A water conservancy management system based on digital twin

Abstract

The present invention discloses a water conservancy management system based on digital twins, and specifically relates to the technical field of water conservancy management. A water conservancy management system based on digital twins comprises a data acquisition module, a data processing module and a data analysis module. By acquiring the performance information and working environment information of the sensor itself, a data processing model is established, an abnormal index of the working state of the sensor is generated, risk marking is performed on the data collected by the sensor under different working states, and further by collecting the quality information of the risk data and the performance information of the running state of the digital twin model, a prediction risk index of the digital twin model is generated. A risk assessment is performed on the digital twin model before prediction, and it is determined whether to generate an early warning signal to avoid the poor quality of the risk data, further increase the data processing burden of the digital twin model when the running state is poor, resulting in the instability of the prediction result, reducing unnecessary prediction tasks, and making the operation of the digital twin model more efficient.

Description

Technical Field

[0001] This invention relates to the field of water conservancy management technology, and more specifically, to a water conservancy management system based on digital twins. Background Technology

[0002] Digital twin technology is a simulation process that integrates multiple disciplines, physical variables, multi-dimensional measurements, and event probability statistics. By establishing a mapping in virtual space, it reflects the entire lifecycle of corresponding physical equipment. A water management system based on digital twins is an advanced water resource management tool. It uses a large number of sensors to form a sensor network to acquire various water resource indicators, and inputs this data into a digital twin model to predict future water resource conditions, flood risks, drought conditions, etc.

[0003] Currently, the monitoring of sensor status in water management systems based on digital twins is inadequate. Typically, intervention measures are only taken when a sensor issues a clear fault warning. Before that, the sensor's condition may have already deteriorated, making it difficult to control the quality of the data acquired. Although digital twin models can preprocess the data, if the model's performance is poor and the data quality is even worse, effective data processing cannot be guaranteed. The lack of risk analysis before model prediction leads to errors in the prediction results.

[0004] To address the aforementioned shortcomings, a technical solution is provided. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a water conservancy management system based on digital twins to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A water conservancy management system based on digital twins includes a data acquisition module, a data processing module, and a data analysis module, with each module connected by signals.

[0008] The data acquisition module collects the sensor's own performance information and operating environment information. After collection, it transmits the sensor's own performance information and operating environment information to the data processing module.

[0009] The data processing module normalizes the acquired sensor performance information and working environment information, establishes a data processing model, and generates an abnormal sensor working state index.

[0010] The data analysis module compares the sensor's abnormal operating state index with the sensor's abnormal operating state index reference threshold and labels the data collected by the sensor under different operating states.

[0011] If the sensor's abnormal operating state index is greater than or equal to the sensor's abnormal operating state index reference threshold, a risk assessment signal is generated, and the data collected by the sensor within time T is marked as risk data.

[0012] In a preferred embodiment, the data acquisition module acquires the sensor's own performance information and operating environment information; the sensor's own performance information includes the response time fluctuation coefficient and the abnormal calibration frequency value, and the operating environment information includes the water pressure abnormal deviation value. After acquisition, the response time fluctuation coefficient, the abnormal calibration frequency value, and the water pressure abnormal deviation value are marked as BD, YX, and SY, respectively.

[0013] In a preferred embodiment, the logic for obtaining the response time fluctuation coefficient is as follows:

[0014] Obtain the sensor's response time within the time period T, and set a baseline threshold for the response time;

[0015] When the sensor's response time exceeds a baseline threshold, it is marked as t. i , i represents the number of times the sensor's response time becomes abnormal, i = {1, 2, ..., j}, j is a positive integer;

[0016] The response time fluctuation coefficient is calculated using the following expression: BD = BC / PJ, where BZ is the standard deviation of the response time under abnormal conditions, and its expression is: PJ is the average response time under abnormal conditions, and its expression is:

[0017] In a preferred embodiment, the logic for obtaining the abnormal calibration frequency value is as follows:

[0018] Obtain the number of times the sensor is calibrated within the time period T, and calculate the average calibration frequency using the following expression: Where ZC is the total number of times the sensor is calibrated within the time period T, and T is the time period for acquiring the number of sensor calibrations;

[0019] Set an average calibration frequency reference threshold. If the average calibration frequency is greater than or equal to the average calibration frequency reference threshold, mark it as JZ'. JZ' indicates the average calibration frequency in an abnormal state.

[0020] The expression for obtaining the abnormal calibration frequency value is: YX = JZ'.

[0021] In a preferred embodiment, the logic for obtaining the abnormal water pressure deviation value is as follows:

[0022] Set the reference threshold range for water pressure under sensor operating conditions, and label it as SY. z min ~SY z max ;

[0023] Obtain the sensor's operating water pressure within time period T, label it as SY, and calculate the abnormal water pressure deviation value, expressed as follows: Where h represents the number of times the sensor's working water pressure exceeds the reference threshold range, h = {1, 2, ..., v}, and h is a positive integer. [q x ,q y This refers to the start and end times when the water pressure exceeds the reference threshold range each time the sensor operates.

[0024] In a preferred embodiment, the data acquisition module is also used to collect quality information of risk data and performance information of the digital twin model's operating status. After collection, it transmits its own performance information and working environment information to the data processing module.

[0025] The quality information of risk data includes the data quality anomaly coefficient, and the performance information of the digital twin model's operating status includes the operating performance coefficient.

[0026] In a preferred embodiment, the data processing module is further configured to normalize the quality information of the acquired risk data and the performance information of the digital twin model's operating status, and establish a data processing model to generate a digital twin model prediction risk index.

[0027] In a preferred embodiment, the data analysis module is further configured to compare the risk index predicted by the digital twin model with a reference threshold for the risk index predicted by the digital twin model, and to conduct a risk assessment on the digital twin model before prediction.

[0028] If the risk index predicted by the digital twin model is greater than or equal to the reference threshold for the risk index predicted by the digital twin model, an early warning signal is generated, and the management personnel determine whether it is necessary to continue to predict the future water supply and demand situation.

[0029] The technical effects and advantages of this invention are as follows:

[0030] 1. This invention acquires sensor performance information and operating environment information, establishes a data processing model, generates a sensor operating state anomaly index, compares the sensor operating state anomaly index with a reference threshold, marks the data collected by the sensor under different operating states with risk, and determines whether to generate a risk assessment signal. When the sensor's operating state declines, the collected data is marked with risk, reducing the pressure on the digital twin model for data processing, reducing the prediction risk caused by sensor problems, and improving data reliability.

[0031] 2. This invention generates a digital twin model prediction risk index by acquiring quality information of risk data and performance information of the digital twin model's operating status. The digital twin model prediction risk index is compared with a reference threshold. Risk assessment is performed on the digital twin model before prediction, and it is determined whether to generate an early warning signal. This avoids excessively poor risk data quality, which would further increase the data processing burden on the digital twin model when its operating status is poor, leading to instability in the prediction results. It also reduces unnecessary prediction tasks, making the digital twin model more efficient and improving the accuracy of prediction. Attached Figure Description

[0032] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0033] Figure 1 This is a schematic diagram of the structure of Embodiment 1 of the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Example 1

[0036] This invention provides, for example Figure 1 The water management system based on digital twins shown includes a data acquisition module, a data processing module, and a data analysis module, with each module connected by signals.

[0037] The data acquisition module collects the sensor's own performance information and operating environment information. After collection, it transmits the sensor's own performance information and operating environment information to the data processing module.

[0038] The data processing module normalizes the acquired sensor performance information and working environment information, establishes a data processing model, and generates an abnormal sensor working state index.

[0039] The data analysis module compares the sensor's abnormal operating state index with the sensor's abnormal operating state index reference threshold and labels the data collected by the sensor under different operating states.

[0040] Digital twins are a concept that combines the actual operation of a physical system with a digital model, and they can play a vital role in water management systems. Sensors play a key role in digital twins; the following are the functions of sensors in water management systems with digital twins:

[0041] Data acquisition and monitoring: Sensors are responsible for real-time monitoring of various parameters in the water system, such as water level, flow velocity, water quality, temperature, humidity, and rainfall. This data forms the basis for building a digital twin, ensuring that the digital model accurately reflects the actual situation.

[0042] Early warning and alarm: Sensors can detect abnormal situations, such as water levels rising too quickly or water quality abnormalities, and issue alarms in a timely manner to help water conservancy managers take emergency measures to prevent disasters or damage.

[0043] Prediction and Optimization: Based on sensor data and digital twin models, water management personnel can make predictive and optimization decisions. They can predict future water supply and demand, formulate appropriate scheduling plans, and optimize the allocation and utilization of water resources.

[0044] Because the performance of sensors deteriorates over long periods of use and the instability of the working environment leads to a decline in sensor performance, the quality of the data acquired by the sensors becomes difficult to control. Therefore, by collecting information on the sensor's own performance and the working environment, the working status of the sensors is evaluated, and the data acquired by the sensors is labeled according to different working statuses.

[0045] It should be noted that the sensor types evaluated in this embodiment are all in direct contact with water, such as water level sensors, water quality sensors, and flow sensors. If the sensor type changes, the collection of its working environment information needs to be changed according to the actual situation, which will not be elaborated here.

[0046] The data acquisition module collects the sensor's own performance information and operating environment information. After collection, it transmits the sensor's own performance information and operating environment information to the data processing module.

[0047] The self-performance information includes the response time fluctuation coefficient and the abnormal calibration frequency value. After acquisition, the data acquisition module marks the response time fluctuation coefficient and the abnormal calibration frequency value as BD and YX, respectively.

[0048] A sensor's response time refers to the time required from detecting a change in the environment or a measured parameter to generating a measurement result. Response time is typically expressed in units of time (e.g., seconds or milliseconds) and is a crucial performance parameter, especially in applications requiring real-time monitoring and control. A shorter response time means the sensor can detect environmental changes more quickly and provide corresponding measurement results, while a longer response time may result in delayed measurement results.

[0049] The logic for obtaining the response time fluctuation coefficient is as follows:

[0050] Obtain the sensor's response time within the time period T, and set a baseline threshold for the response time;

[0051] It should be noted that the response time of a sensor can be obtained by timing the process from when the sensor detects a change in the environment or measurement parameters to when it produces a measurement result. The baseline threshold for response time refers to the maximum upper limit of the response time. This information can be found in the specific sensor datasheet or specification sheet. This information is usually provided by the specific sensor manufacturer and includes detailed descriptions of the sensor response time, which will not be elaborated here.

[0052] When the sensor's response time is less than or equal to a reference threshold, it indicates that the sensor's response time is in a normal state; when the sensor's response time is greater than the reference threshold, it indicates that the sensor's response time is in an abnormal state, and this is marked as t. i , i represents the number of times the sensor's response time becomes abnormal, i = {1, 2, ..., j}, j is a positive integer;

[0053] The response time fluctuation coefficient is calculated using the following expression: BD = BC / PJ, where BZ is the standard deviation of the response time under abnormal conditions, and its expression is: PJ is the average response time under abnormal conditions, and its expression is:

[0054] A higher response time fluctuation coefficient indicates that the sensor is in a poor working state within time T, and the data it collects within time T may have a higher risk. Conversely, a lower response time fluctuation coefficient indicates that the sensor is in a good working state within time T, and the data it collects within time T is of higher quality.

[0055] Sensor calibration is a crucial process used to ensure the accuracy and reliability of sensor measurements. Calibration aims to adjust the sensor's output to be as close as possible to the true or standard value. Sensor performance can change over time, therefore regular maintenance and calibration are necessary to ensure the accuracy of measurement results.

[0056] The logic for obtaining abnormal calibration frequency values ​​is as follows:

[0057] Obtain the number of times the sensor is calibrated within the time period T, and calculate the average calibration frequency using the following expression: Where ZC is the total number of times the sensor is calibrated within the time period T, and T is the time period for acquiring the number of sensor calibrations;

[0058] Set an average calibration frequency reference threshold to evaluate whether the sensor's calibration frequency is abnormal. The average calibration frequency reference threshold can be determined based on previous calibration frequencies or application requirements. If the average calibration frequency is less than the average calibration frequency reference threshold, it means that the sensor's calibration frequency is at a normal level. If the average calibration frequency is greater than or equal to the average calibration frequency reference threshold, it means that the sensor's calibration frequency is in an abnormal state, which is marked as JZ'. JZ' represents the average calibration frequency in an abnormal state.

[0059] The expression for obtaining the abnormal calibration frequency value is: YX = JZ';

[0060] The higher the abnormal calibration frequency value, the more severe the performance degradation of the sensor within time T, the more unstable its working state, and the higher the risk of the data collected within time T. Conversely, the lower the abnormal calibration frequency value, the better the working state of the sensor within time T, and the higher the quality of the data collected within time T.

[0061] The working environment information includes abnormal water pressure deviation values. After collection, the data acquisition module marks the water pressure deviation value as SY.

[0062] Abnormal changes in water pressure can have various effects on underwater sensors, the specific effects of which vary depending on the sensor type, design, and application. Here are some possible effects:

[0063] Sensor performance limitations: Sudden changes in water pressure can subject the sensor to mechanical stress, affecting its performance and accuracy. This may result in erroneous or inaccurate measurement results.

[0064] Sealing issues: Sensors typically require a good seal to prevent water from entering the sensor. Sudden changes in water pressure can compromise the sensor's seal, exposing it to the underwater environment and thus affecting its long-term stability.

[0065] Damage to electronic components: The electronic components inside the sensor may be affected by changes in water pressure, especially at extreme depths. This can lead to damage or failure of the electronic components.

[0066] Material resistance: The materials used for the sensor's housing and components must be able to withstand high pressure to ensure its stability in underwater environments. Abnormal water pressure changes can lead to material fatigue or damage.

[0067] Regarding transmission issues: Underwater sensors typically need to transmit data to the ground or other locations. Abnormal water pressure changes can affect the stability and quality of the data transmission signal;

[0068] The logic for obtaining abnormal water pressure deviation values ​​is as follows:

[0069] Set the reference threshold range for water pressure under sensor operating conditions, and label it as SY. z min ~SY z max ;

[0070] It should be noted that the reference threshold range of water pressure under the working state of the sensor refers to the optimal water pressure range that the sensor can adapt to under the working state. It can be comprehensively considered from the specific sensor datasheet or specification table and the specific depth of the sensor underwater operation, which will not be elaborated here.

[0071] Obtain the sensor's operating water pressure within time period T, label it as SY, and calculate the abnormal water pressure deviation value, expressed as follows: Where h represents the number of times the sensor's working water pressure exceeds the reference threshold range, h = {1, 2, ..., v}, and h is a positive integer. [q x ,q y This refers to the start and end times when the water pressure exceeds the reference threshold range each time the sensor operates.

[0072] It should be noted that some underwater sensors integrate water pressure sensors, which can acquire the working water pressure while measuring water quality data. If not integrated, a professional water pressure sensor can be installed separately for measurement. Professional water pressure sensors have better pressure resistance than sensors used to collect water quality data.

[0073] The higher the abnormal water pressure deviation value, the more unstable the sensor's working state is within time T, and the data it collects within time T may have a higher risk. Conversely, the lower the deviation value, the better the sensor's working state is within time T, and the higher the quality of the data it collects within time T.

[0074] The data processing module normalizes the obtained response time fluctuation coefficient BD, abnormal calibration frequency value YX, and water pressure deviation value SY, and establishes a data processing model. After weighted summation, the sensor working state abnormality index is obtained.

[0075] For example, the sensor working state abnormality index can be obtained by the following formula: WD=a1*BD+a2*YX+a3*SY, where WD is the sensor working state abnormality index, a1, a2, and a3 are the preset proportional coefficients of response time fluctuation coefficient, abnormal calibration frequency value, and water pressure deviation value, respectively, and a1, a2, and a3 are all greater than 0.

[0076] The above calculations show that the larger the response time fluctuation coefficient, abnormal calibration frequency value, and water pressure deviation value, the larger the sensor's working state abnormality index, indicating that the sensor's working state stability within time T is worse, and the data collected within time T may have a higher risk. Conversely, the smaller the response time fluctuation coefficient, abnormal calibration frequency value, and water pressure deviation value, the smaller the sensor's working state abnormality index, indicating that the sensor's working state stability within time T is higher, and the risk of the data collected within time T is lower.

[0077] The data analysis module sets a reference threshold for the sensor's abnormal operating state index, compares the sensor's abnormal operating state index with the reference threshold, and marks the data collected by the sensor under different operating states.

[0078] If the sensor's abnormal operating state index is less than the reference threshold for the sensor's abnormal operating state index, it indicates that the sensor's operating state is highly stable within time T, and the risk of the data collected within time T is low. Therefore, there is no need to perform risk analysis on the sensor before the digital twin model makes a prediction.

[0079] If the sensor's abnormal operating state index is greater than or equal to the reference threshold for the sensor's abnormal operating state index, it indicates that the stability of the sensor's operating state within time T is poor, and the risk of the data collected within time T is high. Risk analysis needs to be performed on the sensor before the digital twin model makes predictions, and a risk assessment signal needs to be issued to mark the data collected by the sensor within time T as risky data.

[0080] This invention acquires sensor performance information and operating environment information, establishes a data processing model, generates a sensor operating state anomaly index, compares the sensor operating state anomaly index with a reference threshold, marks the data collected by the sensor under different operating states with risk, and determines whether to generate a risk assessment signal. When the sensor's operating state declines, the collected data is marked with risk, reducing the pressure on the digital twin model for data processing, reducing the prediction risk caused by sensor problems, and improving data reliability.

[0081] Example 2

[0082] In the above embodiments, by acquiring the sensor's own performance information and working environment information, a data processing model is established to generate a sensor working state anomaly index. The sensor working state anomaly index is compared with a reference threshold, and the data collected by the sensor under different working states is risk-marked. After determining that the data is risky, risk analysis needs to be performed on it before the digital twin model makes predictions to ensure the accuracy of the digital twin model's prediction results. The specific steps are as follows:

[0083] The data acquisition module collects quality information of risk data and performance information of the digital twin model's operating status. After collection, it transmits the quality information of risk data and performance information of the digital twin model's operating status to the data processing module.

[0084] The quality information of risk data includes the data quality anomaly coefficient. After collection, the data acquisition module marks the data quality anomaly coefficient as ZL.

[0085] Data quality is assessed by considering both the missing value rate and outliers. The missing value rate refers to the proportion of missing values ​​(i.e., data points that were not collected or recorded) in a dataset. Calculating the missing value rate is crucial for data quality assessment and analysis. A high missing value rate can affect the reliability of the data and the accuracy of the analysis results. Outliers are values ​​that differ significantly from the majority of data points in the dataset, usually caused by measurement errors, data entry errors, anomalous events, or other abnormal reasons. Outliers can negatively impact data analysis and model building.

[0086] The expression for the data quality anomaly coefficient is as follows: Where QS represents the normalized missing rate of the data, which can be obtained by comparing the number of missing values ​​with the total number of data points; LQ represents the normalized outlier value of the data, which can be obtained by calculating the standard deviation multiple between the data points and the mean using the Z-Score method; α represents the weighting coefficient of the missing rate of the data; and β represents the weighting coefficient of the outlier value of the data.

[0087] The weighting coefficients α for the missing data rate and β for the outliers were derived by combining historical data, suggestions from experts in the field, and the operational requirements of the digital twin model. A large amount of historical data was collected for software and related algorithm simulations to further determine the weighting values.

[0088] A higher data quality anomaly coefficient indicates a lower quality of risk data, which further increases the data processing burden on the digital twin model when it is in poor operating condition, leading to instability in the prediction results. Conversely, a lower coefficient indicates that the digital twin model's processing of risk data is still within a controllable range and will not affect the prediction results.

[0089] The performance information of the digital twin model's running status includes the running performance coefficient. After collection, the data acquisition module marks the running performance coefficient as XN.

[0090] The performance information of a digital twin model can be obtained by comprehensively considering computation time, memory usage, and CPU utilization. Computation time refers to the time required for the digital twin model to run, including the training and inference phases. Shorter computation time generally indicates higher performance and efficiency. Memory usage refers to the memory usage during the operation of the digital twin model, ensuring that the model runs within the available memory. CPU utilization refers to the amount of hardware resources consumed by the digital twin model during runtime.

[0091] The expression for the performance coefficient is as follows: XN = ln(γ*JS + δ*NC + θ*LY + 1), where JS represents computation time, NC represents memory utilization, LY represents CPU utilization, γ represents the weighting coefficient of computation time, δ represents the weighting coefficient of memory utilization, and θ represents the weighting coefficient of CPU utilization. Computation time, memory utilization, and CPU utilization can be obtained in real time during the running of the digital twin model using professional performance monitoring tools such as top, Prometheus, and Grafana.

[0092] The weighting coefficients γ for computation time, δ for memory utilization, and θ for CPU utilization were derived by combining historical data, advice from experts in the field, and the operational requirements of the digital twin model. Furthermore, a large amount of historical data was collected for software and related algorithm simulations to further determine the weight allocation values.

[0093] The data processing module normalizes the acquired data quality anomaly coefficient ZL and operating performance coefficient XN, establishes a data processing model, and calculates the digital twin model prediction risk index through weighted summation.

[0094] For example, the digital twin model prediction risk index can be obtained by the following formula: FX=b1*ZL+b2*XN, where FX is the digital twin model prediction risk index, b1 and b2 are the preset proportional coefficients of the data quality anomaly coefficient and the operational performance coefficient, respectively, and both b1 and b2 are greater than 0.

[0095] The above calculations show that the larger the data quality anomaly coefficient and the operational performance coefficient, the greater the prediction risk index of the digital twin model, indicating that the risk level of the digital twin model prediction is higher and there is a high probability that the prediction results will be incorrect. Conversely, the smaller the data quality anomaly coefficient and the operational performance coefficient, the smaller the prediction risk index of the digital twin model, indicating that the risk level of the digital twin model prediction is within a controllable range.

[0096] The data analysis module sets a reference threshold for the risk index predicted by the digital twin model, compares the risk index predicted by the digital twin model with the reference threshold, and performs a risk assessment on the digital twin model before prediction.

[0097] If the risk index predicted by the digital twin model is less than the reference threshold for the risk index predicted by the digital twin model, it means that the degree of risk predicted by the digital twin model is within a controllable range and can be used to predict the future water supply and demand situation normally.

[0098] If the risk index predicted by the digital twin model is greater than or equal to the reference threshold for the risk index predicted by the digital twin model, it indicates that the risk level of the digital twin model prediction is higher, and there is a high probability that the prediction results will be incorrect. This will generate an early warning signal, and the management personnel will determine whether it is necessary to continue to predict the future water supply and demand situation.

[0099] This invention generates a digital twin model prediction risk index by acquiring quality information of risk data and performance information of the digital twin model's operating status. The digital twin model's prediction risk index is compared with a reference threshold. Risk assessment is performed on the digital twin model before prediction, and it is determined whether to generate an early warning signal. This avoids excessively poor risk data quality, which would further increase the data processing burden on the digital twin model when its operating status is poor, leading to instability in the prediction results. This invention reduces unnecessary prediction tasks, makes the digital twin model more efficient, and improves the accuracy of prediction.

[0100] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0101] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0102] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0103] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0104] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0105] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A water conservancy management system based on digital twin, characterized by: It includes data acquisition module, data processing module and data analysis module, and each module is connected by signals; The data acquisition module collects the sensor's own performance information and working environment information, and after collection, transmits the sensor's own performance information and working environment information to the data processing module; The data processing module normalizes the acquired sensor's own performance information and working environment information, establishes a data processing model, and generates a sensor working status abnormality index; A data analysis module compares the sensor working state abnormality index with the sensor working state abnormality index reference threshold, and marks the data collected by the sensor under different working states; If the sensor working state abnormality index is greater than or equal to the sensor working state abnormality index reference threshold, a risk assessment signal is generated, and the data collected by the sensor within time T is marked as risk data; The data acquisition module collects the sensor's own performance information and working environment information; the sensor's own performance information includes the response time fluctuation coefficient and the abnormal calibration frequency value, and the working environment information includes the water pressure abnormal deviation value. After collection, the response time fluctuation coefficient, the abnormal calibration frequency value, and the water pressure abnormal deviation value are marked as BD, YX, and SY respectively; The logic for obtaining the abnormal water pressure deviation value is as follows: Set the reference threshold range of water pressure when the sensor is in working state, and mark it as SY z min ~SY z max ; Get the working water pressure of the sensor in the T time period, mark it as SY, and calculate the abnormal water pressure deviation value, whose expression is: Wherein, h represents the number of times the working water pressure of the sensor exceeds the reference threshold range, h={1, 2, ..., v}, h is a positive integer, [q x ,q y ] is the start time and end time of each time when the sensor working water pressure exceeds the reference threshold range; The data acquisition module is also used to collect quality information of risk data and performance information of the operating status of the digital twin model. After collection, the performance information and working environment information are transmitted to the data processing module. The quality information of risk data includes the data quality anomaly coefficient, and the performance information of the operating status of the digital twin model includes the operating performance coefficient.

2. A water conservancy management system based on digital twin according to claim 1, characterized in that: The logic for obtaining the response time fluctuation coefficient is as follows: Get the response time of the sensor within the T time period and set the baseline threshold of the response time; When the response time of a sensor is greater than the reference threshold of the response time, it is marked as t i , i represents the number of times the sensor's response time appears abnormal, i = {1, 2, ..., j}, j is a positive integer; Calculate the response time fluctuation coefficient, the expression is as follows: BD = BC / PJ, where BC is the standard deviation of the response time in the abnormal state, and its expression is PJ is the average response time in abnormal state, and its expression is:

3. A water conservancy management system based on digital twin according to claim 1, characterized in that: The logic for obtaining the abnormal calibration frequency value is as follows: Get the number of sensor calibrations within the T time period and calculate the average calibration frequency. The expression is as follows: Where ZC is the total number of sensor calibrations within the T time period, and T is the time period for obtaining the sensor calibration times; The average calibration frequency reference threshold is set. If the average calibration frequency is greater than or equal to the average calibration frequency reference threshold, it is marked as JZ', where JZ' indicates that the average calibration frequency is in an abnormal state. The expression for obtaining the abnormal calibration frequency value is: YX=JZ'.

4. A water conservancy management system based on digital twin according to claim 1, characterized in that: The data processing module is also used to normalize the quality information of the acquired risk data and the performance information of the operating status of the digital twin model, establish a data processing model, and generate a digital twin model prediction risk index.

5. A water conservancy management system based on digital twin according to claim 4, characterized in that: The data analysis module is also used to compare the digital twin model prediction risk index with the digital twin model prediction risk index reference threshold value to conduct risk assessment on the digital twin model before prediction; If the digital twin model prediction risk index is greater than or equal to the digital twin model prediction risk index reference threshold, a warning signal is generated and the management personnel determine whether it is necessary to continue predicting the future water supply and demand situation.

Images