysis is performed to obtain a confluence evolution analysis result;

[0009] Determine the flood outbreak location based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, and determine the pressure that the water conservancy equipment needs to withstand at the flood outbreak location;

[0010] Construct a structural finite element model of the water conservancy equipment, perform a compressive analysis based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data, and obtain compressive performance parameters of each area of ​​the water conservancy equipment;

[0011] Based on the flood outbreak location, the compressive performance parameters of each area of ​​the water conservancy equipment are used to determine the compressive performance parameters of the target area, and the compressive performance parameters of the target area are compared with the required pressure to obtain a comparison result, and based on the comparison result, it is determined whether it is necessary to issue an early warning information.

[0012] Optionally, the preprocessing of the equipment maintenance data, flow data and environmental data to obtain the preprocessed equipment maintenance data, flow data and environmental data includes:

[0013] Performing outlier removal processing on the equipment maintenance data, flow data, and environmental data to obtain the equipment maintenance data, flow data, and environmental data after the outlier removal processing;

[0014] The equipment maintenance data, flow data and environmental data after outlier removal are standardized to obtain pre-processed equipment maintenance data, flow data and environmental data.

[0015] Optionally, the twin model and deduction model of the water conservancy equipment are constructed based on the pre-processed equipment maintenance data, flow data and environmental data, including:

[0016] The hydrological and hydrodynamic model is constructed using the digital twin database based on the preprocessed flow data and environmental data;

[0017] Based on the pre-processed equipment maintenance data, flow data and environmental data, a fusion algorithm is used to construct a water conservancy equipment boundary field, and a twin model is constructed based on the water conservancy equipment boundary field and a hydrological and hydrodynamic model;

[0018] Performing hidden danger evolution based on the preprocessed equipment maintenance data to obtain hidden danger evolution information, and determining the possible failure distribution of water conservancy equipment based on the hidden danger evolution information;

[0019] Based on the pre-processed equipment maintenance data, flow data and environmental data, hidden danger consequences are simulated to obtain hidden danger consequence simulation information, and a simulation model is constructed based on the virtual engine using the possible accident distribution of water conservancy equipment and hidden danger consequence simulation information.

[0020] Optionally, performing flood outbreak uncertainty analysis based on the preprocessed flow data and environmental data to obtain flood outbreak uncertainty analysis results includes:

[0021] Acquire a flood outbreak uncertainty analysis record data set, and perform numerical processing on the flood outbreak uncertainty analysis record data set to obtain a numerical flood outbreak uncertainty analysis record data set;

[0022] Constructing a characteristic data matrix based on the numerical flood outbreak uncertainty analysis record data set, and generating a number of flood outbreak influencing factors based on the characteristic data matrix;

[0023] Generate corresponding flood outbreak impact characteristic values ​​based on a number of flood outbreak impact factors, and perform correlation analysis on a number of flood outbreak impact factors based on the flood outbreak impact characteristic values ​​to obtain factor correlation relationships;

[0024] An uncertainty analysis topological network is generated based on the factor association relationship, uncertainty is deduced using Bayesian theorem based on the preprocessed flow data and environmental data to obtain uncertainty deduction parameters, and flood outbreak uncertainty analysis is performed using the uncertainty analysis topological network based on the uncertainty deduction parameters to obtain flood outbreak uncertainty analysis results.

[0025] Optionally, the confluence evolution analysis is performed based on the preprocessed flow data and environmental data in combination with the twin model and the deduction model to obtain the confluence evolution analysis result, including:

[0026] Generate a water depth-time grid matrix based on the twin model combined with the preprocessed flow data and environmental data;

[0027] Generate a confluence grid based on the deduction model combined with preprocessed flow data and environmental data, perform neighborhood iteration analysis on the confluence grid, and obtain a confluence flow direction;

[0028] Based on the water depth-time grid matrix and the confluence flow direction, a confluence evolution analysis is performed in combination with a cellular automaton to obtain a confluence evolution analysis result.

[0029] Optionally, the determining of the flood outbreak location based on the flood outbreak uncertainty analysis result and the confluence evolution analysis result includes:

[0030] Based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, water level trend change analysis and water level sequence significance analysis are performed to obtain water level trend change information and water level sequence significance information;

[0031] The flood outbreak location is determined based on the water level trend change information and the water level sequence significance information combined with the water level prediction model.

[0032] Optionally, the step of determining the pressure that the water conservancy equipment needs to withstand at the flood outbreak location includes:

[0033] Acquire a historical pressure parameter set and a historical water conservancy equipment environment information set, perform correlation analysis on the historical pressure parameter set and the historical water conservancy equipment environment information set, and obtain a pressure correlation parameter;

[0034] The pressure that the water conservancy equipment needs to withstand at the flood outbreak location is determined based on the pressure-bearing correlation parameter.

[0035] Optionally, the construction of a structural finite element model of the water conservancy equipment, performing a compressive analysis based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data to obtain compressive performance parameters of each area of ​​the water conservancy equipment, includes:

[0036] Based on the structural parameters of the water conservancy equipment, the structural finite element model of the water conservancy equipment is constructed using finite element analysis software;

[0037] Performing finite element static calculation based on the structural finite element model to obtain stress in each area of ​​the water conservancy equipment, and performing self-vibration characteristic analysis based on the structural finite element model to obtain self-vibration characteristic information;

[0038] Based on the stress and self-vibration characteristic information of each area of ​​the water conservancy equipment combined with the pre-processed equipment maintenance data, displacement response and stress response analysis are performed to obtain the target displacement response and target stress response. Based on the target displacement response and target stress response, the compressive resistance analysis of each area of ​​the water conservancy equipment is performed to obtain the compressive resistance performance parameters of each area of ​​the water conservancy equipment.

[0039] Optionally, judging whether it is necessary to issue warning information based on the comparison result includes:

[0040] If the difference between the pressure resistance performance parameter of the target area and the required pressure reaches the preset threshold range, an early warning message is issued.

[0041] In addition, the present invention also provides an intelligent water conservancy early warning system based on digital twins, the system comprising:

[0042] Data collection and preprocessing module: used to collect equipment maintenance data, flow data and environmental data of water conservancy equipment, and preprocess the equipment maintenance data, flow data and environmental data to obtain the preprocessed equipment maintenance data, flow data and environmental data;

[0043] Model building module: used to build twin models and deduction models of water conservancy equipment based on pre-processed equipment maintenance data, flow data and environmental data;

[0044] Flood outbreak uncertainty analysis module: used to perform flood outbreak uncertainty analysis based on preprocessed flow data and environmental data to obtain flood outbreak uncertainty analysis results;

[0045] Confluence evolution analysis module: used to perform confluence evolution analysis based on the pre-processed flow data and environmental data in combination with the twin model and the deduction model to obtain the confluence evolution analysis results;

[0046] Flood outbreak location and pressure determination module: used to determine the flood outbreak location based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, and determine the pressure that the water conservancy equipment needs to withstand at the flood outbreak location;

[0047] Compression analysis module: used to construct a structural finite element model of water conservancy equipment, perform compression analysis based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data, and obtain compression performance parameters of each area of ​​the water conservancy equipment;

[0048] Early warning judgment module: used to determine the compressive performance parameters of the target area based on the flood outbreak location using the compressive performance parameters of each area of ​​the water conservancy equipment, and compare the compressive performance parameters of the target area with the required pressure to obtain a comparison result, and judge whether it is necessary to issue an early warning information based on the comparison result.

[0049] In an embodiment of the present invention, uncertainty analysis of flood outbreaks is performed using an uncertainty analysis topological network based on uncertainty derivation parameters generated by preprocessed flow data and environmental data, thereby improving the accuracy of uncertainty analysis of flood outbreaks and being able to more effectively and comprehensively quantify the uncertainty of flood outbreaks. Based on the water depth-time grid matrix generated by the twin model combined with the preprocessed flow data and environmental data and the confluence direction generated by the deduction model combined with the preprocessed flow data and environmental data, combined with cellular automata, confluence evolution analysis is performed, and the analysis of confluence evolution is added, so that a dynamic confluence evolution analysis process can be achieved. Confluence evolution analysis can achieve sudden warning of flood outbreaks and avoid untimely water conservancy warnings. Based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, the flood outbreak location is determined, and the pressure that the water conservancy equipment needs to withstand at the flood outbreak location is determined, so that the final determined flood outbreak location and the required pressure are more accurate, and high-precision and high-reliability water conservancy warnings can be achieved. Compression analysis based on stress analysis combined with structural finite element model and pre-processed equipment maintenance data can obtain the compressive performance parameters of each area of ​​water conservancy equipment more comprehensively and accurately, and compare them with the pressure that the water conservancy equipment needs to withstand to determine whether it is necessary to issue an early warning information, thereby realizing timely and intelligent early warning of water conservancy, and making flood warning achieve more ideal results. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a flow chart of an intelligent water conservancy early warning method based on digital twins in an embodiment of the present invention;

[0052] Figure 2 It is a schematic diagram of the structural composition of the intelligent water conservancy early warning system based on digital twins in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Embodiment 1

[0055] See also Figure 1 , Figure 1 It is a flow chart of the intelligent water conservancy early warning method based on digital twin in an embodiment of the present invention.

[0056] like Figure 1 As shown, an intelligent water conservancy early warning method based on digital twins includes:

[0057] S11: collecting equipment maintenance data, flow data and environmental data of water conservancy equipment, and preprocessing the equipment maintenance data, flow data and environmental data to obtain preprocessed equipment maintenance data, flow data and environmental data;

[0058] In the specific implementation process of the present invention, the equipment maintenance data, flow data and environmental data are preprocessed to obtain the preprocessed equipment maintenance data, flow data and environmental data, including: performing outlier removal processing on the equipment maintenance data, flow data and environmental data to obtain the equipment maintenance data, flow data and environmental data after the outlier removal processing; performing standardization processing on the equipment maintenance data, flow data and environmental data after the outlier removal processing to obtain the preprocessed equipment maintenance data, flow data and environmental data.

[0059] Specifically, the equipment maintenance data, flow data and environmental data of the water conservancy equipment are continuously collected. The equipment maintenance data includes the structural maintenance information and structural aging information of the water conservancy equipment, the flow data includes the flow velocity, water level, etc., and the environmental data includes the meteorological data and terrain data, etc. The equipment maintenance data, flow data and environmental data are processed for outliers removal, the equipment maintenance data, flow data and environmental data are preliminarily detected for outliers using the median method, and the detected outliers are replaced with 0 values. The equipment maintenance data, flow data and environmental data after the preliminarily detected outliers are finely detected for outliers using the ensemble empirical mode decomposition method, and the detected outliers are replaced with 0 values. The local curve fitting method is used to fill the 0 values, that is, the outliers are corrected, and the equipment maintenance data, flow data and environmental data after the outlier removal processing can be obtained. The equipment maintenance data, flow data and environmental data after outlier removal are standardized, key information in the equipment maintenance data, flow data and environmental data after outlier removal is detected, data features in the key information are extracted, and feature levels corresponding to the data features are determined. According to the data features and feature levels, several corresponding alternative mapping relationships are obtained, and the confidence corresponding to each alternative mapping relationship is calculated based on the probability distribution function. The alternative mapping relationship with the highest confidence is used as the corresponding target mapping relationship. The equipment maintenance data, flow data and environmental data after outlier removal are standardized and mapped using the target mapping relationship based on the preset graph structure. After completing the standardized mapping, the pre-processed equipment maintenance data, flow data and environmental data can be obtained.

[0060] S12: Build twin models and deduction models of water conservancy equipment based on pre-processed equipment maintenance data, flow data and environmental data;

[0061] In the specific implementation process of the present invention, the twin model and deduction model of water conservancy equipment based on pre-processed equipment maintenance data, flow data and environmental data are constructed, including: constructing a hydrological and hydrodynamic model based on the pre-processed flow data and environmental data using a digital twin database; constructing a water conservancy equipment boundary field based on the pre-processed equipment maintenance data, flow data and environmental data using a fusion algorithm, and constructing a twin model based on the water conservancy equipment boundary field and the hydrological and hydrodynamic model; performing hidden danger evolution based on the pre-processed equipment maintenance data to obtain hidden danger evolution information, and determining the possible accident distribution of water conservancy equipment based on the hidden danger evolution information; performing hidden danger consequence deduction based on the pre-processed equipment maintenance data, flow data and environmental data to obtain hidden danger consequence deduction information, and constructing a deduction model based on the virtual engine using the possible accident distribution of water conservancy equipment and the hidden danger consequence deduction information.

[0062] Specifically, a hydrological and hydrodynamic model is constructed based on the preprocessed flow data and environmental data using the digital twin database, and a hydrological and hydrodynamic simulation is carried out based on the preprocessed flow data and environmental data using the digital twin database. The water level simulation value is calculated through the Nash efficiency coefficient and the membership function, and the assimilated data is obtained through the digital twin database. The model parameters are optimized and selected based on the water level simulation value and the assimilated data using the Euclidean patching schedule, and the optimized model parameters are obtained. The hydrological and hydrodynamic model is constructed based on the optimized model parameters. The boundary field of the water conservancy equipment is constructed based on the preprocessed equipment maintenance data, flow data and environmental data using the fusion algorithm, and the preprocessed equipment maintenance data, flow data and environmental data are compared with the assimilated data in the digital twin database, and the deviation between the two is calculated. The boundary field of the water conservancy equipment is constructed by combining the calculated deviation with the fusion algorithm composed of the successive optimization algorithm and the extended Kalman filter algorithm. Based on the boundary field and hydrological and hydrodynamic model of the water conservancy equipment, a twin model is constructed. The boundary field and hydrological and hydrodynamic model of the water conservancy equipment are used by the state differential simulator to map the three-dimensional model in a multi-graphics processor distributed computing environment to obtain a twin model. The digital twin technology is a technology that uses various information technology means and physical entities to map and synchronize to achieve real-time monitoring, analysis and simulation of physical objects. Based on the pre-processed equipment maintenance data, hidden dangers are evolved to obtain hidden danger evolution information. Based on the structural aging information in the pre-processed equipment maintenance data, damage aging analysis is performed. According to the damage aging analysis results, simulated evolution is performed to obtain hidden danger evolution information; and based on the hidden danger evolution information, the possible accident distribution of the water conservancy equipment is determined. According to the hidden danger evolution information, adverse working condition trial calculation and accident analogy are performed. According to the hidden danger evolution information, possible accident paths are determined according to the adverse working condition trial calculation results and accident analogy results, and the possible accident distribution of the water conservancy equipment is determined according to the possible accident paths. Based on the pre-processed equipment maintenance data, flow data and environmental data, the consequence deduction of hidden dangers is carried out. The consequence reasoning is carried out using the interactive state space method and the recursive approximate least squares method through the pre-processed equipment maintenance data, flow data and environmental data to obtain the consequence reasoning information. The empirical mode decomposition is carried out according to the consequence reasoning information to obtain the consequence reasoning information after the empirical mode decomposition. The consequence deduction of hidden dangers is carried out using the support vector machine model according to the consequence reasoning information after the empirical mode decomposition to obtain the consequence deduction information of hidden dangers. The consequence deduction information of hidden dangers may include the probability and regional information of damage caused by excessive impact on water conservancy equipment. Based on the virtual engine, the deduction model is constructed using the possible accident distribution of water conservancy equipment and the deduction information of hidden danger consequences. Through the model component of the virtual engine, the possible accident distribution of water conservancy equipment and the deduction of hidden danger consequences can be connected to the data interface of the interactive component to construct the deduction model.

[0063] S13: Perform flood outbreak uncertainty analysis based on the preprocessed flow data and environmental data to obtain flood outbreak uncertainty analysis results;

[0064] In the specific implementation process of the present invention, the flood outbreak uncertainty analysis is performed based on the pre-processed flow data and environmental data to obtain the flood outbreak uncertainty analysis results, including: obtaining a flood outbreak uncertainty analysis record data set, and digitizing the flood outbreak uncertainty analysis record data set to obtain a digitized flood outbreak uncertainty analysis record data set; constructing a characteristic data matrix based on the digitized flood outbreak uncertainty analysis record data set, and generating a number of flood outbreak influencing factors based on the characteristic data matrix; generating corresponding flood outbreak impact characteristic values ​​based on a number of flood outbreak influencing factors, and performing correlation analysis on a number of flood outbreak influencing factors based on the flood outbreak impact characteristic values ​​to obtain factor correlation relationships; generating an uncertainty analysis topological network based on the factor correlation relationships, performing uncertainty derivation based on the pre-processed flow data and environmental data using Bayesian theorem to obtain uncertainty derivation parameters, and performing flood outbreak uncertainty analysis based on the uncertainty derivation parameters using the uncertainty analysis topological network to obtain flood outbreak uncertainty analysis results.

[0065] Specifically, a flood outbreak uncertainty analysis record data set is obtained from a database, and the flood outbreak uncertainty analysis record data set includes historical flood outbreak uncertainty quantification and flood outbreak water volume and flow rate. The flood outbreak uncertainty analysis record data set is numerically processed. Before data analysis, the non-numerical data in the data set needs to be converted into numerical data for subsequent analysis and processing, that is, numerical processing. Label coding can be used to convert the category data in the flood outbreak uncertainty analysis record data set into continuous integer coding, thereby realizing the numerical conversion in the data set and obtaining the numerical flood outbreak uncertainty analysis record data set. A feature data matrix is ​​constructed based on the numerical flood outbreak uncertainty analysis record data set, and a feature data set is obtained by using a feature extraction algorithm through the numerical flood outbreak uncertainty analysis record data set. Each feature data in the feature data set is decentralized to obtain a number of decentralized feature data, and a feature average value is calculated for a number of decentralized feature data. A new feature data set is constructed based on the feature average value, and a covariance matrix is ​​calculated based on the new feature data set. The eigenvalues ​​and eigenvectors of the covariance matrix are calculated, and a feature data matrix is ​​constructed based on the eigenvalues ​​and eigenvectors of the covariance matrix. Based on the feature data matrix, several flood outbreak influencing factors are generated. Feature interaction based on the attention mechanism is performed through the feature data matrix. The feature interaction based on the attention mechanism can automatically adjust the weight of the features according to the importance of different features, obtain dependency features, and generate several flood outbreak influencing factors according to the dependency features. Based on several flood outbreak influencing factors, corresponding flood outbreak impact characteristic values ​​are generated, and each flood outbreak influencing factor is evaluated. The flood outbreak influencing factor has a corresponding flood outbreak impact assessment coefficient, so the corresponding flood outbreak impact characteristic value can be obtained through its flood outbreak impact assessment coefficient. Based on the flood outbreak impact characteristic value, several flood outbreak influencing factors are analyzed for correlation relationships, and several flood outbreak influencing factors are used as nodes. A dependency matrix is ​​constructed according to the dependency features and the flood outbreak impact characteristic values, and a directed graph is generated according to the dependency matrix. The dependency hierarchy relationship between nodes is analyzed according to the directed graph, and the factor correlation relationship can be obtained. Based on the factor association relationship, an uncertainty analysis topological network is generated, and several flood outbreak influencing factors are connected according to the factor association relationship. The corresponding flood outbreak impact characteristic values ​​are used as the connection strength between the factors. After several flood outbreak influencing factors are connected, the uncertainty analysis topological network can be obtained.Based on the pre-processed flow data and environmental data, Bayesian theorem is used to derive uncertainty. Based on the pre-processed flow data and environmental data, Bayesian joint probability calculation is performed using multivariate Gaussian distribution to obtain Bayesian joint probability. According to the Bayesian joint probability, posterior parameters are calculated using likelihood function and Taylor formula. According to the posterior parameters, uncertainty is derived using preset rate deviation combined with Heaviside function. Heaviside function has stronger adaptability to change and variation derivation. Uncertainty derivation parameters are obtained. Uncertainty derivation parameters may include uncertainty quantification and quantitative error. Based on the uncertainty derivation parameters, the uncertainty analysis topological network is used to perform flood outbreak uncertainty analysis. The uncertainty derivation parameters are input into the uncertainty analysis topological network to obtain the flood outbreak uncertainty analysis result, which is the flood outbreak uncertainty quantitative probability. Based on the uncertainty derivation parameters generated by the pre-processed flow data and environmental data, the uncertainty analysis topological network is used to perform flood outbreak uncertainty analysis, which improves the accuracy of flood outbreak uncertainty analysis and can more effectively and comprehensively quantify the uncertainty of flood outbreak.

[0066] S14: performing a confluence evolution analysis based on the preprocessed flow data and environmental data in combination with the twin model and the deduction model to obtain a confluence evolution analysis result;

[0067] In the specific implementation process of the present invention, the confluence evolution analysis is performed based on the preprocessed flow data and environmental data in combination with the twin model and the deduction model to obtain the confluence evolution analysis result, including: generating a water depth-time grid matrix based on the twin model in combination with the preprocessed flow data and environmental data; generating a confluence grid based on the deduction model in combination with the preprocessed flow data and environmental data, performing neighborhood iteration analysis on the confluence grid to obtain the confluence flow direction; performing confluence evolution analysis based on the water depth-time grid matrix and the confluence flow direction in combination with a cellular automaton to obtain the confluence evolution analysis result.

[0068] Specifically, a water depth-time grid matrix is ​​generated based on the twin model combined with the preprocessed flow data and environmental data, and the water depth and water level information that changes with time is generated according to the hydrological and hydrodynamic model in the twin model combined with the preprocessed flow data and environmental data. Each frame of data in the water depth and water level information that changes with time is used as a matrix element to form a water depth-time grid matrix. The construction of the water depth-time grid matrix can improve the evolution efficiency and accuracy. Based on the deduction model combined with the preprocessed flow data and environmental data, a confluence grid is generated. The deduction model is combined with the preprocessed flow data and environmental data to determine the initial confluence grid using a preset script, and the initial confluence grid is streamlined and optimized to obtain the final confluence grid. The confluence grid is subjected to neighborhood iteration analysis, and the confluence along-course change analysis is performed according to the confluence grid to obtain the confluence along-course change information. The grid neighborhood analysis and update iteration are performed according to the along-course change information to obtain the initial confluence flow direction, and the flow direction uniformity correction is performed using the edge neighborhood and the corner neighborhood according to the initial confluence flow direction to obtain the final confluence flow direction. Based on the water depth-time grid matrix and the confluence flow direction, the confluence evolution analysis is performed in combination with cellular automata, the cell state is determined, the neighborhood relationship of the cell is established, and the conversion rule of the cell state is established. According to the neighborhood relationship of the cell and the conversion rule of the cell state, a cellular automaton simulation model is established, and the cellular scale effect analysis, cell splitting and cell merging are performed on the cellular automaton simulation model to obtain an optimized cellular automaton simulation model. According to the optimized cellular automaton simulation model, the confluence path analysis is performed using the water depth-time grid matrix and the confluence flow direction to obtain the confluence dynamic path. The process evolution of the confluence is performed based on the confluence dynamic path to obtain the confluence evolution analysis result, that is, the time, speed and water level of the confluence. The scale effect of the confluence can be effectively analyzed by cellular automata, so that the final result has a smaller error with the actual water situation, and the water machine aggregation evolution process can be analyzed more intuitively, while shortening the confluence evolution analysis time. Based on the water depth-time grid matrix generated by the twin model combined with the preprocessed flow data and environmental data, and the confluence direction generated by the deduction model combined with the preprocessed flow data and environmental data, the confluence evolution analysis is performed in combination with cellular automata. The confluence evolution analysis is added to achieve a dynamic confluence evolution analysis process. The confluence evolution analysis can realize sudden early warning of flood outbreaks and avoid untimely water conservancy early warnings.

[0069] S15: Determine the flood outbreak location based on the flood outbreak uncertainty analysis result and the confluence evolution analysis result, and determine the pressure that the water conservancy equipment needs to withstand at the flood outbreak location;

[0070] In the specific implementation process of the present invention, the method of determining the flood outbreak location based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results includes: performing water level trend change analysis and water level sequence significance analysis based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results to obtain water level trend change information and water level sequence significance information; determining the flood outbreak location based on the water level trend change information and water level sequence significance information in combination with a water level prediction model.

[0071] Furthermore, determining the pressure that the water conservancy equipment needs to withstand at the flood outbreak location includes: obtaining a historical pressure parameter set and a historical water conservancy equipment environmental information set, performing correlation analysis on the historical pressure parameter set and the historical water conservancy equipment environmental information set to obtain a pressure correlation parameter; and determining the pressure that the water conservancy equipment needs to withstand at the flood outbreak location based on the pressure correlation parameter.

[0072] Specifically, based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, water level trend change analysis and water level sequence significance analysis are performed. Based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, the water level trend change analysis is performed using the univariate regression analysis method to obtain water level trend change information. Based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, the water level sequence significance analysis is performed using the Mann-Kendall method to obtain water level sequence significance information. In the water level trend change analysis and water level sequence significance analysis, a machine learning algorithm is used for auxiliary analysis. Based on the water level trend change information and water level sequence significance information, the flood outbreak location is determined in combination with a water level prediction model. The water level prediction model is a convergence model obtained by inputting a sample data set into a deep neural network model for training. The historical pressure parameter set and the historical water conservancy equipment environment information set are obtained from the database. The historical pressure parameter set is the pressure that the water conservancy equipment in the past suffered at the corresponding flood outbreak location during the flood outbreak and the heterogeneous vector composed of the pressure suffered. The historical water flow equipment environment information set is the water level, flow and meteorological data of the water conservancy equipment during the past flood outbreak. The historical pressure parameter set and the historical water conservancy equipment environment information set are subjected to correlation analysis, and the heterogeneous vectors in the historical water conservancy equipment environment information set and the historical pressure parameter set are dimensionless processed to obtain the dimensionless historical water conservancy equipment environment information set and the dimensionless heterogeneous vectors, and the correlation coefficient between the dimensionless historical water conservancy equipment environment information set and the dimensionless heterogeneous vectors is calculated. The influence correlation of the dimensionless historical water conservancy equipment environment information set on the dimensionless heterogeneous vectors is calculated according to the correlation coefficient, and the influence correlation is used as the pressure correlation parameter, that is, the pressure correlation parameter is obtained. Through the correlation analysis, the pressure that the water conservancy equipment needs to bear can be more accurately determined, and the accuracy and pertinence of the early warning can be improved. The pressure that the water conservancy equipment needs to bear at the flood outbreak location is determined based on the pressure correlation parameter. Thereby, the final determined flood outbreak location and the required pressure can be more accurate, and a high-precision and high-reliability water conservancy early warning can be achieved.

[0073] S16: constructing a structural finite element model of the water conservancy equipment, performing a compressive analysis based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data, and obtaining compressive performance parameters of each area of ​​the water conservancy equipment;

[0074] In the specific implementation process of the present invention, the structural finite element model of the water conservancy equipment is constructed, and a compressive analysis is performed based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data to obtain the compressive performance parameters of each area of ​​the water conservancy equipment, including: constructing the structural finite element model of the water conservancy equipment using finite element analysis software based on the structural parameters of the water conservancy equipment; performing finite element static calculation based on the structural finite element model to obtain the stress in each area of ​​the water conservancy equipment, and performing self-vibration characteristic analysis based on the structural finite element model to obtain self-vibration characteristic information; performing displacement response and stress response analysis based on the stress and self-vibration characteristic information of each area of ​​the water conservancy equipment combined with the pre-processed equipment maintenance data to obtain the target displacement response and target stress response, and performing compressive analysis of each area of ​​the water conservancy equipment based on the target displacement response and target stress response to obtain the compressive performance parameters of each area of ​​the water conservancy equipment.

[0075] Specifically, a structural finite element model of the water conservancy equipment is constructed using finite element analysis software based on the structural parameters of the water conservancy equipment. Finite element static calculation is performed based on the structural finite element model, and static calculation is performed based on the structural finite element model using preset boundary conditions and preset loads to obtain several directional displacement components and several stress components, and the several directional displacement components and several stress components are superimposed to obtain the stress of each area of ​​the water conservancy equipment. Based on the structural finite element model, a self-vibration characteristic analysis is performed, and a potential fluid unit is used to use the structural finite element model to analyze the water flow and water pressure effects. According to the preset coupling boundary, an energy transfer analysis of the water flow dynamics and the structure of the water conservancy equipment is performed to obtain the energy transfer analysis results. According to the energy transfer analysis results and the water flow and water pressure effect analysis, a self-vibration characteristic analysis is performed to obtain the self-vibration characteristic information. Based on the stress and self-vibration characteristic information of each area of ​​the water conservancy equipment combined with the pre-processed equipment maintenance data, the displacement response and stress response analysis are performed. Based on the stress and self-vibration characteristic information of each area of ​​the water conservancy equipment combined with the pre-processed equipment maintenance data, the normal displacement, compressive strength, elastic modulus and ultimate strain of each area of ​​the water conservancy equipment are calculated. According to the normal displacement, compressive strength, elastic modulus and ultimate strain of each area of ​​the water conservancy equipment, the target displacement response and target stress response are calculated using a preset interaction model, and the target displacement response and target stress response can be obtained. Based on the target displacement response and target stress response, the compression analysis of each area of ​​the water conservancy equipment is performed. According to the target displacement response and target stress response, the ultimate strain and ultimate elastic strain of each area of ​​the water conservancy equipment under pressure and the ultimate bearing value are analyzed, and then the compression performance parameters of each area of ​​the water conservancy equipment are obtained. Compression analysis based on stress analysis combined with the structural finite element model and the pre-processed equipment maintenance data can obtain the compression performance parameters of each area of ​​the water conservancy equipment more comprehensively and accurately.

[0076] S17: Based on the flood outbreak location, the compressive performance parameters of each area of ​​the water conservancy equipment are used to determine the compressive performance parameters of the target area, and the compressive performance parameters of the target area are compared with the required pressure to obtain a comparison result, and based on the comparison result, it is determined whether it is necessary to issue an early warning information.

[0077] In the specific implementation of the present invention, judging whether it is necessary to issue a warning message based on the comparison result includes: if the difference between the pressure resistance performance parameter of the target area and the required pressure reaches a preset threshold range, issuing a warning message.

[0078] Specifically, determine the pressure resistance performance parameters of the water conservancy equipment at the flood outbreak location, that is, determine the ultimate pressure bearing value of the target area, compare the pressure resistance performance parameters of the target area with the required pressure, compare the ultimate pressure bearing value with the pressure that the water conservancy equipment needs to withstand at the flood outbreak location, perform a difference operation between the ultimate pressure bearing value and the pressure that the water conservancy equipment needs to withstand at the flood outbreak location, obtain the corresponding difference, compare the corresponding difference with the preset threshold interval, if the difference reaches the preset threshold interval, it means that the pressure borne by the water conservancy equipment is close to the ultimate pressure bearing value, and it is necessary to issue an early warning message, if the corresponding difference reaches the preset threshold interval, it is not necessary to issue an early warning message. In this way, it is possible to respond to flood outbreaks in a timely manner and achieve the reliability of water conservancy equipment's response to flood outbreaks.

[0079] In an embodiment of the present invention, uncertainty analysis of flood outbreaks is performed using an uncertainty analysis topological network based on uncertainty derivation parameters generated by preprocessed flow data and environmental data, thereby improving the accuracy of uncertainty analysis of flood outbreaks and being able to more effectively and comprehensively quantify the uncertainty of flood outbreaks. Based on the water depth-time grid matrix generated by the twin model combined with the preprocessed flow data and environmental data and the confluence direction generated by the deduction model combined with the preprocessed flow data and environmental data, combined with cellular automata, confluence evolution analysis is performed, and the analysis of confluence evolution is added, so that a dynamic confluence evolution analysis process can be achieved. Confluence evolution analysis can achieve sudden warning of flood outbreaks and avoid untimely water conservancy warnings. Based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, the flood outbreak location is determined, and the pressure that the water conservancy equipment needs to withstand at the flood outbreak location is determined, so that the final determined flood outbreak location and the required pressure are more accurate, and high-precision and high-reliability water conservancy warnings can be achieved. Compression analysis based on stress analysis combined with structural finite element model and pre-processed equipment maintenance data can obtain the compressive performance parameters of each area of ​​water conservancy equipment more comprehensively and accurately, and compare them with the pressure that the water conservancy equipment needs to withstand to determine whether it is necessary to issue an early warning information, thereby realizing timely and intelligent early warning of water conservancy, and making flood warning achieve more ideal results.

[0080] Embodiment 2

[0081] See also Figure 2 , Figure 2 It is a schematic diagram of the structural composition of the intelligent water conservancy early warning system based on digital twins in an embodiment of the present invention.

[0082] like Figure 2 As shown, an intelligent water conservancy early warning system based on digital twins, the system includes:

[0083] Data collection and preprocessing module 21: used to collect equipment maintenance data, flow data and environmental data of water conservancy equipment, and preprocess the equipment maintenance data, flow data and environmental data to obtain the preprocessed equipment maintenance data, flow data and environmental data;

[0084] Model building module 22: used to build twin models and deduction models of water conservancy equipment based on pre-processed equipment maintenance data, flow data and environmental data;

[0085] Flood outbreak uncertainty analysis module 23: used to perform flood outbreak uncertainty analysis based on pre-processed flow data and environmental data to obtain flood outbreak uncertainty analysis results;

[0086] Confluence evolution analysis module 24: used to perform confluence evolution analysis based on the pre-processed flow data and environmental data in combination with the twin model and the deduction model to obtain confluence evolution analysis results;

[0087] Flood outbreak location and pressure determination module 25: used to determine the flood outbreak location based on the flood outbreak uncertainty analysis result and the confluence evolution analysis result, and determine the pressure that the water conservancy equipment needs to withstand at the flood outbreak location;

[0088] Compression analysis module 26: used to construct a structural finite element model of the water conservancy equipment, perform compression analysis based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data, and obtain compression performance parameters of each area of ​​the water conservancy equipment;

[0089] Early warning judgment module 27: used to determine the pressure resistance parameters of the target area based on the flood outbreak location using the pressure resistance parameters of each area of ​​the water conservancy equipment, and compare the pressure resistance parameters of the target area with the required pressure to obtain a comparison result, and judge whether it is necessary to issue an early warning information based on the comparison result.

[0090] In the specific implementation process of the present invention, the specific implementation method of the system item can refer to the implementation method of the above-mentioned method item, which will not be repeated here.

[0091] In an embodiment of the present invention, uncertainty analysis of flood outbreaks is performed using an uncertainty analysis topological network based on uncertainty derivation parameters generated by preprocessed flow data and environmental data, thereby improving the accuracy of uncertainty analysis of flood outbreaks and being able to more effectively and comprehensively quantify the uncertainty of flood outbreaks. Based on the water depth-time grid matrix generated by the twin model combined with the preprocessed flow data and environmental data and the confluence direction generated by the deduction model combined with the preprocessed flow data and environmental data, combined with cellular automata, confluence evolution analysis is performed, and the analysis of confluence evolution is added, so that a dynamic confluence evolution analysis process can be achieved. Confluence evolution analysis can achieve sudden warning of flood outbreaks and avoid untimely water conservancy warnings. Based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, the flood outbreak location is determined, and the pressure that the water conservancy equipment needs to withstand at the flood outbreak location is determined, so that the final determined flood outbreak location and the required pressure are more accurate, and high-precision and high-reliability water conservancy warnings can be achieved. Compression analysis based on stress analysis combined with structural finite element model and pre-processed equipment maintenance data can obtain the compressive performance parameters of each area of ​​water conservancy equipment more comprehensively and accurately, and compare them with the pressure that the water conservancy equipment needs to withstand to determine whether it is necessary to issue an early warning information, thereby realizing timely and intelligent early warning of water conservancy, and making flood warning achieve more ideal results.

[0092] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0093] In addition, the above is a detailed introduction to an intelligent water conservancy early warning method and system based on digital twins provided in an embodiment of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An intelligent water conservancy early warning method based on digital twins, characterized in that: The method comprises: Collecting equipment maintenance data, flow data and environmental data of water conservancy equipment, and preprocessing the equipment maintenance data, flow data and environmental data to obtain preprocessed equipment maintenance data, flow data and environmental data; A twin model and a deduction model of water conservancy equipment are constructed based on the pre-processed equipment maintenance data, flow data and environmental data; the specific steps of constructing the twin model and the deduction model of water conservancy equipment include: constructing a hydrological and hydrodynamic model using a digital twin database based on the pre-processed flow data and environmental data; constructing a boundary field of water conservancy equipment using a fusion algorithm based on the pre-processed equipment maintenance data, flow data and environmental data, and constructing a twin model based on the water conservancy equipment boundary field and the hydrological and hydrodynamic model; performing hidden danger evolution based on the pre-processed equipment maintenance data to obtain hidden danger evolution information, and determining the possible accident distribution of water conservancy equipment based on the hidden danger evolution information; performing hidden danger consequence deduction based on the pre-processed equipment maintenance data, flow data and environmental data to obtain hidden danger consequence deduction information, and constructing a deduction model based on the possible accident distribution of water conservancy equipment and hidden danger consequence deduction information based on the virtual engine; Conduct flood outbreak uncertainty analysis based on preprocessed flow data and environmental data to obtain flood outbreak uncertainty analysis results; Based on the pre-processed flow data and environmental data combined with the twin model and the deduction model, a confluence evolution analysis is performed to obtain a confluence evolution analysis result; Determine the flood outbreak location based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, and determine the pressure that the water conservancy equipment needs to withstand at the flood outbreak location; Construct a structural finite element model of the water conservancy equipment, perform a compressive analysis based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data, and obtain compressive performance parameters of each area of ​​the water conservancy equipment; Based on the flood outbreak location, the compressive performance parameters of each area of ​​the water conservancy equipment are used to determine the compressive performance parameters of the target area, and the compressive performance parameters of the target area are compared with the required pressure to obtain a comparison result, and based on the comparison result, it is determined whether it is necessary to issue an early warning information.

2. The intelligent water conservancy early warning method based on digital twin according to claim 1 is characterized in that: The preprocessing of the equipment maintenance data, flow data and environmental data to obtain the preprocessed equipment maintenance data, flow data and environmental data includes: Performing outlier removal processing on the equipment maintenance data, flow data, and environmental data to obtain the equipment maintenance data, flow data, and environmental data after the outlier removal processing; The equipment maintenance data, flow data and environmental data after outlier removal are standardized to obtain pre-processed equipment maintenance data, flow data and environmental data.

3. The intelligent water conservancy early warning method based on digital twin according to claim 1 is characterized in that: The flood outbreak uncertainty analysis is performed based on the pre-processed flow data and environmental data to obtain the flood outbreak uncertainty analysis results, including: Acquire a flood outbreak uncertainty analysis record data set, and perform numerical processing on the flood outbreak uncertainty analysis record data set to obtain a numerical flood outbreak uncertainty analysis record data set; Constructing a characteristic data matrix based on the numerical flood outbreak uncertainty analysis record data set, and generating a number of flood outbreak influencing factors based on the characteristic data matrix; Generate corresponding flood outbreak impact characteristic values ​​based on a number of flood outbreak impact factors, and perform correlation analysis on a number of flood outbreak impact factors based on the flood outbreak impact characteristic values ​​to obtain factor correlation relationships; An uncertainty analysis topological network is generated based on the factor association relationship, uncertainty is deduced using Bayesian theorem based on the preprocessed flow data and environmental data to obtain uncertainty deduction parameters, and flood outbreak uncertainty analysis is performed using the uncertainty analysis topological network based on the uncertainty deduction parameters to obtain flood outbreak uncertainty analysis results.

4. The intelligent water conservancy early warning method based on digital twin according to claim 1 is characterized in that: The confluence evolution analysis is performed based on the pre-processed flow data and environmental data in combination with the twin model and the deduction model to obtain the confluence evolution analysis results, including: Generate a water depth-time grid matrix based on the twin model combined with the preprocessed flow data and environmental data; Generate a confluence grid based on the deduction model combined with preprocessed flow data and environmental data, perform neighborhood iteration analysis on the confluence grid, and obtain a confluence flow direction; Based on the water depth-time grid matrix and the confluence flow direction, a confluence evolution analysis is performed in combination with a cellular automaton to obtain a confluence evolution analysis result.

5. The intelligent water conservancy early warning method based on digital twin according to claim 1 is characterized in that: The determining of the flood outbreak location based on the flood outbreak uncertainty analysis result and the confluence evolution analysis result comprises: Based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, water level trend change analysis and water level sequence significance analysis are performed to obtain water level trend change information and water level sequence significance information; The flood outbreak location is determined based on the water level trend change information and the water level sequence significance information combined with the water level prediction model.

6. The intelligent water conservancy early warning method based on digital twin according to claim 1 is characterized in that: Determining the pressure that the water conservancy equipment needs to withstand at the flood outbreak location includes: Acquire a historical pressure parameter set and a historical water conservancy equipment environment information set, perform correlation analysis on the historical pressure parameter set and the historical water conservancy equipment environment information set, and obtain a pressure correlation parameter; The pressure that the water conservancy equipment needs to withstand at the flood outbreak location is determined based on the pressure-bearing correlation parameter.

7. The intelligent water conservancy early warning method based on digital twin according to claim 1 is characterized in that: The construction of the structural finite element model of the water conservancy equipment, the compression analysis based on the stress analysis combined with the structural finite element model and the pre-processed equipment maintenance data, and the compression performance parameters of each area of ​​the water conservancy equipment are obtained, including: Based on the structural parameters of the water conservancy equipment, the structural finite element model of the water conservancy equipment is constructed using finite element analysis software; Performing finite element static calculation based on the structural finite element model to obtain stress in each area of ​​the water conservancy equipment, and performing self-vibration characteristic analysis based on the structural finite element model to obtain self-vibration characteristic information; Based on the stress and self-vibration characteristic information of each area of ​​the water conservancy equipment combined with the pre-processed equipment maintenance data, displacement response and stress response analysis are performed to obtain the target displacement response and target stress response. Based on the target displacement response and target stress response, the compressive resistance analysis of each area of ​​the water conservancy equipment is performed to obtain the compressive resistance performance parameters of each area of ​​the water conservancy equipment.

8. The intelligent water conservancy early warning method based on digital twin according to claim 1 is characterized in that: The determining whether it is necessary to issue warning information based on the comparison result includes: If the difference between the pressure resistance performance parameter of the target area and the required pressure reaches the preset threshold range, an early warning message is issued.

9. An intelligent water conservancy early warning system based on digital twins, used to apply the intelligent water conservancy early warning method as described in any one of claims 1 to 8 above, characterized in that: The system comprises: Data collection and preprocessing module: used to collect equipment maintenance data, flow data and environmental data of water conservancy equipment, and preprocess the equipment maintenance data, flow data and environmental data to obtain the preprocessed equipment maintenance data, flow data and environmental data; Model building module: used to build a twin model and a deduction model of water conservancy equipment based on pre-processed equipment maintenance data, flow data and environmental data; the specific steps of building the twin model and the deduction model of water conservancy equipment include: building a hydrological and hydrodynamic model using a digital twin database based on the pre-processed flow data and environmental data; building a boundary field of water conservancy equipment based on the pre-processed equipment maintenance data, flow data and environmental data using a fusion algorithm, and building a twin model based on the water conservancy equipment boundary field and the hydrological and hydrodynamic model; performing hidden danger evolution based on the pre-processed equipment maintenance data to obtain hidden danger evolution information, and determining the possible accident distribution of water conservancy equipment based on the hidden danger evolution information; performing hidden danger consequence deduction based on the pre-processed equipment maintenance data, flow data and environmental data to obtain hidden danger consequence deduction information, and building a deduction model based on the virtual engine using the possible accident distribution of water conservancy equipment and the hidden danger consequence deduction information; Flood outbreak uncertainty analysis module: used to perform flood outbreak uncertainty analysis based on preprocessed flow data and environmental data to obtain flood outbreak uncertainty analysis results; Confluence evolution analysis module: used to perform confluence evolution analysis based on the pre-processed flow data and environmental data in combination with the twin model and the deduction model to obtain the confluence evolution analysis results; Flood outbreak location and pressure determination module: used to determine the flood outbreak location based on the flood outbreak uncertainty analysis results and the confluence evolution analysis results, and determine the pressure that the water conservancy equipment needs to withstand at the flood outbreak location; Compression analysis module: used to construct a structural finite element model of water conservancy equipment, perform compression analysis based on stress analysis combined with the structural finite element model and pre-processed equipment maintenance data, and obtain compression performance parameters of each area of ​​the water conservancy equipment; Early warning judgment module: used to determine the compressive performance parameters of the target area based on the flood outbreak location using the compressive performance parameters of each area of ​​the water conservancy equipment, and compare the compressive performance parameters of the target area with the required pressure to obtain a comparison result, and judge whether it is necessary to issue an early warning information based on the comparison result.

Images