A telemetry terminal based on Hongmeng system

Abstract

The present invention relates to the field of hydrological monitoring technology, specifically a telemetry terminal based on the Hongmeng system, and the system includes: a hydrological data acquisition module, a spatial data analysis module, a monitoring network optimization module, a flow modeling and prediction module, an intelligent anomaly identification module, and a change trend analysis module. In the present invention, the Hongmeng interconnection is used to identify and connect hydrological monitoring sensors to improve the accuracy of the data, and the geographic location coding is used to enhance the traceability and application scope of the data. By analyzing the relationship and dependency between geographic locations, the understanding of complex hydrological phenomena is optimized, and the network structure is adjusted according to the actual data flow to improve the efficiency of data transmission, reduce data delays and losses caused by network problems, and improve the ability to respond quickly to abnormal events by analyzing the real-time data of water flow, so as to provide real-time and accurate support for water resources management and disaster warning, and ensure the operational efficiency of the system and the quality of hydrological monitoring data.

Description

Technical Field

[0001] The present invention relates to the field of hydrological monitoring technology, and in particular to a telemetry terminal based on the Hongmeng system. Background Art

[0002] The field of hydrological monitoring technology focuses on collecting and analyzing the physical, chemical and biological parameters of various water bodies, including lakes, rivers, reservoirs and groundwater. It aims to evaluate and manage water resources and ensure that water quality and quantity meet the needs of agriculture, industry, residents' lives and ecosystems. By installing a variety of sensors to monitor water levels, flows, rainfall, water quality, predict floods and droughts, optimize water resource allocation, and provide support for water pollution prevention and control, hydrological data is transmitted to the monitoring center in real time through communication technology, enabling decision makers to formulate response measures based on the latest data. Combined with automation and remote control technology, monitoring efficiency and accuracy are improved.

[0003] Among them, the telemetry terminal focuses on automatically collecting data from various types of hydrological monitoring sites. By combining a variety of hydrological sensors, including water level meters and flow meters, it monitors water levels, flows, rainfall and other hydrological indicators in real time, and performs trend analysis on the data to identify data change trends and periodic patterns. Combined with data caching, it prevents data loss when communication is interrupted. It aims to achieve flood monitoring and early warning, urban water management, optimization of agricultural irrigation systems, and environmental protection, improve the frequency and accuracy of hydrological data collection, enhance the real-time and reliability of hydrological monitoring, and provide strong technical support for water resources management.

[0004] Traditional telemetry terminals are inadequate in achieving automation and real-time performance in hydrological monitoring, and are still limited in terms of real-time data collection, processing and transmission efficiency. In an unstable communication environment, data delays and loss problems occur, affecting decision makers' immediate response capabilities. The analysis of the relationships and spatial dependencies between data points is not in-depth enough, which limits the accuracy of predictions of complex hydrological phenomena such as floods and droughts in the fields of urban water management, agricultural irrigation system optimization and environmental protection, affecting the overall management and application efficiency of water resources. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and propose a telemetry terminal based on the Hongmeng system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution. A telemetry terminal based on the Hongmeng system includes:

[0007] The hydrological data acquisition module is based on Hongmeng Internet technology, identifies and connects multiple hydrological monitoring sensors, collects water level, flow rate and rainfall data, and records the geographic location code and time information of the data points to generate a water body monitoring data set;

[0008] The spatial data analysis module analyzes the relationship between the hydrological data of multiple geographical locations based on the water body monitoring data set, identifies the spatial dependency in the data, and outputs the spatial dependency analysis results;

[0009] The monitoring network optimization module uses the spatial dependency analysis results to evaluate the efficiency and coverage of the sensor network, analyze the connection and data transmission routes of the sensors, adjust the network structure to optimize the delay and data transmission efficiency, and generate sensor network configuration parameters;

[0010] The flow modeling and prediction module simulates and predicts the water flow state in real time according to the sensor network configuration parameters, analyzes the changes in the water flow velocity field and pressure field, predicts the changes in water flow, and outputs a water state analysis model;

[0011] The intelligent anomaly recognition module analyzes and calculates the uncertainty and random fluctuations in the data based on the water body state analysis model and the real-time water body flow data, identifies the abnormal flow pattern of the water body, and generates real-time abnormal monitoring results;

[0012] The change trend analysis module identifies the change trends and periodic patterns of various water body data, including water level, flow, and precipitation, and generates telemetry data analysis results by performing time series analysis on various real-time monitoring data according to the real-time abnormal monitoring results.

[0013] As a further solution of the present invention, the water body monitoring data set includes a hydrological data set, geographic location information, and collection time information; the spatial dependency analysis results include analysis results of the impact of upstream on downstream flow velocity, a water level relationship diagram between geographic locations, and a spatial data correlation score; the sensor network configuration parameters include network connection paths, data transmission efficiency information, and sensor deployment density data; the water body state analysis model includes a water flow velocity field model, a water pressure field model, and a predicted water body flow change diagram; the real-time abnormal monitoring results include identified abnormal flow patterns, time and location information of flow anomalies, and abnormal event identification records; the telemetry data analysis results include water level change trend information, a flow periodicity analysis diagram, and rainfall time series prediction results.

[0014] As a further solution of the present invention, the hydrological data acquisition module includes:

[0015] The sensor connection submodule is based on Hongmeng interconnection technology to identify and connect hydrological monitoring sensors, record sensor identification, and generate sensor connection status;

[0016] The data recording submodule monitors the water level, flow rate and rainfall data in real time based on the sensor connection status, records the geographic location code and time information of the data point, and generates hydrological data collection records;

[0017] The data set generation submodule standardizes and formats the data based on the hydrological data collection records, and generates a water body monitoring data set by combining data cleaning and verification.

[0018] As a further solution of the present invention, the spatial data analysis module includes:

[0019] The geographic relationship analysis submodule analyzes the hydrological data relationship between multiple geographical locations based on the water body monitoring data set, and generates a data relationship analysis table by comparing the change trends between the hydrological data items;

[0020] The interaction assessment submodule quantifies the impact of upstream flow velocity changes on downstream water levels based on the data relationship analysis table, assesses hydrological interactions between multiple locations, and generates hydrological impact assessment information;

[0021] The dependency output submodule analyzes the spatial dependency characteristics of the hydrological data and generates a spatial dependency analysis result by identifying the direct and indirect dependencies between multiple data points based on the hydrological impact assessment information.

[0022] As a further solution of the present invention, the monitoring network optimization module includes:

[0023] The transmission efficiency analysis submodule analyzes the connection quality and data delay of the current sensor network in real time based on the spatial dependency analysis result, detects the efficiency of nodes within the coverage area, calculates the network efficiency score, and generates network efficiency evaluation information;

[0024] The structure adjustment submodule optimizes the connection and data route of the sensor based on the network efficiency evaluation information, including reallocating the roles of network nodes and adjusting the data transmission path, optimizing the data transmission delay of the sensor network, and generating a network structure adjustment record;

[0025] The parameter configuration submodule adjusts the data transmission frequency and power parameters of multiple sensors based on the network structure adjustment record, analyzes the position relationship of multiple sensor nodes and the network data flow pattern, and generates sensor network configuration parameters according to the requirements of the data transmission task and the signal interference.

[0026] As a further solution of the present invention, the specific formula for calculating the network efficiency score is:

[0027] ;

[0028] in, Represents the average efficiency of the entire sensor network and reflects the overall level of network performance. Representatives from The transmission delay time of the data collected by each node is used to evaluate the data transmission efficiency. Representatives according to The weight coefficient is determined by the geographical location of each node and the importance of the monitoring data. Represents the total number of nodes in the monitoring network, ensuring that all nodes are considered fairly. It is the index of the node, which is used to iterate each node in the summation process and provide an indicator reflecting the network performance by calculating the weighted average delay time.

[0029] As a further solution of the present invention, the traffic modeling and prediction module includes:

[0030] The water state simulation submodule uses real-time hydrological data based on the sensor network configuration parameters to simulate the water flow velocity field and water flow direction, calculate the water flow dynamics of multiple monitoring points, and generate water flow state simulation results;

[0031] The pressure field analysis submodule analyzes water pressure changes based on the water flow state simulation results, evaluates the pressure field distribution at multiple locations, identifies and records pressure anomalies, and generates water pressure field analysis information;

[0032] The flow prediction submodule identifies the periodic variation pattern of the water flow based on the water pressure field analysis information, predicts the water flow, and generates a water state analysis model.

[0033] As a further solution of the present invention, the intelligent abnormality recognition module includes:

[0034] The data fluctuation analysis submodule calculates the fluctuation and uncertainty in the real-time water flow data based on the water state analysis model, evaluates the coefficient of variation and deviation index of the data, and generates uncertainty analysis results;

[0035] The pattern analysis submodule compares and analyzes the real-time traffic data based on the uncertainty analysis results, marks and records the data points whose fluctuations exceed the normal range, identifies abnormal traffic patterns, and generates abnormal pattern recognition results;

[0036] The abnormal event recording submodule classifies and records the identified abnormal events based on the abnormal pattern recognition results, including recording the time, location and impact range of the events, and outputs real-time abnormal monitoring results.

[0037] As a further solution of the present invention, the change trend analysis module includes:

[0038] The time data processing submodule performs data cleaning on the time series data of water level, flow velocity and rainfall based on the real-time abnormal monitoring results, including correcting abnormal values ​​and filling missing values, combining data smoothing to reduce the impact of random fluctuations, and generating time series data;

[0039] The trend analysis submodule calculates the predicted values ​​at multiple time points by performing time series analysis on the water body data based on the time series data, identifies the change trends of various hydrological data, and generates data trend identification results;

[0040] The water level warning submodule is based on the data trend identification results, analyzes the change trend of water body data, evaluates the water level change range of the target water body, identifies the risk water level and flow, sends warning information, and outputs the telemetry data analysis results.

[0041] As a further solution of the present invention, the specific formula for calculating the predicted values ​​at multiple time points is:

[0042] ;

[0043] in, represents the model prediction value at time t, Represents a specific time point in the time series. represents the mean of the time series and is used to adjust the model to an appropriate baseline. Represents the first-order autoregressive coefficient, which is affected by time data points, Represents the second-order autoregressive coefficient, which is affected by time data points, Representative time The observed value of Representative time The observed value of Represents the first-order moving average coefficient, which is used to adjust the The impact Represents at time The random error, Represents at time The random error of the forecast provides an adjustment for the forecast error at the previous moment.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are:

[0045] In the present invention, Hongmeng Internet is used to identify and connect hydrological monitoring sensors to improve data accuracy, geographic location coding is used to enhance data traceability and application scope, and the understanding of complex hydrological phenomena is optimized by analyzing the relationships and dependencies between geographic locations. The network structure is adjusted according to actual data fluidity to improve data transmission efficiency and reduce data delays and losses caused by network problems. By analyzing real-time data on water flow, the ability to respond quickly to abnormal events is enhanced, providing real-time and accurate support for water resources management and disaster warning, thereby ensuring the operational efficiency of the system and the quality of hydrological monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a system flow chart of the present invention;

[0047] Figure 2 It is a schematic diagram of the system framework of the present invention;

[0048] Figure 3 It is a flow chart of the hydrological data acquisition module of the present invention;

[0049] Figure 4 It is a flow chart of the spatial data analysis module of the present invention;

[0050] Figure 5 This is a flow chart of the monitoring network optimization module of the present invention;

[0051] Figure 6 It is a flow chart of the flow modeling and prediction module of the present invention;

[0052] Figure 7 It is a flow chart of the intelligent abnormality identification module of the present invention;

[0053] Figure 8 It is a flow chart of the change trend analysis module of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0056] Embodiment 1

[0057] See also Figure 1 to Figure 2 , a telemetry terminal based on Hongmeng system includes:

[0058] The hydrological data acquisition module is based on Hongmeng Internet technology, identifies and connects multiple hydrological monitoring sensors, collects water level, flow rate and rainfall data, and records the geographic location code and time information of the data points to generate a water body monitoring data set;

[0059] The spatial data analysis module analyzes the relationship between hydrological data of multiple geographical locations based on water body monitoring data sets, identifies spatial dependencies in the data, and outputs spatial dependency analysis results;

[0060] The monitoring network optimization module uses the results of spatial dependency analysis to evaluate the efficiency and coverage of the sensor network, analyze the sensor connection and data transmission routes, adjust the network structure to optimize latency and data transmission efficiency, and generate sensor network configuration parameters;

[0061] The flow modeling and prediction module simulates and predicts the water flow state in real time according to the sensor network configuration parameters, analyzes the changes in the water flow velocity field and pressure field, predicts the changes in water flow, and outputs a water state analysis model;

[0062] The intelligent anomaly recognition module uses the water body state analysis model to analyze and calculate the uncertainty and random fluctuations in the data through real-time water flow data, identify the abnormal flow pattern of the water body, and generate real-time abnormal monitoring results;

[0063] Based on the real-time abnormal monitoring results, the change trend analysis module conducts time series analysis on a variety of real-time monitoring data to identify the change trends and periodic patterns of various water body data, including water level, flow, and precipitation, and generates telemetry data analysis results.

[0064] The water body monitoring data set includes hydrological data set, geographic location information, and collection time information. The spatial dependency analysis results include the analysis results of the impact of upstream on downstream flow velocity, the water level relationship diagram between geographic locations, and the spatial data correlation score. The sensor network configuration parameters include network connection paths, data transmission efficiency information, and sensor deployment density data. The water body state analysis model includes the water flow velocity field model, the water pressure field model, and the predicted water body flow change diagram. The real-time abnormal monitoring results include the identified abnormal flow pattern, the time and location information of the flow anomaly, and the abnormal event identification record. The telemetry data analysis results include water level change trend information, flow periodicity analysis diagram, and rainfall time series prediction results.

[0065] See also Figure 2 and Figure 3 , the hydrological data acquisition module includes:

[0066] The sensor connection submodule is based on Hongmeng interconnection technology to identify and connect hydrological monitoring sensors, record sensor identification, and generate sensor connection status;

[0067] In the sensor connection sub-module, based on the Hongmeng interconnection technology, the automatic identification program is started, and data is exchanged with the main control system through the built-in communication protocol. The sensor is matched and registered according to the model and serial number. The connection status of the sensor is monitored and recorded in real time by the system, including the sensor's physical interface detection, communication protocol synchronization and security authentication process. The communication frequency and data transmission rate are adjusted according to the sensor's performance indicators and working status, the network's resource allocation and data flow stability are optimized, the efficiency and accuracy of the sensor connection are ensured, and the sensor connection status record is generated.

[0068] The data recording submodule monitors the water level, flow rate and rainfall data in real time based on the sensor connection status, records the geographic location code and time information of the data points, and generates hydrological data collection records;

[0069] In the data recording submodule, based on the sensor connection status, the data collection task is activated in real time according to the connection status. Data is read for different types of hydrological monitoring sensors, including water level meters, flow meters and rain gauges. The data points include hydrological data, geographic location codes and timestamps. The consistency of time information is ensured through clock synchronization. The geographic coding system is automatically adjusted according to the sensor location to ensure that the data accurately corresponds to the specific location. The format of the received raw data is standardized to ensure that the data can meet the analysis requirements in subsequent processing and generate real-time and accurate hydrological data collection records.

[0070] The dataset generation submodule standardizes and formats the data based on the hydrological data collection records, and combines data cleaning and verification to generate a water monitoring dataset;

[0071] In the dataset generation submodule, data standardization and formatting are carried out based on the hydrological data collection records. The system normalizes the data according to preset standards to make the data meet the input requirements of the analysis model, and formats it to ensure that the data layout meets the needs of subsequent processing procedures. By cleaning the data, invalid and duplicate records are eliminated, and missing data is reasonably filled or annotated to enhance data integrity. The verification stage performs consistency checks by comparing historical data to ensure the accuracy and reliability of the dataset, and generates a standardized dataset for water body monitoring. The dataset is used to support subsequent data analysis and hydrological model construction.

[0072] See also Figure 2 and Figure 4 , spatial data analysis modules include:

[0073] The geographic relationship analysis submodule analyzes the hydrological data relationship between multiple geographical locations based on the water body monitoring data set, and generates a data relationship analysis table by comparing the change trends between hydrological data items;

[0074] In the geographic relationship analysis submodule, based on the water body monitoring data set, the data of the contained geographical locations are summarized and classified, including multiple indicators such as water level, flow velocity, and rainfall. The time series analysis method is used to calculate the changing trend and periodic fluctuation of the data of each geographical point over time. The correlation analysis technology is used to compare the relationship between the hydrological data of different geographical locations. The linear or nonlinear association between data items is quantified by calculating the Pearson and Spearman correlation coefficients. The impact of seasonal changes and extreme climate events is taken into account to reveal the intrinsic connection between the hydrological data of geographical locations, and generate an analysis table including the relationship between multiple hydrological data.

[0075] The interaction assessment submodule quantifies the impact of upstream flow velocity changes on downstream water levels based on the data relationship analysis table, evaluates the hydrological interactions among multiple locations, and generates hydrological impact assessment information;

[0076] In the above content, based on the data relationship analysis table, the impact of upstream flow velocity changes on downstream water levels is quantified according to the formula , calculate the downstream water level change ;

[0077] In the formula, represents the upstream flow velocity change, represents the influence coefficient;

[0078] Detailed explanation of the formula and the process of formula calculation and derivation:

[0079] Assume that the upstream flow velocity is Increase to ,but , set the influence coefficient , apply the formula:

[0080] ;

[0081] Calculations show that an increase in upstream flow velocity will cause the downstream water level to rise by 0.3 meters, reflecting the direct impact of upstream changes on downstream locations.

[0082] The dependency output submodule analyzes the spatial dependency characteristics of hydrological data and generates spatial dependency analysis results by identifying the direct and indirect dependencies between multiple data points based on the hydrological impact assessment information;

[0083] In the dependency output submodule, based on the hydrological impact assessment information, by analyzing the hydrological data of each monitoring point, including water level and flow velocity, and the geographical location relationship between data points, the geostatistical method Kriging and spatial autocorrelation analysis are used to identify the direct and indirect dependencies between data points, analyze the data flow from upstream to downstream and the potential impact on the downstream geographical location, and evaluate the correlation of spatial data by calculating the Moran's I index to ensure that the analysis results can truly reflect the spatial dependency characteristics of hydrological data and generate spatial dependency analysis results.

[0084] See also Figure 2 and Figure 5 , the monitoring network optimization module includes:

[0085] The transmission efficiency analysis submodule analyzes the connection quality and data delay of the current sensor network in real time based on the results of spatial dependency analysis, detects the efficiency of nodes within the coverage area, calculates the network efficiency score, and generates network efficiency evaluation information;

[0086] The specific formula for calculating the network efficiency score is:

[0087] ;

[0088] in, Represents the average efficiency of the entire sensor network and reflects the overall level of network performance. Representatives from The transmission delay time of the data collected by each node is used to evaluate the data transmission efficiency. Representatives according to The weight coefficient is determined by the geographical location of each node and the importance of the monitoring data. Represents the total number of nodes in the monitoring network, ensuring that all nodes are considered fairly. It is the index of the node, which is used to iterate each node in the summation process and provide an indicator reflecting the network performance by calculating the weighted average delay time.

[0089] formula:

[0090] ;

[0091] Detailed explanation of the formula and the process of formula calculation and derivation:

[0092] The formula is used to calculate the weighted average efficiency of the entire sensor network , taking into account the data delay of each sensor node and the weight of the corresponding node , used to measure the efficiency performance of the network;

[0093] Parameter meaning and setting value:

[0094] Indicates The data delay time of each node,

[0095] Indicates The weight coefficient of each node,

[0096] Indicates the total number of nodes. Assume there are 5 nodes in the network.

[0097] is the index of the node, used to iterate over each node during the summation process,

[0098] Assume that the data delay of the node and weight They are, respectively, in node 1, Second, , in node 2, Second, , in node 3, Second, , in node 4, Second, , in node 5, Second, ;

[0099] Substitute the parameters into the formula for calculation:

[0100] ;

[0101] ;

[0102] ;

[0103] ;

[0104] The result 2.175 reflects the weighted average efficiency of the network, which means the average data transmission performance of the network considering the importance of each node.

[0105] The structural adjustment submodule optimizes the connection and data routes of sensors based on the network efficiency evaluation information, including reallocating the roles of network nodes and adjusting the data transmission paths, optimizing the data transmission delay of the sensor network, and generating network structural adjustment records;

[0106] In the structure adjustment submodule, based on the network efficiency evaluation information, the response time and transmission load of multiple nodes are analyzed, the nodes with low efficiency due to response delay or data loss are identified, the parameters of the target nodes are reconfigured, and the number of data transmission hops and path length are reduced by upgrading some nodes to relay nodes or data aggregation points, including adjusting the data transmission path between nodes, using the shortest path algorithm to calculate the optimal data flow route, introducing additional relay nodes to enhance signal coverage in areas with poor connection quality, and using network simulation tools to predict the performance of the adjusted network to ensure that each adjustment can actually improve the overall efficiency of the network, optimize the network structure, and generate network structure adjustment records.

[0107] The parameter configuration submodule is based on the network structure adjustment record, by analyzing the position relationship of multiple sensor nodes and the network data flow pattern, according to the requirements of the data transmission task and the signal interference, it adjusts the data transmission frequency and power parameters of multiple sensors to generate the sensor network configuration parameters;

[0108] In the parameter configuration submodule, based on the network structure adjustment record, the geographical location of each node and the surrounding electromagnetic environment are analyzed to identify the source of signal interference. According to the data traffic pattern of each node and the overall load of the network, the node's transmission power and data transmission frequency are adjusted, including reducing the power of nodes in high-interference areas to reduce mutual interference, and increasing the frequency of nodes on key data paths to ensure timely transmission of data. Bandwidth resources are dynamically allocated according to data type and priority, network load is balanced and data transmission efficiency is maximized. Through data analysis and parameter adjustment, sensor network configuration parameter records are generated to optimize the network's operating efficiency and data transmission stability.

[0109] See also Figure 2 and Figure 6 , the traffic modeling and prediction module includes:

[0110] The water state simulation submodule uses real-time hydrological data based on the sensor network configuration parameters to simulate the water flow velocity field and flow direction, calculate the water flow dynamics at multiple monitoring points, and generate water flow state simulation results;

[0111] In the water state simulation submodule, the simulation process is executed based on the sensor network configuration parameters. The real-time hydrological data of multiple monitoring points, including the flow velocity and water level data of each point, are input into the water flow dynamics model using the target data. The model includes an algorithm for calculating the flow velocity field and the direction of the water flow. The algorithm operates based on the laws of physics, including conservation laws and fluid dynamics equations. The water flow state around each monitoring point is simulated through an iterative method to ensure the accuracy and real-time performance of the simulation. The water flow dynamics of each point are analyzed and calculated, and the water flow state simulation results are generated according to the target calculation results. The results include the water flow velocity and direction information of each monitoring point, providing a comprehensive view of the water body behavior.

[0112] The pressure field analysis submodule analyzes water pressure changes based on the water flow state simulation results, evaluates the pressure field distribution at multiple locations, identifies and records pressure anomalies, and generates water pressure field analysis information;

[0113] In the pressure field analysis submodule, based on the water flow state simulation results, the water flow simulation data of each monitoring point is extracted, including flow velocity and water level parameters. The data is used to calculate the water pressure at each point. The fluid statics equation is used, and the equation takes into account the density of water and the acceleration of gravity. The calculated water pressure value is mapped to the geographical location of each monitoring point through numerical analysis methods, and a pressure field distribution map is drawn. The pressure data is automatically analyzed, locations with abnormal pressure are identified, abnormal points are marked and recorded, and potential hydrological risks are monitored and prevented. The generated water pressure field analysis information provides key data for subsequent water resources management and emergency response.

[0114] The flow prediction submodule identifies the periodic change pattern of water flow based on the water pressure field analysis information, predicts the water flow, and generates a water state analysis model;

[0115] In the above content, based on the water pressure field analysis information, the periodic change pattern of water flow is identified and predicted. According to the formula , calculate the future water flow ;

[0116] In the formula, represents the currently observed water flow, Represents the periodic growth rate based on historical data analysis;

[0117] Detailed explanation of the formula and the process of formula calculation and derivation:

[0118] Assume that the current water flow is , the annual traffic growth rate is , apply the formula:

[0119] ;

[0120] Calculations show that over the coming period, water body flows are expected to increase , providing critical forecast information for water resource management and flood early warning systems.

[0121] See also Figure 2 and Figure 7 , the intelligent anomaly recognition module includes:

[0122] The data fluctuation analysis submodule calculates the fluctuation and uncertainty in the real-time water flow data based on the water state analysis model, evaluates the coefficient of variation and deviation index of the data, and generates uncertainty analysis results;

[0123] In the above content, based on the water state analysis model, the fluctuation and uncertainty in the real-time water flow data are calculated according to the formula and , calculate the coefficient of variation and Deviation Index ;

[0124] In the formula, represents the sample standard deviation, represents the sample mean, Represents each data point, represents the sample size;

[0125] Detailed explanation of the formula and the process of formula calculation and derivation:

[0126] Suppose there is a set of real-time traffic data ,average value , standard deviation , applying the coefficient of variation formula:

[0127] ;

[0128] calculate :

[0129] ;

[0130] The calculation reveals the degree of data fluctuation and the skewness of the data distribution, the coefficient of variation The data shows that the dispersion is relatively small, and the deviation index It is pointed out that the data distribution is symmetrical relative to the mean value and there is no significant skewness. The uncertainty analysis results are generated through the analysis process, providing quantitative indicators of data fluctuations and deviations.

[0131] The pattern analysis submodule compares and analyzes the real-time traffic data based on the uncertainty analysis results, marks and records the data points whose fluctuations exceed the normal range, identifies abnormal traffic patterns, and generates abnormal pattern recognition results;

[0132] In the pattern analysis submodule, based on the results of uncertainty analysis, the real-time flow data is compared and analyzed, and statistical models are used to detect and mark data points whose fluctuations exceed the normal range. A flow fluctuation baseline is established through historical data. Fluctuations beyond the range are regarded as abnormal and recorded. The pattern recognition algorithm is used to analyze abnormal data points and identify statistically significant abnormal flow patterns. Patterns are used to indicate potential environmental changes or human intervention. By marking abnormal data and analyzing the causes and patterns of abnormal flow, the generated abnormal pattern recognition results provide data support for water resource management and emergency response.

[0133] The abnormal event recording submodule classifies and records the identified abnormal events based on the abnormal pattern recognition results, including recording the time, location and impact range of the event, and outputs real-time abnormal monitoring results;

[0134] In the abnormal event recording submodule, based on the abnormal pattern recognition results, the identified abnormal events are classified and recorded, including the specific time, location and scope of the event, and the causes and consequences of the event are analyzed. The deep data mining and pattern analysis technology are used to ensure that each abnormal event is accurately captured and archived, and communicated to the relevant decision makers and emergency response teams in real time through the communication system, providing real-time updated abnormal monitoring results to ensure a quick and effective response to abnormal events. The output real-time abnormal monitoring results provide key information for ensuring public safety and sustainable management of water resources.

[0135] See also Figure 2 and Figure 8 , the change trend analysis module includes:

[0136] The time data processing submodule performs data cleaning on the time series data of water level, flow velocity and rainfall based on the real-time abnormal monitoring results, including correcting abnormal values ​​and filling missing values, combining data smoothing to reduce the impact of random fluctuations and generate time series data;

[0137] In the time data processing submodule, based on the real-time abnormal monitoring results, the collected time series data are cleaned, including water level, flow rate and rainfall. The algorithm is used to automatically identify and correct the outliers in the data. The box plot is used through statistical analysis methods to identify and eliminate extreme values ​​beyond the normal range. For missing values ​​in the data set, linear interpolation and time-weighted average are used to fill in to ensure the integrity of the data. Moving average and exponential smoothing are used to process the data to reduce random fluctuations in the data and improve data quality, ensure the accuracy and availability of time series data, generate time series data, and provide a data basis for subsequent analysis and decision-making.

[0138] The trend analysis submodule is based on time series data. By performing time series analysis on water body data, the forecast values ​​at multiple time points are calculated, the changing trends of various hydrological data are identified, and data trend identification results are generated.

[0139] The specific formula for calculating the predicted values ​​at multiple time points is:

[0140] ;

[0141] in, represents the model prediction value at time t, Represents a specific time point in the time series. represents the mean of the time series and is used to adjust the model to an appropriate baseline. Represents the first-order autoregressive coefficient, which is affected by time data points, Represents the second-order autoregressive coefficient, which is affected by time data points, Representative time The observed value of Representative time The observed value of Represents the first-order moving average coefficient, which is used to adjust the The impact Represents at time The random error, Represents at time The random error of the forecast provides an adjustment for the forecast error at the previous moment.

[0142] formula:

[0143] ;

[0144] Detailed explanation of the formula and the process of formula calculation and derivation:

[0145] Formula used to calculate the forecast value of time series , which contains the superposition of multiple influencing factors and error terms, is used to reflect the impact of previous observations and random changes in the time series on future values. By substituting and calculating specific values, the predicted value at the next moment is calculated;

[0146] Parameter meaning and setting value:

[0147] is the mean of the time series, assuming that the average value of historical data is 100, reflecting the basic level of the entire time series.

[0148] is the first-order autoregressive coefficient, assuming it is 0.5, indicating the influence of the data point at the previous moment on the current prediction.

[0149] is the second-order autoregressive coefficient, assuming it is 0.3, showing the impact of the data from the previous two moments on the current one.

[0150] For time The observed value of is assumed to be 110, representing the hydrological observation value at the previous moment.

[0151] For time The observation value of is assumed to be 105, which represents the hydrological observation data two moments ago.

[0152] is the first-order moving average coefficient, assumed to be 0.4, used to smooth the random error of the previous moment.

[0153] For time The random error is assumed to be -2.

[0154] For time The random error of is assumed to be 3, which represents the prediction error at the current moment;

[0155] Substitute the parameters into the formula for calculation:

[0156] ;

[0157] ;

[0158] ;

[0159] ;

[0160] The result 188.7 shows that under the influence of given coefficients and historical data, the predicted hydrological data value at the next moment is approximately 188.7. The value is used to analyze the future change trend of hydrological values.

[0161] The water level warning submodule is based on the data trend recognition results. By analyzing the change trend of water body data, it evaluates the water level change range of the target water body, identifies the risk water level and flow, sends warning information, and outputs the telemetry data analysis results;

[0162] In the water level warning submodule, based on the data trend identification results, the long-term and short-term change trends of water body data are analyzed, and the trend analysis tools, time series analysis and regression models are used to evaluate the range of changes in water levels and flows, and identify risk water levels that reach or exceed safety thresholds. When this situation is detected, a warning message is immediately sent through the automation system. The warning system combines real-time data and historical trends to predict dangerous water level situations. The warning information includes the location information of water level exceeding the standard and the expected dangerous time point, and outputs the telemetry data analysis results. The results support real-time monitoring and emergency response measures to ensure timely response by managers and agencies.

[0163] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A telemetry terminal based on Hongmeng system, characterized by: The system comprises: The hydrological data acquisition module is based on Hongmeng Internet technology, identifies and connects multiple hydrological monitoring sensors, collects water level, flow rate and rainfall data, and records the geographic location code and time information of the data points to generate a water body monitoring data set; The spatial data analysis module analyzes the relationship between the hydrological data of multiple geographical locations based on the water body monitoring data set, identifies the spatial dependency in the data, and outputs the spatial dependency analysis results; The monitoring network optimization module uses the spatial dependency analysis results to evaluate the efficiency and coverage of the sensor network, analyze the connection and data transmission routes of the sensors, adjust the network structure to optimize the delay and data transmission efficiency, and generate sensor network configuration parameters; The flow modeling and prediction module simulates and predicts the water flow state in real time according to the sensor network configuration parameters, analyzes the changes in the water flow velocity field and pressure field, predicts the changes in water flow, and outputs a water state analysis model; The intelligent anomaly recognition module analyzes and calculates the uncertainty and random fluctuations in the data based on the water body state analysis model and the real-time water body flow data, identifies the abnormal flow pattern of the water body, and generates real-time abnormal monitoring results; The change trend analysis module identifies the change trends and periodic patterns of various water body data, including water level, flow, and precipitation, and generates telemetry data analysis results by performing time series analysis on various real-time monitoring data according to the real-time abnormal monitoring results.

2. The telemetry terminal based on the Hongmeng system according to claim 1 is characterized in that: The water body monitoring data set includes a hydrological data set, geographic location information, and collection time information. The spatial dependency analysis results include analysis results of the impact of upstream on downstream flow velocity, a water level relationship diagram between geographic locations, and a spatial data correlation score. The sensor network configuration parameters include network connection paths, data transmission efficiency information, and sensor deployment density data. The water body state analysis model includes a water flow velocity field model, a water pressure field model, and a predicted water body flow change diagram. The real-time abnormal monitoring results include identified abnormal flow patterns, time and location information of flow anomalies, and abnormal event identification records. The telemetry data analysis results include water level change trend information, a flow periodicity analysis diagram, and rainfall time series prediction results.

3. The telemetry terminal based on the Hongmeng system according to claim 1 is characterized in that: The hydrological data acquisition module comprises: The sensor connection submodule is based on Hongmeng interconnection technology to identify and connect hydrological monitoring sensors, record sensor identification, and generate sensor connection status; The data recording submodule monitors the water level, flow rate and rainfall data in real time based on the sensor connection status, records the geographic location code and time information of the data point, and generates hydrological data collection records; The data set generation submodule standardizes and formats the data based on the hydrological data collection records, and generates a water body monitoring data set by combining data cleaning and verification.

4. The telemetry terminal based on the Hongmeng system according to claim 1 is characterized in that: The spatial data analysis module includes: The geographic relationship analysis submodule analyzes the hydrological data relationship between multiple geographical locations based on the water body monitoring data set, and generates a data relationship analysis table by comparing the change trends between the hydrological data items; The interaction assessment submodule quantifies the impact of upstream flow velocity changes on downstream water levels based on the data relationship analysis table, assesses hydrological interactions between multiple locations, and generates hydrological impact assessment information; The dependency output submodule analyzes the spatial dependency characteristics of the hydrological data and generates a spatial dependency analysis result by identifying the direct and indirect dependencies between multiple data points based on the hydrological impact assessment information.

5. The telemetry terminal based on the Hongmeng system according to claim 1 is characterized in that: The monitoring network optimization module includes: The transmission efficiency analysis submodule analyzes the connection quality and data delay of the current sensor network in real time based on the spatial dependency analysis result, detects the efficiency of nodes within the coverage area, calculates the network efficiency score, and generates network efficiency evaluation information; The structure adjustment submodule optimizes the connection and data route of the sensor based on the network efficiency evaluation information, including reallocating the roles of network nodes and adjusting the data transmission path, optimizing the data transmission delay of the sensor network, and generating a network structure adjustment record; The parameter configuration submodule adjusts the data transmission frequency and power parameters of multiple sensors based on the network structure adjustment record, analyzes the position relationship of multiple sensor nodes and the network data flow pattern, and generates sensor network configuration parameters according to the requirements of the data transmission task and the signal interference.

6. The telemetry terminal based on the Hongmeng system according to claim 5 is characterized in that: The specific formula for calculating the network efficiency score is: ； in, Represents the average efficiency of the entire sensor network and reflects the overall level of network performance. Representatives from The transmission delay time of the data collected by each node is used to evaluate the data transmission efficiency. Representatives according to The weight coefficient is determined by the geographical location of each node and the importance of the monitoring data. Represents the total number of nodes in the monitoring network, ensuring that all nodes are considered fairly. It is the index of the node, which is used to iterate each node in the summation process and provide an indicator reflecting the network performance by calculating the weighted average delay time.

7. The telemetry terminal based on the Hongmeng system according to claim 1 is characterized in that: The traffic modeling and prediction module includes: The water state simulation submodule uses real-time hydrological data based on the sensor network configuration parameters to simulate the water flow velocity field and water flow direction, calculate the water flow dynamics of multiple monitoring points, and generate water flow state simulation results; The pressure field analysis submodule analyzes water pressure changes based on the water flow state simulation results, evaluates the pressure field distribution at multiple locations, identifies and records pressure anomalies, and generates water pressure field analysis information; The flow prediction submodule identifies the periodic variation pattern of the water flow based on the water pressure field analysis information, predicts the water flow, and generates a water state analysis model.

8. The telemetry terminal based on the Hongmeng system according to claim 1 is characterized in that: The intelligent anomaly recognition module comprises: The data fluctuation analysis submodule calculates the fluctuation and uncertainty in the real-time water flow data based on the water state analysis model, evaluates the coefficient of variation and deviation index of the data, and generates uncertainty analysis results; The pattern analysis submodule compares and analyzes the real-time traffic data based on the uncertainty analysis results, marks and records the data points whose fluctuations exceed the normal range, identifies abnormal traffic patterns, and generates abnormal pattern recognition results; The abnormal event recording submodule classifies and records the identified abnormal events based on the abnormal pattern recognition results, including recording the time, location and impact range of the events, and outputs real-time abnormal monitoring results.

9. The telemetry terminal based on the Hongmeng system according to claim 1 is characterized in that: The change trend analysis module includes: The time data processing submodule performs data cleaning on the time series data of water level, flow velocity and rainfall based on the real-time abnormal monitoring results, including correcting abnormal values ​​and filling missing values, combining data smoothing to reduce the impact of random fluctuations, and generating time series data; The trend analysis submodule calculates the predicted values ​​at multiple time points by performing time series analysis on the water body data based on the time series data, identifies the change trends of various hydrological data, and generates data trend identification results; The water level warning submodule is based on the data trend identification results, analyzes the change trend of water body data, evaluates the water level change range of the target water body, identifies the risk water level and flow, sends warning information, and outputs the telemetry data analysis results.

10. The telemetry terminal based on the Hongmeng system according to claim 9 is characterized in that: The specific formula for calculating the predicted values ​​at multiple time points is: ； in, represents the model prediction value at time t, Represents a specific time point in the time series. represents the mean of the time series and is used to adjust the model to an appropriate baseline. Represents the first-order autoregressive coefficient, which is affected by time data points, Represents the second-order autoregressive coefficient, which is affected by time data points, Representative time The observed value of Representative time The observed value of Represents the first-order moving average coefficient, which is used to adjust the The impact Represents at time The random error, Represents at time The random error of the forecast provides an adjustment for the forecast error at the previous moment.

Images