Water energy abnormal condition sensing method and device and computer equipment

Abstract

The invention relates to a water energy abnormal condition sensing method and device and computer equipment. The method comprises the following steps: acquiring water flow power monitoring data and water area pollution monitoring data of a water energy monitoring area; performing water flow pollutant coupling analysis according to the water flow power monitoring data and the water area pollution monitoring data to obtain water flow nonlinear flow data; performing viscosity flow behavior analysis according to the water flow power monitoring data and the water area pollution monitoring data to obtain fluid shear stress analysis data; performing data consensus analysis on the water flow nonlinear flow data and the fluid shear stress analysis data to obtain regional condition consensus data; and performing anomaly analysis according to the area condition consensus data to obtain water energy current anomaly data and water energy anomaly prediction data of the water energy monitoring area. By the adoption of the method, abnormal situations can still be accurately analyzed in a complex and changeable water energy system.

Description

Technical Field

[0001] The present application relates to the field of intelligent sensing technology, and in particular to a method, device and computer equipment for sensing abnormal water energy conditions. Background Art

[0002] Traditionally, sensing anomalies in water energy systems relies primarily on a combination of physical sensors and manual inspections. Flow meters, pressure gauges, water level sensors, and temperature sensors deployed at key nodes such as hydropower plants, pumping stations, and water pipelines collect data in real time, and anomalies are identified manually or based on preset threshold rules. For example, if abnormal fluctuations in water flow or pressure are detected, an alarm is triggered to indicate a potential fault. However, traditional water storage systems are sensitive to environmental interference, have limited sensing accuracy, and have high maintenance costs, making them difficult to handle abnormal situations in complex and ever-changing water energy systems. Summary of the Invention

[0003] Based on this, it is necessary to provide a water energy anomaly perception method, device and computer equipment that can accurately analyze abnormal situations in complex and changeable water energy systems to address the above technical problems.

[0004] In a first aspect, the present application provides a method for sensing abnormal water energy conditions, comprising:

[0005] Obtain water flow dynamics monitoring data and water pollution monitoring data in water energy monitoring areas;

[0006] Based on the water flow dynamics monitoring data and the water area pollution monitoring data, a water flow pollutant coupling analysis is performed on the water energy monitoring area to obtain water flow nonlinear flow data;

[0007] Perform viscosity flow behavior analysis on the water energy monitoring area based on the water flow dynamics monitoring data and the water pollution monitoring data to obtain fluid shear stress analysis data;

[0008] Performing data consensus analysis on the water flow nonlinear flow data and the fluid shear stress analysis data to obtain regional situation consensus data of the water energy monitoring area;

[0009] According to the regional situation consensus data, an abnormality analysis is performed on the water energy monitoring area to obtain the current abnormal water energy data and the water energy abnormality prediction data of the water energy monitoring area.

[0010] In a second aspect, the present application also provides a water energy abnormality sensing device, comprising:

[0011] Monitoring data acquisition module, used to obtain water flow dynamics monitoring data and water pollution monitoring data in the water energy monitoring area;

[0012] A water flow dynamics analysis module is used to perform water flow pollutant coupling analysis on the water energy monitoring area based on the water flow dynamics monitoring data and the water area pollution monitoring data to obtain water flow nonlinear flow data;

[0013] A water flow viscosity analysis module is used to perform viscosity flow behavior analysis on the water energy monitoring area based on the water flow dynamics monitoring data and the water area pollution monitoring data to obtain fluid shear stress analysis data;

[0014] A data consensus analysis module, configured to perform data consensus analysis on the water nonlinear flow data and the fluid shear stress analysis data to obtain regional situation consensus data of the water energy monitoring area;

[0015] The regional anomaly analysis module is used to perform an anomaly analysis on the water energy monitoring area based on the regional situation consensus data, and obtain the current water energy anomaly data and water energy anomaly prediction data of the water energy monitoring area.

[0016] In a third aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any step of a method for sensing abnormal water energy conditions when executing the computer program.

[0017] The above-mentioned water energy anomaly perception method, device, and computer equipment collect water flow dynamics monitoring data and water pollution monitoring data within the water energy monitoring area, comprehensively considering dynamic parameters such as water flow velocity, flow direction, and flow rate, as well as pollutant concentration, type, and diffusion characteristics, to achieve comprehensive perception of water flow behavior and pollution conditions. On this basis, combined with water flow pollutant coupling analysis, the nonlinear flow characteristics of the water flow are accurately extracted. At the same time, through viscosity flow behavior analysis, the shear stress variation pattern of the fluid under different pollution environments is deeply explored, thereby obtaining fluid mechanics characteristic data. Further, consensus analysis is performed on the nonlinear flow data and shear stress data to construct a unified and coordinated data cognition model, which effectively reflects the overall operating status and environmental quality of the water energy monitoring area. Ultimately, in-depth mining of this consensus data can achieve accurate identification of potential anomalies in the water energy system and prediction of future anomaly trends. It can still accurately analyze anomalies in complex and changing water energy systems, significantly improving the intelligence level, dynamic response capability, and forward-looking decision support capability of the water resources monitoring system, and providing scientific and reliable data support and technical guarantee for water environment governance and sustainable use of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a diagram of an application environment of a method for sensing abnormal water energy conditions in one embodiment;

[0020] Figure 2 A schematic flow chart of a method for sensing abnormal conditions of water energy in one embodiment;

[0021] Figure 3 1 is a flow chart of a method for obtaining nonlinear flow data of water flow in one embodiment;

[0022] Figure 4 A schematic flow chart of a method for obtaining nonlinear flow data of water flow in another embodiment;

[0023] Figure 5 Schematic diagram of a flow chart of a method for obtaining fluid shear stress analysis data in one embodiment;

[0024] Figure 6 A schematic flow chart of a method for obtaining fluid shear stress analysis data in another embodiment;

[0025] Figure 7 1 is a flow chart of a method for obtaining regional situation consensus data in one embodiment;

[0026] Figure 8 This is a structural block diagram of a water energy abnormality sensing device in one embodiment;

[0027] Figure 9 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0029] The present invention provides a method for sensing abnormal water energy conditions, which can be applied to Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104 or placed on a cloud or other network server. Server 104 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0030] In an exemplary embodiment, Figure 2 As shown, a method for sensing abnormal conditions of water energy is provided, which is applied to Figure 1 The server in FIG. 1 is taken as an example to illustrate the method, including the following steps 202 to 210. Among them:

[0031] Step 202: Acquire water flow dynamics monitoring data and water pollution monitoring data in the water energy monitoring area.

[0032] Among them, the water energy monitoring area can be a specific water area where real-time data collection and environmental perception are carried out by setting up a sensor network or monitoring system. This area usually involves the development and utilization of water resources, environmental governance or energy conversion processes, such as reservoirs, rivers, artificial canals, and waters around hydroelectric power stations.

[0033] Among them, water flow dynamics monitoring data can be physical quantities reflecting the movement characteristics of water bodies collected in real time by hydrological monitoring equipment, including flow velocity, flow direction, water level, water pressure, flow rate, turbulence intensity, etc.

[0034] Among them, water pollution monitoring data can be numerical information reflecting the water pollution status obtained by multi-parameter water quality sensors or chemical analysis methods, mainly including dissolved oxygen, pH, chemical oxygen demand (COD), ammonia nitrogen, heavy metal ions, turbidity, suspended matter, etc.

[0035] Specifically, by deploying a variety of sensor equipment (such as flow meters, water level meters, multi-parameter water quality sensors, etc.) at key nodes in the water energy monitoring area, real-time water flow dynamics monitoring data including water flow velocity, water level, water pressure, flow direction, as well as water area pollution monitoring data such as pH value, dissolved oxygen, ammonia nitrogen, COD, and heavy metal ion concentration are collected. The water flow dynamics monitoring data and water area pollution monitoring data of the water energy monitoring area are transmitted to the data processing center through a wireless transmission module.

[0036] Step 204 : Based on the water flow dynamics monitoring data and the water pollution monitoring data, a water flow pollutant coupling analysis is performed on the water energy monitoring area to obtain water flow nonlinear flow data.

[0037] Among them, the coupling analysis of water flow pollutants can be to jointly model and analyze the water flow dynamics behavior and the diffusion, migration and reaction mechanism of pollutants in the water body. By establishing a multi-physical field coupling model, it can simulate how pollutants move, accumulate or settle with the water flow, thereby revealing the driving mechanism of hydrodynamic changes on pollution behavior.

[0038] Among them, the nonlinear flow data of water flow can be obtained by solving the coupling model or data mining, which is a data set reflecting the complex flow patterns such as non-steady state, vortex, turbulence or local disturbance that appear in the water flow under the influence of pollution, and is used to characterize the nonlinear dynamic response characteristics existing in the water body.

[0039] Specifically, based on the collected water flow dynamics monitoring data (such as flow velocity, flow direction, and flow rate) and water pollution monitoring data (such as pollutant type, concentration, and diffusion rate), a coupling model between water flow and pollutants is constructed. After introducing boundary conditions and initial state parameters in the coupling model simulation process, a multi-physics field simulation method (such as CFD-based fluid-pollutant coupling modeling) is adopted. Combined with the control equations (such as the Navier-Stokes equations and the pollutant transport equations), the diffusion, sedimentation, and reverse disturbance processes of pollutants in the fluid medium are iteratively solved to establish a real water body operation scenario, and the nonlinear disturbance pattern and flow structure evolution data of the water flow under the influence of pollutants are obtained as nonlinear flow data of the water flow.

[0040] Step 206 : Based on the water flow dynamics monitoring data and the water pollution monitoring data, viscosity flow behavior analysis is performed on the water energy monitoring area to obtain fluid shear stress analysis data.

[0041] Among them, viscosity flow behavior analysis can be based on the influence of pollutant concentration on the physical properties of water bodies, combined with non-Newtonian fluid mechanics theory and flow field characteristics to study the viscosity change process of water bodies, so as to reveal key behaviors such as fluid shear response, energy dissipation and flow stability changes caused by pollutants.

[0042] Among them, the fluid shear stress analysis data can be obtained through numerical calculation or simulation, and is quantitative data reflecting the shear strength and distribution characteristics of the fluid under the action of internal stratified sliding or external disturbance, which is used to evaluate the mechanical behavior and flow resistance characteristics of water bodies under different pollution levels and flow states.

[0043] Specifically, the team used hydrodynamic monitoring data and water pollution monitoring data to determine the types of pollutants in the water and their concentration levels, thereby determining whether the water exhibited non-Newtonian fluid properties. If the water was confirmed to exhibit non-Newtonian fluid properties, a mathematical model reflecting the viscosity variation of the water under different pollution concentrations was constructed based on non-Newtonian fluid mechanics models (such as the power law model and the Bingham model), combined with the hydrodynamic monitoring data and water pollution monitoring data. Numerical simulation methods were then used to calculate the shear stress distribution at different time and spatial locations. Coupled analysis was performed using the water velocity field and the pollutant distribution field to optimize the local and global shear stress data of the water under the influence of pollution, generating fluid shear stress analysis data.

[0044] Step 208 : performing data consensus analysis on the water nonlinear flow data and the fluid shear stress analysis data to obtain regional situation consensus data of the water energy monitoring area.

[0045] Among them, data consensus analysis can be a processing method that integrates and models the consistency of heterogeneous information from multiple monitoring dimensions or data sources, and forms a unified environmental cognition model through technologies such as feature extraction, dimension normalization, and modal alignment to eliminate data redundancy, enhance feature expression capabilities, and improve overall data quality.

[0046] Among them, regional situation consensus data can be a structured data set that integrates multi-dimensional characteristics such as water flow, pollutants, shear stress, etc. after data consensus analysis and processing. It can describe the current hydrodynamic state, pollution distribution characteristics and mechanical response conditions of the water energy monitoring area.

[0047] Specifically, the nonlinear flow data of water flow and the fluid shear stress analysis data are subjected to spatiotemporal semantic alignment processing, and then at least two multi-source data fusion technologies are used, such as multi-factor difference function, feature extraction of principal component analysis (PCA), probabilistic modeling based on Bayesian inference, and data fusion framework based on deep neural network, to explore the deep correlation between flow characteristics and viscous behavior, realize information collaboration and redundancy elimination between data, and perform heterogeneous collaborative reasoning and fusion of various deep correlations to form regional situation consensus data.

[0048] Step 210 , performing an anomaly analysis on the water energy monitoring area based on the regional situation consensus data, and obtaining the current anomaly data and the anomaly prediction data of the water energy in the water energy monitoring area.

[0049] Among them, anomaly analysis can be achieved by building statistical models, machine learning models or deep learning models to identify data anomalies that deviate from normal patterns in the water energy system, including sudden pollution, flow rate imbalance, shear force anomalies, etc.

[0050] Among them, the current abnormal data of water energy can be a data set based on real-time monitoring and model analysis to detect various abnormal phenomena occurring in the water energy monitoring area at the current moment, usually including information such as the time, location, type of abnormality and its characteristic value, which is used for operation and maintenance response and risk control.

[0051] Among them, water energy anomaly prediction data can be data output based on historical consensus data and trend modeling results to predict hydrodynamic anomalies or pollution incidents that may occur within a certain time range in the future. It includes the time point, regional scope, development intensity, etc. of potential anomalies, and is key predictive information for achieving early intervention and intelligent regulation.

[0052] Specifically, based on the regional consensus data, anomaly analysis is performed on the water and energy monitoring area, and the data obtained after two different implementation processes are weighted fused. The two different implementations are:

[0053] The first one is to construct a high-dimensional spatiotemporal feature tensor based on regional consensus data that integrates water nonlinear flow data and fluid shear stress analysis data, and use a multi-scale convolutional neural network (3D-CNN) to extract key flow and pollution behavior features in different time windows and spatial regions; then use a graph convolutional neural network (GCN) to establish the spatial topological association between each monitoring point in the water energy monitoring area to capture the propagation pattern of abnormal signals in the region; introduce a self-attention mechanism to weight the feature sequence to enhance the system's sensitivity to weak abnormal trends, and combine it with a multimodal comparative learning method to improve the feature recognition ability between different data sources; use a time series prediction model based on the Transformer structure to perform trend modeling on high-dimensional features, output the first initial current abnormal data and the first initial abnormal prediction data, and use the prediction feedback to optimize the consensus data extraction and model parameter update.

[0054] The second method is to build a complete spatiotemporal feature data set based on regional situation consensus data to describe the hydrodynamic and pollution coupling state of the water energy monitoring area under normal operating conditions. Then, intelligent anomaly detection algorithms such as isolation forest, local outlier factor (LOF) or abnormal interval identification based on statistical models are introduced to compare and analyze the spatiotemporal feature data set corresponding to the regional situation consensus data of the current water energy monitoring area with the historical model, thereby identifying characteristic deviations that may indicate abnormal states such as sudden changes in water flow velocity, abnormal fluctuations in pollutant concentration or shear stress imbalance, and obtain the second initial current abnormal data. At the same time, time series modeling technology (such as ARIMA model or deep learning method based on long short-term memory network LSTM) is further combined to model and predict the evolution trend of the spatiotemporal feature data set corresponding to the regional situation consensus data of the current water energy monitoring area over time, so as to identify potential abnormal risks in advance and output water energy abnormality prediction data to generate the second initial abnormal prediction data.

[0055] Finally, after determining the fusion weight according to the timeliness requirements of the water energy monitoring area, the first initial current abnormal data and the second initial current abnormal data are weightedly fused to obtain the water energy current abnormal data; and the first initial abnormal prediction data and the second initial abnormal prediction data are weightedly fused to obtain the water energy abnormal prediction data.

[0056] In the above-mentioned water energy anomaly perception method, by collecting water flow dynamics monitoring data and water pollution monitoring data within the water energy monitoring area, comprehensive perception of water flow behavior and pollution conditions is achieved by comprehensively considering dynamic parameters such as water flow velocity, flow direction, and flow rate, as well as pollutant concentration, type, and diffusion characteristics. On this basis, combined with water flow pollutant coupling analysis, the nonlinear flow characteristics of the water flow are accurately extracted. At the same time, through viscosity flow behavior analysis, the shear stress variation pattern of the fluid under different pollution environments is deeply explored, thereby obtaining fluid mechanics characteristic data. Further consensus analysis is performed on the nonlinear flow data and shear stress data to construct a unified and coordinated data cognition model, which effectively reflects the overall operating status and environmental quality of the water energy monitoring area. Ultimately, in-depth mining of this consensus data can achieve accurate identification of potential anomalies in the water energy system and prediction of future anomaly trends. It can also accurately analyze anomalies in complex and changing water energy systems, significantly improving the intelligence level, dynamic response capability, and forward-looking decision support capabilities of the water resources monitoring system, and providing scientific and reliable data support and technical guarantee for water environment governance and sustainable use of water resources.

[0057] In an exemplary embodiment, Figure 3As shown, based on the water flow dynamics monitoring data and the water pollution monitoring data, the water flow pollutant coupling analysis is performed on the water energy monitoring area to obtain the water flow nonlinear flow data, including steps 302 to 306.

[0058] Step 302: Analyze the water flow dynamics in the water energy monitoring area based on the water flow dynamics monitoring data to obtain regional water flow dynamics analysis data.

[0059] Hydrodynamics is a branch of science that studies the motion of water under natural or artificial boundary conditions and the mechanical forces to which it is subjected. It encompasses the interrelationships between dynamic parameters such as velocity, direction, flow rate, water pressure, and water level. Its theoretical foundation is typically based on governing equations for conservation of mass and momentum (such as the Navier-Stokes equations and the shallow water equations), and is widely used in the modeling and simulation of water flow behavior in rivers, reservoirs, hydraulic structures, and urban water environments.

[0060] Among them, regional hydrodynamic analysis data can be structured result data obtained by modeling and calculating the hydrodynamic monitoring data collected in a specific water energy monitoring area, which usually includes information such as flow velocity distribution, water pressure gradient, flow direction change, turbulence structure and energy distribution at different time and spatial positions in the area.

[0061] Specifically, the collected hydrodynamic monitoring data are preprocessed, such as outlier removal, time synchronization and spatial interpolation, to ensure the integrity and consistency of the data; then, the preprocessed hydrodynamic monitoring data is used to construct a hydrodynamic field simulation framework based on the Navier-Stokes equations or shallow water dynamics model, and the boundary conditions (such as hydraulic structures, water body boundaries, inflow and outflow) and initial conditions (such as initial flow velocity, water level distribution) are combined to perform simulation and solution; during the solution process, numerical methods (such as finite difference, finite volume or Lattice Boltzmann method) are used to model the hydrodynamic evolution process of the monitored area, and the spatiotemporal distribution characteristics such as local flow field disturbances, mainstream path evolution, boundary layer characteristics and fluid kinetic energy changes are extracted, and finally regional hydrodynamic analysis data that can be used for subsequent nonlinear analysis are obtained.

[0062] Step 304 : Perform heterogeneous medium enhancement on the regional hydrodynamic analysis data to obtain regional hydrodynamic enhancement data.

[0063] Among them, heterogeneous medium enhancement can be a method that identifies the differences in spatial physical properties of water bodies or their surrounding environments (such as riverbed roughness, water depth changes, hydraulic interference, etc.), converts these heterogeneous characteristics into model parameters (such as spatial variation coefficient, resistance factor, local disturbance term) and introduces them into the water flow dynamics model, thereby enhancing the model's ability to fit complex flow behaviors in real water environments and improving its accuracy and physical rationality.

[0064] Regional hydrodynamic enhancement data can be a high-precision hydrodynamic dataset generated by enhancing heterogeneous media modeling based on basic hydrodynamic analysis data. It not only describes basic flow velocity and water level distributions but also includes complex features such as localized flow disturbances, fluid retention zones, or areas of enhanced turbulence caused by differences in spatial properties.

[0065] Specifically, the heterogeneous factors existing in the water energy monitoring area are identified from the regional hydrodynamic enhancement data, such as differences in riverbed geological structure, changes in water depth, interference from hydraulic structures, distribution of aquatic plants or sediments, etc. These factors will cause the water flow to exhibit significantly different physical behaviors in different areas. Then, a heterogeneous parameter field is introduced into the hydrodynamic model, such as the spatially variable bottom roughness coefficient, local resistance factor, permeability distribution or flow disturbance factor, etc., to construct a spatial variable weight matrix, and encode these heterogeneous features into structural parameters that can be identified by the model. Then, regional weighted interpolation, hierarchical modeling or multi-resolution grid technology is used to perform local heterogeneous medium enhancement processing on the regional hydrodynamic enhancement data to simulate the response behavior and change trend of water flow in heterogeneous media. The generated hydrodynamic enhancement data has higher spatial resolution and flow accuracy.

[0066] Step 306 : Based on the water pollution monitoring data, the reaction-diffusion-convection optimization is performed on the regional water flow dynamics enhancement data to obtain water flow nonlinear flow data.

[0067] Reaction-diffusion-convection optimization can be a method for coupling pollutant migration and reaction processes in water bodies, comprehensively considering the convective transport of pollutants with water flow, the diffusion behavior caused by molecules or turbulence, and the physical and chemical reactions occurring in the water body. This optimization process constructs a set of reaction-diffusion-convection (RDC) equations and combines them with numerical simulation algorithms to accurately calculate the complex interactions between pollutant behavior and the flow field, thereby generating nonlinear flow data that accurately reflects the changing characteristics of water flow under pollution disturbances.

[0068] Specifically, the water pollution monitoring data is coupled with the enhanced regional hydrodynamics enhancement data, and the reaction-diffusion-convection (RDC) mathematical model is introduced to comprehensively consider the physical transport (convection and diffusion) and chemical behavior (adsorption, precipitation, degradation, redox, etc.) of pollutants in the water body for simulation; in the modeling process, the pollutant input and elimination mechanism is expressed by setting boundary conditions (such as the location and intensity of pollution sources) and source-sink terms, and the model is discretized and numerically solved in combination with numerical methods (such as the finite volume method or adaptive grid solution) to achieve a fine coupling simulation between pollution behavior and hydrodynamic disturbance; the obtained nonlinear flow data of water flow not only retains the complex flow characteristics of the water body itself, but also embeds the nonlinear disturbance pattern of the flow field under the dynamic intervention of pollutants.

[0069] In this example, a basic hydrodynamic model is first constructed by systematically analyzing the hydrodynamic monitoring data of the water energy monitoring area to fully understand the velocity, direction, and pressure distribution characteristics of the water flow in the area. A heterogeneous medium enhancement mechanism is then introduced to fully account for actual environmental differences such as water body bottom sediments, structural obstacles, and local flow resistance, improving the model's adaptability to complex water flow behavior and simulation accuracy. Furthermore, combined with water pollution monitoring data, reaction-diffusion-convection optimization is performed to effectively simulate the transport and reaction processes of pollutants in water flow, generating nonlinear water flow data with physical coupling logic. This significantly improves the authenticity of water flow modeling and the accuracy of pollution diffusion prediction, providing a highly reliable data foundation and model support for water resource regulation, water environment management, and abnormal state identification.

[0070] In an exemplary embodiment, Figure 4 As shown, based on the water pollution monitoring data, the regional water flow dynamics enhancement data is optimized by reaction diffusion convection to obtain water flow nonlinear flow data, including steps 402 to 404.

[0071] Step 402 : Based on the water pollution monitoring data, the pollutant diffusion process of the regional hydrodynamics enhancement data in the water energy monitoring area is simulated to obtain pollutant diffusion enhancement data.

[0072] Among them, the pollutant diffusion process can be the natural migration of pollutants from high-concentration areas to low-concentration areas. In water bodies, it is usually affected by factors such as water convection, molecular diffusion, turbulent diffusion, and boundary conditions (such as riverbeds and obstacles).

[0073] Among them, pollutant diffusion enhancement data can be obtained by introducing real physical environmental factors such as hydrodynamic heterogeneity, turbulent structure, and boundary disturbance on the basis of basic pollutant diffusion simulation, which is a higher-precision and more physically consistent pollutant concentration distribution data. This data not only reflects the macroscopic behavior of pollutants migrating and diffusing with water flow, but also reveals the complex aggregation and dilution characteristics of pollutants in local retention areas, shear zones or boundary layers.

[0074] Specifically, key parameters such as pollutant type, concentration distribution, diffusion coefficient, pollution source location and emission intensity are extracted from water pollution monitoring data, and combined with the velocity field, flow direction change and local disturbance information described in the regional hydrodynamic enhancement data to construct a mathematical model reflecting the migration and diffusion behavior of pollutants with water flow; the mathematical model reflecting the migration and diffusion behavior of pollutants with water flow is based on the convection-diffusion control equation, combined with the heterogeneous characteristics of the hydrodynamic field, and by setting the boundary conditions (such as source term concentration, boundary flow velocity) and initial conditions of pollutants, the migration path, diffusion range and local enrichment phenomenon of pollutants in the monitoring area are dynamically simulated. In order to improve the simulation accuracy of the above model, the turbulent diffusion correction coefficient, the concentration response function of the flow field shear zone and the local diffusion adjustment parameter of the bottom retention zone are further introduced to enhance the model's ability to characterize complex diffusion behavior. Finally, the enhanced model is solved by numerical solution methods (such as the finite volume method or the Lagrangian particle tracking algorithm) to obtain high-precision distribution and evolution data of pollutants in the region, which is the pollutant diffusion enhancement data.

[0075] Step 404 , simulating the microbial growth reaction and microbial degradation reaction in the pollutant diffusion enhancement data to obtain water nonlinear flow data.

[0076] Microbial growth is the process by which microorganisms in water, under suitable environmental conditions (e.g., moderate temperature, pH, and dissolved oxygen), reproduce and expand their populations using pollutants or organic substrates as nutrients. This process is often described using the Monod kinetic model, where microbial growth rate is regulated by both pollutant concentration and environmental factors, and is a key indicator of the water's self-purification capacity.

[0077] Among them, microbial degradation reaction can be the process in which microorganisms in water bodies decompose pollutants into harmless or low-toxic intermediates or end products through metabolic activities during their growth, such as degrading organic pollutants into carbon dioxide and water, and converting ammonia nitrogen into nitrates. This reaction is usually closely related to microbial growth.

[0078] Specifically, based on pollutant diffusion enhancement data, the spatial concentration distribution of pollutants in the water body that changes over time is determined, and highly polluted areas are identified as areas of active microbial reaction. Subsequently, dominant microbial communities related to target pollutants (such as organic matter and ammonia nitrogen) are selected in highly polluted areas, and their growth kinetic models (such as the Monod equation or its modified form) are established based on experimental data or literature parameters. This is used to describe the growth rate of microorganisms under different pollutant concentrations and environmental factors (such as temperature, pH, and dissolved oxygen). At the same time, a microbial degradation reaction model for pollutants is constructed, setting the pollutant concentration as the substrate input and quantitatively describing the amount of pollutant removed through the reaction term. The above two types of reaction models are further coupled with the pollutant concentration field and the hydrodynamic field in the spatial dimension to form a bio-physical coupled reaction system that evolves in time and space. By inputting pollutant diffusion enhancement data, a multi-step numerical solution is performed to simulate the two-way feedback process between pollutants and microorganisms. The final output is nonlinear flow data containing comprehensive characteristics such as flow field disturbances under the influence of microbial activity, dynamic changes in pollutant concentration, and nonlinear shear response of water flow.

[0079] In one embodiment, the calculation formula for the nonlinear flow data of water flow is:

[0080]

[0081] in, is the nonlinear flow data of water flow, ρ is the water density, is the time rate of change of the water velocity field, is the water convection term, is the water velocity, t is the time, is the pressure gradient term, is the viscous diffusion term, μ is the viscous diffusion coefficient of water flow, is the external force of water flow, γ is the efficiency coefficient of microbial degradation of pollutants, is the spatial heterogeneity data of water bodies, is the spatial gradient of pollutant concentration, is the concentration of microorganisms in water, β is the first diffusion regulation coefficient, is the spatial variation data of pollutant diffusion in water bodies, is the spatial variation data of the pollutant diffusion coefficient, α is the diffusion rate constant of microorganisms, is the rate of change of microbial concentration over time, is the data on the effect of water flow on the distribution of microbial concentration, H di is the first pollutant diffusion term, H de is the first microbial degradation item, H dy is the dynamic term of microbial concentration.

[0082] In this example, by combining water pollution monitoring data with high-precision simulations of pollutant diffusion processes in regional hydrodynamic enhancement data, the diffusion paths, rates, and local enrichment effects of pollutants in water bodies under complex hydrodynamic environments are fully considered, generating more physically realistic pollutant diffusion enhancement data. Furthermore, a microbial growth and degradation reaction model is introduced to simulate the dynamic biological response process between pollutants and microorganisms in water bodies, enabling a deep coupling analysis of pollution migration behavior and ecological response mechanisms. This not only improves the level of detail and dynamic prediction capabilities of pollution behavior modeling, but also generates nonlinear flow data that comprehensively reflects the characteristics of water flow disturbances driven by pollution, providing higher-dimensional and more explanatory supporting data and model basis for water environment evolution assessment, water quality trend prediction, and ecological restoration strategies.

[0083] In an exemplary embodiment, Figure 5 As shown, based on the water flow dynamics monitoring data and the water pollution monitoring data, the viscosity flow behavior analysis is performed on the water energy monitoring area to obtain the fluid shear stress analysis data, including steps 502 to 504.

[0084] Step 502 : Based on the water flow dynamics monitoring data, a non-Newtonian fluid dynamics analysis is performed on the water energy monitoring area to obtain plastic fluid shear stress analysis data.

[0085] Among them, non-Newtonian fluid dynamics analysis can be considered in the process of fluid mechanics modeling, in which the special case that the fluid viscosity is no longer a constant but changes with the shear rate is considered. By adopting rheological models (such as the Bingham model, the Herschel-Bulkley model, etc.) suitable for different non-Newtonian behaviors (such as shear thinning, shear thickening or yield stress), a nonlinear constitutive relationship is established and embedded in the hydrodynamic equation for solution, so as to accurately simulate the flow behavior and shear stress distribution of water bodies with complex components (such as high concentrations of pollutants, suspended matter or colloidal particles) under actual working conditions.

[0086] Among them, the plastic fluid shear stress analysis data can be structured data obtained through non-Newtonian fluid modeling and used to describe the shear behavior of water under yield stress conditions. It usually includes information such as the shear stress value, strain rate, distribution range of the yield zone and flow zone of the fluid at various spatial positions. This type of data can reveal whether the water body meets the flow conditions under different boundaries, flow rates and pollution backgrounds, as well as the spatial variation pattern of shear force.

[0087] Specifically, the flow dynamics monitoring data is used to extract information such as the velocity gradient, velocity vector field, and turbulence intensity of each monitoring point, and the pollutant concentration and suspended particle content in the area are used to preliminarily determine whether the water body exhibits non-Newtonian characteristics. Especially in areas of eutrophication or where the water body is rich in colloids or high-density particulate matter, the water flow often no longer obeys the linear shear law. If the water body exhibits non-Newtonian characteristics, a non-Newtonian fluid model suitable for the water flow dynamics monitoring data and the environmental type that meets the water flow dynamics monitoring data is then selected, such as the Bingham model (suitable for water bodies that exhibit yield stress characteristics) or the Herschel-Bulkley model (suitable for shear thinning or shear thickening phenomena), to establish a nonlinear constitutive relationship between shear stress and shear rate. After the water flow dynamics monitoring data is added to the model, it is embedded in the hydrodynamic field simulation framework. Combined with the velocity field and boundary conditions, the finite element or finite volume method is used to numerically solve the shear stress distribution in the area to obtain spatial shear stress data reflecting the plastic flow behavior of the water body.

[0088] Step 504 : analyzing the nonlinear change of the pollutant concentration in the water energy monitoring area of ​​the plastic fluid shear stress analysis data based on the water pollution monitoring data to obtain fluid shear stress analysis data.

[0089] Nonlinear changes can be defined as the relationship between variables in a system not being a simple linear relationship, but rather exhibiting dynamic responses that are non-uniform, sudden, or increasing / decreasing as input conditions (such as pollutant concentration, flow rate, and temperature) change. In coupled hydrodynamic and pollutant systems, nonlinear changes often manifest themselves in the effects of pollutant concentration on water viscosity, shear stress, or flow velocity. This means that even a small pollution disturbance can cause shear stress to increase exponentially or drastically change local flow conditions. This is a core manifestation of system complexity and sensitivity.

[0090] Specifically, the concentration distribution information of pollutants in the time and space dimensions is extracted from the water pollution monitoring data, including the release intensity of different pollution sources, the types of pollutants (such as organic matter, heavy metals, suspended particles) and their migration paths and accumulation areas in the water body; then these pollutant concentration data are coupled with the existing plastic fluid shear stress distribution for analysis, and a functional relationship between pollutant concentration and water viscosity change is constructed. Especially in high-concentration pollution areas, pollutants will significantly change the rheological properties of the water body, resulting in nonlinear enhancement or threshold mutation of shear stress; based on the functional relationship between pollutant concentration and water viscosity change, the pollution concentration gradient is used as the driving variable, and a high-resolution numerical solution is used to iteratively solve the fluid response dominated by concentration to simulate the dynamic evolution process of shear stress under different pollution loads, and further correct the shear stress field to obtain fluid shear stress analysis data that integrates the impact of pollution.

[0091] In this embodiment, by performing non-Newtonian fluid dynamics analysis on water flow dynamics monitoring data, a plastic flow model reflecting the water body under the influence of high pollution, high suspended matter or colloidal substances is constructed, and the shear stress distribution characteristics that reflect the yield stress characteristics are accurately obtained, thereby improving the modeling accuracy of the rheological behavior of complex water bodies. On this basis, the nonlinear changes in pollutant concentration in time and space on the shear stress are analyzed in combination with water pollution monitoring data, revealing the coupling relationship between pollutants and hydrodynamic response. It can achieve deep linkage modeling among hydrodynamics, pollution and rheology, generate high-precision, dynamically evolving fluid shear stress analysis data, and effectively improve the scientificity and foresight of water body anomaly identification, flow resistance prediction and pollution intervention strategy formulation.

[0092] In an exemplary embodiment, Figure 6 As shown, based on the water pollution monitoring data, the nonlinear change of the pollutant concentration in the water energy monitoring area of ​​the plastic fluid shear stress analysis data is analyzed to obtain the fluid shear stress analysis data, including steps 602 to 606.

[0093] Step 602 : analyzing the convection of pollutants in the water energy monitoring area of ​​the plastic fluid shear stress analysis data based on the water pollution monitoring data to obtain plastic fluid shear stress convection data.

[0094] Convection is the phenomenon in which pollutants are transported along the water flow under the dominant dynamic force of the water flow. Its speed and direction are primarily determined by the velocity field of the fluid. In actual aquatic environments, convective transport reflects the main path for pollutants to spread from the source to downstream areas along the water flow. It is one of the dominant mechanisms in the pollutant migration process and is particularly significant in high-velocity waters.

[0095] Plastic fluid shear stress convection data can be obtained by simulating the spatial distribution of shear stress responses generated by the convection migration of pollutants along the water flow, assuming that the water body is a non-Newtonian fluid (with yield stress). This data not only records the propagation path and velocity of pollutants in the main direction of the water flow, but also reflects the complex dynamics of the fluid after being disturbed by pollutants, such as local shear enhancement, viscosity adjustment, and flow field deviation.

[0096] Specifically, based on the concentration distribution of pollutants at different time and space points, emission source location, initial concentration, and flow velocity in water pollution monitoring data, a convection transport equation is established for the migration of pollutants in the water body along the dominant direction of fluid motion. Since water is a plastic non-Newtonian fluid, its flow characteristics are affected by shear rate and yield stress. Therefore, the migration path of pollutants in the water flow depends not only on the macroscopic flow velocity field, but also on the modulation of viscosity changes, fluid resistance, and shear zone distribution. On this basis, the convection transport equation is added as a correction term to the non-Newtonian hydrodynamic field as a modified non-Newtonian hydrodynamic model, and the pollutants are embedded in the modified non-Newtonian hydrodynamic model as passive transport factors. By solving the coupled convection transport equation, the transport behavior of pollutants in the water body along the mainstream direction and their dynamic impact on the local shear stress field are analyzed. It simulates how pollutants accelerate migration in high-velocity areas and accumulate in low-velocity or yield zones, generating plastic fluid shear stress convection data.

[0097] Step 604 : Analyze the diffusion of pollutants in the water energy monitoring area based on the plastic fluid shear stress convection data according to the water pollution monitoring data to obtain plastic fluid shear stress diffusion data.

[0098] Diffusion can be the random diffusion of pollutants in water bodies driven by concentration gradients, including molecular diffusion and turbulent diffusion. Diffusion is typically more pronounced in regions with lower water velocities or in boundary layers. It determines the ability of pollutants to spread in non-mainstream directions, such as vertical and radial directions, and is a key factor influencing the accumulation or dilution of pollutants in a local environment.

[0099] Plastic fluid shear stress diffusion data can be derived from the shear stress variation generated by pollutant diffusion simulations combined with the properties of non-Newtonian fluids. This data reflects the dynamic impact of pollutant diffusion in all directions on local viscosity, stress distribution, and fluid structure. This data can characterize the enhanced or abnormal perturbation behavior of shear stress driven by pollution in low-velocity, stagnant, or high-gradient regions, and serves as an important intermediate data source for identifying pollution in complex flow fields.

[0100] Specifically, key parameters such as the concentration gradient, flow velocity change rate, and turbulence intensity of pollutants in different regions are extracted from the shear stress convection data of plastic fluids. Combined with the diffusion coefficient, water temperature, and viscosity characteristics given in the water pollution monitoring data, a diffusion equation for the diffusion behavior of pollutants in water bodies is constructed. Since plastic non-Newtonian fluids have the characteristic that the viscosity changes with the shear rate, the diffusion behavior no longer simply obeys Fick's law, but is intensified in high shear areas and hindered in low shear areas, showing heterogeneous and direction-dependent diffusion dynamics. Therefore, a modified diffusion coefficient field based on the regulation of the local shear stress field is introduced into the diffusion equation, and the reaction-convection-diffusion equation group is used to simulate the diffusion path and diffusion rate of pollutants under different hydraulic states. Through numerical solution, it is obtained how pollutants expand radially, tangentially, or vertically in a shear stress-dominated heterogeneous fluid system, as well as their feedback effect on the overall shear stress distribution, and finally the plastic fluid shear stress diffusion data is generated.

[0101] Step 606 , simulating the nonlinear high-order response of the plastic fluid shear stress diffusion data to obtain fluid shear stress analysis data.

[0102] Nonlinear higher-order reactions are the nonlinear, multivariable, and non-steady-state processes that occur when pollutants in water are affected by multiple mechanisms, including microbial metabolism, chemical transformation, and sedimentation and resuspension. These reactions often manifest as a disproportion between pollutant concentration and reaction rate, threshold effects, and feedback enhancement or inhibition. These reactions amplify or restructure the shear stress field in water and are a key driver of complex rheological behavior.

[0103] Specifically, based on the plastic fluid shear stress diffusion data obtained during the diffusion stage, high-concentration areas, reaction hot spots, and fluid stress anomaly areas are identified. Combined with specific information on pollutant types, biological reaction parameters, and environmental factors (such as temperature, pH, and dissolved oxygen) in water pollution monitoring data, a nonlinear high-order reaction model is constructed to describe the complex reaction behaviors of pollutants in water bodies. This model not only includes the primary or secondary degradation reactions of pollutants, but also integrates multiple physical-chemical-biological mechanisms such as microbial metabolism, adsorption-desorption dynamics, and sedimentation-resuspension processes to form a multivariate dynamic system that couples pollutant concentration, reaction rate, and shear stress. In the process of solving the nonlinear high-order reaction model, nonlinear functions (such as logistic functions and power-law functions) or data-driven models based on neural networks are introduced to fit the reaction rate. Through time advancement and spatial distribution simulation, the changing trend of shear stress under the influence of complex reactions is dynamically evolved, resulting in fluid shear stress analysis data that integrates the synergistic effects of convection, diffusion, and nonlinear reactions.

[0104] In one embodiment, the calculation formula for fluid shear stress analysis data is:

[0105]

[0106] Where τ is the fluid shear stress analysis data, is the shear stress analysis data of plastic fluid, is the viscosity effect of the fluid, η0 is the yield stress coefficient of the water body, u is the water flow velocity, y is the direction perpendicular to the water flow velocity, λ(N di +N de ) is the reaction and pollutant diffusion term, λ is the comprehensive reaction coefficient, N di is the second pollutant diffusion term, N de is the second microbial degradation item, N ho is the material reaction acceleration term, is the time rate of change of pollutant concentration, is the pollutant convection term, is the water flow velocity, is the spatial gradient of pollutant concentration, ξ is the pollutant response coefficient, is the spatial heterogeneity data of the water body, θ is the second diffusion adjustment coefficient, is the spatial variation data of pollutant diffusion in water bodies, is the spatial variation data of the pollutant diffusion coefficient, θ is the nonlinear acceleration effect coefficient of the pollutant concentration change, is the second-order time derivative of the pollutant concentration, is the convection term of the pollutant concentration change.

[0107] In this embodiment, by using water pollution monitoring data to model the convection behavior of pollutants in the plastic fluid shear stress analysis data, the impact of pollutants migrating with water flow on the local shear stress distribution in a non-Newtonian fluid environment is accurately portrayed. Further, combined with the diffusion characteristics of pollutants, a shear stress diffusion evolution model driven by pollutant concentration gradient is constructed to capture its heterogeneous diffusion process in high viscosity and low-speed retention areas. Finally, by performing nonlinear high-order reaction simulation on the shear stress diffusion data, the influence of multiple factors such as microbial degradation, adsorption and sedimentation are integrated to form fluid shear stress analysis data that comprehensively reflects the mechanical response of water bodies driven by pollution. This can effectively improve the spatial resolution and dynamic response capabilities of the impact of pollution disturbances on the water flow stress field, providing more scientific and accurate data support and decision-making basis for pollution risk assessment, hydrodynamic regulation and ecological intervention strategies.

[0108] In an exemplary embodiment, Figure 7 As shown, the data consensus analysis is performed on the water nonlinear flow data and the fluid shear stress analysis data to obtain the regional situation consensus data of the water energy monitoring area, including steps 702 to 710. Among them:

[0109] Step 702 : performing spatiotemporal semantic alignment on the water flow nonlinear flow data and the fluid shear stress analysis data to obtain water flow nonlinear alignment data and fluid shear stress alignment data.

[0110] Spatiotemporal semantic alignment is the process of uniformly mapping data from different sources with varying temporal sampling frequencies and spatial resolutions on both the time axis and spatial coordinates, while also standardizing the expression of their physical semantics (such as flow velocity and shear stress). This alignment ensures the comparability and consistency of multi-source data within the same analytical framework, providing the input foundation for subsequent fusion calculations with time synchronization, spatial matching, and semantic compatibility.

[0111] Among them, the nonlinear alignment data of water flow can be the nonlinear characteristic data of water flow in a unified time and space coordinate system obtained after completing the spatiotemporal semantic alignment, including key indicators reflecting complex hydrodynamic behavior such as disturbance intensity, flow velocity variability, and local flow field instability.

[0112] Among them, the fluid shear stress alignment data can be processed in a unified format and calibrated in physical quantities for the shear stress data at different positions and times after the spatiotemporal semantic alignment to ensure that it is structurally consistent with the water flow nonlinear data.

[0113] Specifically, the nonlinear flow data and fluid shear stress analysis data are timestamp-matched and spatially mapped to ensure consistency in sampling time and monitoring location. Then, based on spatiotemporal alignment, hydrodynamic characteristics (such as local disturbances and sudden changes in flow velocity) and mechanical characteristics (such as shear stress gradients) are expressed in a unified data space through feature embedding. This addresses issues such as inconsistent scales, different sampling frequencies, or missing data across multiple data sources, resulting in structurally consistent, semantically consistent, and spatiotemporally aligned nonlinear flow and fluid shear stress data.

[0114] Step 704 : Using the multi-factor difference function of the water energy monitoring area, the cognitive difference of the water flow nonlinear alignment data and the fluid shear stress alignment data is quantified to obtain data cognitive deviation information.

[0115] Among them, the multi-factor difference function can be a function model used to measure the degree of deviation between different data segments in multiple characteristic dimensions. It usually combines factors such as flow velocity change rate, stress gradient, time fluctuation frequency, spatial variability, etc., and obtains the difference information between data and baseline state through comprehensive calculation. It is a key mathematical tool for identifying potential anomalies and abnormal behaviors.

[0116] Among them, the data cognitive deviation information can be generated based on the calculation results of the multi-factor difference function, and is an information set used to characterize the degree of deviation of water flow and shear stress data relative to the system cognitive model (such as the normal operating mode or expert experience model).

[0117] Specifically, a multi-factor difference function for the regional hydrodynamic characteristics of the water energy monitoring area is constructed. This multi-factor difference function integrates multiple key variables, including flow velocity gradient, shear stress change rate, fluid disturbance intensity, flow direction deviation angle, and historical benchmark behavior patterns. These factors are then extracted as feature vectors, and feature encoding is performed on each spatiotemporal data segment. Each segment is then compared one-by-one with a preset cognitive benchmark model (such as historical health status data, expert-annotated data, or the system's stable operating range). During this one-by-one comparison, the distance or degree of deviation between each data unit and the benchmark model in the multi-factor space is calculated (using Mahalanobis distance, Euclidean distance, KL divergence, etc.), and cognitive difference information for each data point is obtained as data cognitive deviation information.

[0118] Step 706 : Perform data confidence analysis on the water flow nonlinear alignment data and the fluid shear stress alignment data to obtain data uncertainty information.

[0119] Among them, data confidence analysis can be a process of comprehensively evaluating the credibility, uncertainty and sensitivity of data to environmental interference. It is usually carried out in combination with the predicted fluctuation range, sampling quality, equipment error model or Bayesian inference results. The purpose is to identify which data are more trustworthy and which may have larger errors.

[0120] Data uncertainty information can be the result of data confidence analysis, used to describe the uncertainty level of a data point or data segment, including indicators such as model output fluctuation, sampling error, information entropy, or confidence interval width. It is used to help screen out low-confidence data and ensure the accuracy and stability of the fusion results.

[0121] Specifically, a unified uncertainty assessment framework is constructed based on the sources of error in the acquisition process of nonlinear alignment data of water flow and fluid shear stress alignment data, the instability in the model inference process, and the fluctuating influence of environmental factors. This uncertainty assessment framework integrates multiple uncertainty quantification methods, such as Bayesian inference to estimate the confidence of model outputs, Monte Carlo Dropout to sample and analyze prediction fluctuations in deep neural networks, and fuzzy entropy and information entropy metrics to assess data ambiguity and the degree of information loss. Simultaneously, techniques such as time series variance sliding windows and spatially distributed anomaly sensitivity heat maps are introduced into the assessment process to dynamically monitor the amplitude of change and the intensity of disturbances at each data point within a continuous spatiotemporal range. By comparing indicators such as the width of the credible interval, response consistency, and fluctuation frequency between data, a confidence score and uncertainty distribution data are generated for each data unit as data uncertainty information.

[0122] Step 708 : Select target data from the water nonlinear flow data and the fluid shear stress analysis data based on the data cognitive deviation information and the data uncertainty information to obtain water nonlinear target data and fluid shear stress target data.

[0123] Among them, the nonlinear target data of water flow can be a data subset with high representativeness, high information density and credibility, which is screened out from the aligned full amount of nonlinear water flow data based on cognitive deviation and uncertainty information, and is used to participate in subsequent key event identification, model training or fusion analysis.

[0124] Among them, the fluid shear stress target data can be a high-quality subset selected from the aligned and evaluated shear stress data. It is representative in terms of spatial distribution, stress change trend or abnormal performance, and can be used for cross-modal reasoning and collaborative modeling with water flow data.

[0125] Specifically, based on the data cognitive deviation information and data uncertainty information, a scoring mechanism consisting of cognitive deviation and uncertainty level is established, where cognitive deviation reflects the behavioral difference from historical or theoretical models, while uncertainty level measures the credibility of the data in physical fluctuations or prediction models; then a weighted fusion algorithm or fuzzy comprehensive evaluation method is used to standardize the two scoring dimensions and calculate the comprehensive score, which is used to screen out target data that is both representative and credible from the data cognitive deviation information and data uncertainty information. The screening process can set a threshold strategy (such as eliminating low-confidence and high-deviation data) and give priority to high-confidence and significant deviation areas to ensure that the selected target data can truly reflect potential anomalies or structural changes while avoiding noise or misjudgment interference. The selected target data are used as water flow nonlinear target data and fluid shear stress target data, representing the dynamic behavior characteristics of the area with monitoring value.

[0126] Step 710 , performing heterogeneous reasoning fusion on the water flow nonlinear target data and the fluid shear stress target data to obtain regional situation consensus data.

[0127] Among them, heterogeneous reasoning fusion can be a method of jointly modeling and logically reasoning data of different types, structures, and semantic layers (such as water disturbance characteristics and shear stress fields) in the same analysis framework. It is usually combined with technical means such as graph neural networks, multimodal learning, and attention mechanisms. It aims to explore the intrinsic correlations between heterogeneous data and form a unified cognitive output, such as regional situation consensus data, to achieve cross-layer fusion of intelligent perception and reasoning capabilities.

[0128] Specifically, multimodal representation learning techniques are used to extract features and uniformly encode the heterogeneous physical properties, dimensions, data structure, and semantic representation of nonlinear flow and shear stress target data. For example, semantic alignment of flow disturbance features and shear stress response features is achieved through a shared embedding space or multi-scale feature mapping approach. A heterogeneous graph neural network (GNN) or attention-enhanced fusion model is then introduced to construct the processed nonlinear flow and shear stress target data into a spatiotemporal graph. The spatiotemporal dependencies and mutual influence strengths between the data are modeled at the node and edge weight levels, respectively. Graph reasoning is then used to explore their coupled evolutionary patterns and anomalous linkage features. Furthermore, a rule-based reasoning module or rule constraints are introduced to logically verify and correct conflicting regions and inconsistent evolutionary trends in the coupled evolutionary patterns and anomalous linkage features, thereby improving the stability and interpretability of the consensus data. The resulting regional consensus data retains the deep representation of nonlinear hydrodynamic characteristics and mechanical disturbance information while integrating the complementary strengths of various data sources to form unified environmental cognitive data for global perception and decision support.

[0129] In this embodiment, by performing spatiotemporal semantic alignment on the nonlinear flow data of water flow and the fluid shear stress analysis data, the consistency of multi-source heterogeneous data in terms of time scale and spatial distribution is achieved, ensuring the accuracy and logical integrity of data fusion; further, by constructing a multi-factor difference function, the degree of behavioral deviation between hydrodynamics and shear force is quantified, and cognitive abnormality signals in key areas are accurately identified; at the same time, combined with data confidence analysis, the credibility and stability of each data point are evaluated, effectively filtering out noise and uncertain information; on this basis, representative and reliable target data are selected from the full amount of data, and through heterogeneous reasoning fusion technology, in-depth mining and collaborative modeling of complex environmental characteristics are achieved, ultimately generating highly integrated and interpretable regional situation consensus data. This can significantly improve the data processing intelligence level and fusion decision-making capabilities of the water environment monitoring system, and provide key technical support and model foundation for accurate anomaly identification, pollution warning and water resource optimization management.

[0130] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0131] Based on the same inventive concept, the embodiment of the present application also provides a water energy abnormality sensing device for implementing the above-mentioned water energy abnormality sensing method. Figure 8 As shown, it includes: a monitoring data acquisition module 802, a water flow dynamics analysis module 804, a water flow viscosity analysis module 806, a data consensus analysis module 808 and a regional anomaly analysis module 810. The implementation solution for solving the problem provided by the device is similar to the implementation solution described in the above method. Therefore, the specific limitations in the embodiments of one or more water energy anomaly perception devices provided below can refer to the limitations of a water energy anomaly perception method above, and will not be repeated here. Each module in the above-mentioned water energy anomaly perception device can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0132] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0133] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0134] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0135] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of each of the above-described method embodiments.

[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0137] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but are not limited to these.

[0138] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0139] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for sensing abnormal conditions of water energy, characterized in that: The method comprises: Obtain water flow dynamics monitoring data and water pollution monitoring data in water energy monitoring areas; Based on the water flow dynamics monitoring data and the water area pollution monitoring data, a water flow pollutant coupling analysis is performed on the water energy monitoring area to obtain water flow nonlinear flow data; Perform viscosity flow behavior analysis on the water energy monitoring area based on the water flow dynamics monitoring data and the water pollution monitoring data to obtain fluid shear stress analysis data; Performing data consensus analysis on the water flow nonlinear flow data and the fluid shear stress analysis data to obtain regional situation consensus data of the water energy monitoring area; According to the regional situation consensus data, an abnormality analysis is performed on the water energy monitoring area to obtain the current abnormal water energy data and the water energy abnormality prediction data of the water energy monitoring area.

2. The method according to claim 1, characterized in that The water flow pollutant coupling analysis is performed on the water energy monitoring area based on the water flow dynamics monitoring data and the water area pollution monitoring data to obtain water flow nonlinear flow data, including: Analyzing the water flow dynamics of the water energy monitoring area based on the water flow dynamics monitoring data to obtain regional water flow dynamics analysis data; Performing heterogeneous medium enhancement on the regional hydrodynamic analysis data to obtain regional hydrodynamic enhancement data; According to the water pollution monitoring data, the reaction-diffusion-convection optimization is performed on the regional water flow dynamics enhancement data to obtain the water flow nonlinear flow data.

3. The method according to claim 2, characterized in that The step of performing reaction-diffusion-convection optimization on the regional water flow dynamics enhancement data based on the water pollution monitoring data to obtain the water flow nonlinear flow data includes: According to the water pollution monitoring data, the regional hydrodynamics enhancement data is used to simulate the pollutant diffusion process in the water energy monitoring area to obtain pollutant diffusion enhancement data; The microbial growth reaction and microbial degradation reaction in the pollutant diffusion enhancement data are simulated to obtain the water flow nonlinear flow data.

4. The method according to claim 3, characterized in that The calculation formula for the nonlinear flow data of water flow is: in, is the nonlinear flow data of water flow, ρ is the water density, is the time rate of change of the water velocity field, is the water convection term, is the water velocity, t is the time, is the pressure gradient term, is the viscous diffusion term, μ is the viscous diffusion coefficient of water flow, is the external force of water flow, γ is the efficiency coefficient of microbial degradation of pollutants, is the spatial heterogeneity data of water bodies, is the spatial gradient of pollutant concentration, is the concentration of microorganisms in water, β is the first diffusion regulation coefficient, is the spatial variation data of pollutant diffusion in water bodies, is the spatial variation data of the pollutant diffusion coefficient, α is the diffusion rate constant of microorganisms, is the rate of change of microbial concentration over time, is the data on the effect of water flow on the distribution of microbial concentration, H di is the first pollutant diffusion term, H de is the first microbial degradation item, H dy is the dynamic term of microbial concentration.

5. The method according to claim 1, wherein The viscosity flow behavior analysis of the water energy monitoring area is performed based on the water flow dynamics monitoring data and the water pollution monitoring data to obtain fluid shear stress analysis data, including: Based on the water flow dynamics monitoring data, a non-Newtonian fluid dynamics analysis is performed on the water energy monitoring area to obtain plastic fluid shear stress analysis data; According to the water area pollution monitoring data, the nonlinear change of the pollutant concentration of the plastic fluid shear stress analysis data in the water energy monitoring area is analyzed to obtain the fluid shear stress analysis data.

6. The method according to claim 5, characterized in that The step of analyzing the nonlinear change of the pollutant concentration of the plastic fluid shear stress analysis data in the water energy monitoring area according to the water pollution monitoring data to obtain the fluid shear stress analysis data includes: Analyzing the convection of pollutants in the water energy monitoring area using the plastic fluid shear stress analysis data according to the water pollution monitoring data to obtain plastic fluid shear stress convection data; Analyzing the diffusion of pollutants in the water energy monitoring area based on the plastic fluid shear stress convection data according to the water pollution monitoring data to obtain plastic fluid shear stress diffusion data; The nonlinear high-order response of the plastic fluid shear stress diffusion data is simulated to obtain the fluid shear stress analysis data.

7. The method according to claim 6, characterized in that The calculation formula for the fluid shear stress analysis data is: Where τ is the fluid shear stress analysis data, is the shear stress analysis data of plastic fluid, is the viscosity effect of the fluid, η0 is the yield stress coefficient of the water body, u is the water flow velocity, y is the direction perpendicular to the water flow velocity, λ(N di +N de ) is the reaction and pollutant diffusion term, λ is the comprehensive reaction coefficient, N di is the second pollutant diffusion term, N de is the second microbial degradation item, N ho is the material reaction acceleration term, is the time rate of change of pollutant concentration, is the pollutant convection term, is the water flow velocity, is the spatial gradient of pollutant concentration, ξ is the pollutant response coefficient, is the spatial heterogeneity data of the water body, θ is the second diffusion adjustment coefficient, is the spatial variation data of pollutant diffusion in water bodies, is the spatial variation data of the pollutant diffusion coefficient, θ is the nonlinear acceleration effect coefficient of the pollutant concentration change, is the second-order time derivative of the pollutant concentration, is the convection term of the pollutant concentration change.

8. The method according to claim 1, characterized in that The performing of data consensus analysis on the water nonlinear flow data and the fluid shear stress analysis data to obtain regional situation consensus data of the water energy monitoring area includes: Performing spatiotemporal semantic alignment on the water flow nonlinear flow data and the fluid shear stress analysis data to obtain water flow nonlinear alignment data and fluid shear stress alignment data; Using the multi-factor difference function of the water energy monitoring area, quantifying the cognitive differences of the water flow nonlinear alignment data and the fluid shear stress alignment data to obtain data cognitive deviation information; and performing data confidence analysis on the water flow nonlinear alignment data and the fluid shear stress alignment data to obtain data uncertainty information; selecting target data from the water flow nonlinear flow data and the fluid shear stress analysis data according to the data cognitive deviation information and the data uncertainty information to obtain water flow nonlinear target data and fluid shear stress target data; Heterogeneous reasoning and fusion are performed on the water flow nonlinear target data and the fluid shear stress target data to obtain the regional situation consensus data.

9. A water energy abnormality sensing device, characterized in that: The device comprises: Monitoring data acquisition module, used to obtain water flow dynamics monitoring data and water pollution monitoring data in the water energy monitoring area; A water flow dynamics analysis module is used to perform water flow pollutant coupling analysis on the water energy monitoring area based on the water flow dynamics monitoring data and the water area pollution monitoring data to obtain water flow nonlinear flow data; A water flow viscosity analysis module is used to perform viscosity flow behavior analysis on the water energy monitoring area based on the water flow dynamics monitoring data and the water area pollution monitoring data to obtain fluid shear stress analysis data; A data consensus analysis module, configured to perform data consensus analysis on the water nonlinear flow data and the fluid shear stress analysis data to obtain regional situation consensus data of the water energy monitoring area; The regional anomaly analysis module is used to perform an anomaly analysis on the water energy monitoring area based on the regional situation consensus data, and obtain the current water energy anomaly data and water energy anomaly prediction data of the water energy monitoring area.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images