Hydraulic engineering operation and maintenance management system based on digital twinning

Abstract

The invention provides a hydraulic engineering operation and maintenance management system based on digital twinning, and relates to the technical field of operation and maintenance management, and the system comprises a hydrological sensitive point screening module which carries out the finite element stress hot spot and hydrological sensitive point screening of a target hydraulic engineering; the sensor layout module is used for carrying out multi-modal sensor layout; the twinning model construction module pushes real-time data to a digital twinning synchronization engine; a comparison loss value set determination module performs comparison loss analysis on the real-time digital twinborn model and a historical digital twinborn model synchronously constructed last time; the reverse mapping module performs reverse mapping on the multi-mode sensor network; the asynchronous sampling module carries out asynchronous sampling on the multi-mode sensor network and carries out operation and maintenance management scheme identification. The technical problem that the sampling frequency cannot be adaptively adjusted according to the real-time change in the prior art can be solved, the technical target of intelligent sampling of the multi-modal sensor is achieved, and the technical effect of improving the key data acquisition precision is achieved.

Description

Technical Field

[0001] This application relates to the technical field of operation and maintenance management, and particularly to a digital-twin-based operation and maintenance management system for water conservancy projects. Background Art

[0002] In the current intelligent operation and maintenance management of water conservancy projects, the integration of sensor networks and digital twin technology has gradually become the mainstream application method. Especially in large hydraulic structures such as dams, sluices or diversion tunnels, multi-modal sensors are used to realize the real-time monitoring of multi-dimensional information such as structural stress, water flow state, temperature, and power operation. Combined with three-dimensional modeling and simulation analysis, the cognitive ability of the project state has been effectively improved. However, there are still significant defects in the sensor layout strategy, data processing efficiency, and dynamic response ability in the existing technology. At present, in the data acquisition and processing link, the data types generated by multi-modal sensors are diverse and the frequencies are different. The existing solutions usually adopt fixed-frequency acquisition and unified data channel processing, and fail to dynamically adjust the sampling strategy according to the data importance or change rate, resulting in waste of network bandwidth and delayed response of some key data.

[0003] In summary, there is a technical problem in the existing technology that due to the lack of a dynamic recognition and differential processing mechanism for the data characteristics of multi-modal sensors, the sampling frequency and data transmission strategy cannot be adaptively adjusted according to real-time changes, further affecting the data utilization efficiency, response timeliness, and abnormal warning ability of the water conservancy project monitoring system. Summary of the Invention

[0004] The purpose of this application is to provide a digital-twin-based operation and maintenance management system for water conservancy projects to solve the technical problem in the existing technology that due to the lack of a dynamic recognition and differential processing mechanism for the data characteristics of multi-modal sensors, the sampling frequency and data transmission strategy cannot be adaptively adjusted according to real-time changes, further affecting the data utilization efficiency, response timeliness, and abnormal warning ability of the water conservancy project monitoring system.

[0005] In view of the above problems, the present application provides a digital-twin-based operation and maintenance management system for water conservancy projects, including: a hydrological sensitive point screening module for screening finite element stress hot spots and hydrological sensitive points of a target water conservancy project to obtain a finite element stress hot spot set and a hydrological sensitive point set; a sensor layout module for traversing the finite element stress hot spot set and the hydrological sensitive point set to perform multi-modal sensor layout to obtain a multi-modal sensor network with layout completed; a twin model construction module for using an industrial edge gateway to push the real-time data collected in the multi-modal sensor network to a digital twin synchronization engine to construct a real-time digital twin model; a comparison loss value set determination module for performing comparison loss analysis on the real-time digital twin model and the historical digital twin model constructed in the previous synchronization to determine a comparison loss value set; a reverse mapping module for performing reverse mapping on the multi-modal sensor network based on the comparison loss value set to determine a multi-modal sensor anchor point set; and an asynchronous sampling module for performing asynchronous sampling on the multi-modal sensor network according to the multi-modal sensor anchor point set and the comparison loss value set, and identifying an operation and maintenance management plan according to the asynchronous sampling result to determine a target operation and maintenance management plan.

[0006] Preferably, the digital-twin-based operation and maintenance management system for water conservancy projects further includes: the multi-modal sensors are selected from at least one of the following sensors: fiber Bragg grating strain gauges, piezoelectric accelerometers, ultrasonic water level gauges, RTD temperature probes, and smart meters.

[0007] Preferably, the digital-twin-based operation and maintenance management system for water conservancy projects further includes: an association traceability analysis unit for starting from the multi-modal sensor anchor point set to perform association traceability analysis on the multi-modal sensor network to determine an associated multi-modal sensor group set; and an asynchronous sampling unit for determining an operation and maintenance management sampling scale set based on the comparison loss value set, distributing the operation and maintenance management sampling scale set to the multi-modal sensor anchor point set and the associated multi-modal sensor group set for asynchronous sampling, and determining a target operation and maintenance management plan according to the asynchronous sampling result.

[0008] Preferably, the digital-twin-based operation and maintenance management system for water conservancy projects further includes: a network retrieval unit for retrieving the multi-modal sensor network within a preset association range based on the positions of the multi-modal sensor anchor point set and in combination with the water flow direction of the target water conservancy project to determine an associated multi-modal sensor group set.

[0009] Preferably, the water conservancy project operation and maintenance management system based on digital twin further includes: a normalization processing unit, configured to perform normalization processing on the comparison loss value set respectively to obtain a comparison loss feature normalization value set; an operation and maintenance management coefficient set obtaining unit, configured to divide each comparison loss feature normalization value in the comparison loss feature normalization value set by the sum of the comparison loss feature normalization value set to obtain an operation and maintenance management coefficient set; an operation and maintenance management sampling scale set obtaining unit, configured to traverse and calculate the difference between the operation and maintenance management coefficient set and 1, and multiply the calculation result by a preset standard sampling scale to obtain the operation and maintenance management sampling scale set.

[0010] Preferably, the water conservancy project operation and maintenance management system based on digital twin further includes: a data acquisition unit, configured to collect data for the multi-modal sensor anchor point set and the associated multi-modal sensor group set respectively according to the corresponding operation and maintenance management sampling scale set to obtain a multi-modal sensor anchor point sampling data sequence set and an associated multi-modal sensor group sampling data sequence set; an analysis unit, configured to pre-construct an operation and maintenance management plan recognizer, and use the operation and maintenance management plan recognizer to analyze the multi-modal sensor anchor point sampling data sequence set and the associated multi-modal sensor group sampling data sequence set to obtain the target operation and maintenance management plan.

[0011] Preferably, the water conservancy project operation and maintenance management system based on digital twin further includes: a preprocessing unit, configured to preprocess the real-time data collected in the multi-modal sensor network in the industrial edge gateway by using Kalman filtering to obtain a preprocessed multi-modal sensor preprocessed real-time data set; a transmission unit, configured to, according to the HTTP protocol, the industrial edge gateway transmits the multi-modal sensor preprocessed real-time data set to the digital twin synchronization engine; a digital twin model construction unit, configured to the digital twin synchronization engine constructs a digital twin model according to the multi-modal sensor preprocessed real-time data set to obtain the real-time digital twin model.

[0012] Preferably, the water conservancy project operation and maintenance management system based on digital twin further includes: a simulation calculation unit, configured to the digital twin synchronization engine retrieves a finite element model and a fluid mechanics model, and performs simulation calculation on the multi-modal sensor preprocessed real-time data set to obtain the real-time digital twin model.

[0013] Preferably, the water conservancy project operation and maintenance management system based on digital twin further includes: a three-dimensional model construction unit for constructing a three-dimensional model of the target water conservancy project using BIM technology and setting external load boundaries; a stress simulation unit for meshing the three-dimensional model using ANSYS and performing stress simulation based on the external load boundaries to determine a structural stress distribution map; a finite element stress hot spot set acquisition unit for taking the points exceeding a preset stress threshold in the structural stress distribution map as the finite element stress hot spot set; and a water flow simulation unit for performing water flow simulation based on the three-dimensional model to determine a hydrological sensitive point set.

[0014] Preferably, the water conservancy project operation and maintenance management system based on digital twin further includes: a historical data acquisition unit for acquiring historical hydrological data and historical meteorological data of the area where the target water conservancy project is located; a flow velocity field distribution map generation unit for using the historical hydrological data and historical meteorological data as initial conditions, importing the three-dimensional model into water flow simulation software for water flow simulation, and generating a flow velocity field distribution map; and a hydrological sensitive point set determination unit for determining a hydrological sensitive point set based on the flow velocity field distribution map.

[0015] The technical solution provided in this application has at least the following technical effects or advantages: By achieving the technical goal of intelligent sampling of multi-modal sensors driven by comparison loss and synchronous modeling linkage of digital twin, the technical effects of improving the acquisition accuracy of key data, optimizing system resource allocation, enhancing the perception ability of the operation state of water conservancy projects, and abnormal response ability are achieved.

[0016] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specific embodiments of this application are specifically given. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0018] Figure 1 It is a schematic structural diagram of a water conservancy project operation and maintenance management system based on digital twin of this application.

[0019] Figure 2 This is a schematic structural diagram of the asynchronous sampling module in a water conservancy project operation and maintenance management system based on digital twin of the present application.

[0020] Explanation of reference numerals in the drawings: Hydrological sensitive point screening module 1, sensor layout module 2, twin model construction module 3, comparison loss value set determination module 4, inverse mapping module 5, asynchronous sampling module 6, associated traceability analysis unit 61, asynchronous sampling unit 62. Detailed implementation manners

[0021] By providing a water conservancy project operation and maintenance management system based on digital twin, the present application solves the technical problem in the prior art that due to the lack of a dynamic recognition and differential processing mechanism for multi-modal sensor data characteristics, the sampling frequency and data transmission strategy cannot be adaptively adjusted according to real-time changes, further affecting the data utilization efficiency, response timeliness and abnormal warning ability of the water conservancy project monitoring system. The technical goal of realizing the intelligent sampling of multi-modal sensors driven by comparison loss and the linkage of digital twin synchronous modeling is achieved, and the technical effects of improving the acquisition accuracy of key data, optimizing system resource allocation, enhancing the operation state perception ability and abnormal response ability of the water conservancy project are achieved.

[0022] Next, the technical solutions in the present application will be clearly and completely described with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the drawings rather than all.

[0023] Please refer to the attached Figure 1 , the present application provides a water conservancy project operation and maintenance management system based on digital twin, specifically including: A hydrological sensitive point screening module 1, which is used to screen the finite element stress hot spots and hydrological sensitive points of the target water conservancy project to obtain a finite element stress hot spot set and a hydrological sensitive point set.

[0024] Specifically, the target water conservancy project refers to a specific engineering entity, such as a dam, a canal, a pumping station or a sluice gate, etc., which is the object of monitoring and operation and maintenance of this system. The finite element stress hot spots and hydrological sensitive points of the target water conservancy project are screened. The finite element stress hot spots are the key positions with a relatively high degree of stress concentration, prone to structural fatigue or damage, calculated and identified in the three-dimensional model through the finite element analysis method. The finite element analysis is a method of discretizing a continuous structure into a finite number of small elements and then solving mechanical responses such as stress and displacement through numerical calculations. For example, the ANSYS software is used to simulate the stress state of the dam under water pressure and temperature changes. Then, the screening of hydrological sensitive points is also required. The hydrological sensitive points refer to the positions that are sensitive to hydrological changes, located in areas where the water flow velocity changes violently, eddies are easily formed or the influence of climate is relatively large. The basis for determining the hydrological sensitive points comes from the statistical analysis of historical hydrological and meteorological data, and then the water flow dynamic simulation is carried out through simulation software (such as MIKE or Fluent). Finally, the finite element stress hot spot set and the hydrological sensitive point set are obtained, that is, the list of all high-risk and key monitored structural parts and hydrological positions, which determines the key areas for subsequent modeling and data synchronization.

[0025] The sensor layout module 2 is used to traverse the finite element stress hot spot set and the hydrological sensitive point set to layout multi-modal sensors, and obtain the multi-modal sensor network with layout completed.

[0026] Specifically, traversing the finite element stress hot spot set and the hydrological sensitive point set means checking and processing each identified key monitoring point in turn, judging the environmental conditions and monitoring requirements of each point one by one, and then formulating a sensor layout plan. The finite element stress hot spot set refers to the positions where the stress values are significantly higher than other areas in the structural analysis, concentrated at the structural corners, boundary connections or stress mutation points; the hydrological sensitive point set refers to the areas that are particularly sensitive to water flow changes, prone to eddies, violent water level fluctuations or scouring.

[0027] Then, the multi-modal sensors are laid out. According to the monitoring objectives of different points, different types of sensors are installed at the corresponding positions. The multi-modal sensors refer to a group of sensors with multiple monitoring functions. For example, the fiber Bragg grating strain gauge used to detect structural strain, the piezoelectric accelerometer used to record vibration and impact, the ultrasonic water level gauge used to measure the water level, the RTD temperature probe used for temperature measurement, and the smart meter used to collect the electrical data of the equipment. The layout of different points is determined according to their characteristics. For example, strain gauges and temperature probes may be installed at the bottom of the downstream of the dam, while only water level gauges may be required to be laid out at the upstream flood discharge channel.

[0028] With the sensor layout completed for all key points, a complete multi-modal sensor network is finally formed. It is a collaborative monitoring system composed of multiple sensor nodes, featuring wide distribution, diverse types, and complementary functions. It can collect data from multiple angles and in real time on the structural state and operating environment of hydraulic engineering projects.

[0029] The twin model construction module 3 is used to push the real-time data collected in the multi-modal sensor network to the digital twin synchronization engine through an industrial edge gateway, and construct a real-time digital twin model.

[0030] Specifically, the industrial edge gateway is used to process and transmit the data collected by the multi-modal sensor network. The industrial edge gateway is a computing device deployed on site, which can perform operations such as pre-processing, protocol conversion, and format encapsulation on the data from sensors, and has local computing capabilities. The industrial edge gateway can complete the preliminary screening and compression of data nearby, thereby reducing communication latency and improving real-time performance and bandwidth utilization efficiency.

[0031] Next, the processed data will be pushed to the digital twin synchronization engine. The digital twin synchronization engine is a module responsible for constructing and updating the digital twin model. It receives the real-time data from the edge gateway and uses it to drive the virtual model to keep in sync with the actual project. The digital twin synchronization engine not only receives data, but also dynamically adjusts the model state according to preset physical rules, simulation logics, and model parameters. For example, when the abnormal increase in the vibration data of the dam body uploaded by the edge gateway occurs, the digital twin engine will adjust the structural response performance in the virtual model of the dam body in real time to reflect the potential fatigue risk.

[0032] Finally, a real-time digital twin model is constructed. The real-time digital twin model is an engineering digital copy that is continuously updated based on sensor real-time data, and can synchronously reflect the state changes of the engineering entity at different time nodes. For example, during the flood season, if the real-time data shows that the water level is rising continuously, the water flow simulation in the real-time digital twin model will change accordingly, and predict the overflow point and the position of sudden stress increase, so as to achieve accurate early warning.

[0033] The comparison loss value set determination module 4 is used to perform comparison loss analysis on the real-time digital twin model and the historical digital twin model constructed in the previous synchronization, and determine the comparison loss value set.

[0034] Specifically, a comparison loss analysis is performed on the real-time digital twin model and the historical digital twin model. The digital twin model currently generated by sensor data is compared point by point and parameter by parameter with the model saved at a previous moment. The real-time digital twin model is a virtual replication of the current state of the project and can reflect the real-time changes in structure, environment, and equipment; while the historical digital twin model represents the state at a past moment. The core of the comparison loss analysis is to find the differences between these two models in key physical parameters, such as stress, deformation, water level, flow rate, etc., to evaluate whether there are abnormal changes in the project operation.

[0035] Immediately afterwards, all the differences found in the comparison are classified and quantified to generate a set of data for analysis and decision-making, and a set of comparison loss values is determined. The comparison loss value is the difference between the same physical quantity at the same position at two moments. For example, the displacement at a certain measurement point was 4 mm last time and is now 9 mm, then the comparison loss value is 5 mm.

[0036] The inverse mapping module 5 is used to perform inverse mapping on the multi-modal sensor network based on the set of comparison loss values to determine the multi-modal sensor anchor point set.

[0037] Specifically, inverse mapping is performed on the multi-modal sensor network based on the set of comparison loss values. Using the parameter anomaly information contained in the set of comparison loss values, trace back to the data source location where the abnormal change occurred, and identify the sensors that played a key role in the model differences. The set of comparison loss values is the difference data between the digital twin models at two moments in terms of structural stress, water level, temperature, etc., and the multi-modal sensor network is a sensor system deployed at various key points of the water conservancy project, including various types of sensors, such as strain gauges, water level gauges, accelerometers, etc. Inverse mapping refers to the process of inferring the cause from the result, that is, by analyzing the changes in the comparison loss values, inversely check the sensors whose measured physical quantities have changed significantly, so as to find the source of abnormal changes.

[0038] Then, the key sensor points identified during the inverse mapping process are grouped together to determine the multi-modal sensor anchor point set, which constitutes a set of sensors for key observation or response. The multi-modal sensor anchor point set plays an "anchoring" role in monitoring the structural state changes and is the source point where faults germinate or the position with the most active changes.

[0039] The asynchronous sampling module 6 is used to perform asynchronous sampling on the multi-modal sensor network according to the multi-modal sensor anchor point set and the set of comparison loss values, and identify the operation and maintenance management plan according to the asynchronous sampling results to determine the target operation and maintenance management plan.

[0040] Specifically, based on the multi-modal sensor anchor point set and the comparison loss value set, asynchronous sampling is performed on the multi-modal sensor network. Based on the identified key sensor points and combined with their corresponding loss degrees, the sampling frequencies and time sequences of each sensor are determined to achieve targeted non-uniform time interval data acquisition. Asynchronous sampling means that each sensor no longer collects data simultaneously or at a fixed frequency, but dynamically adjusts the sampling strategy according to its importance and change rate.

[0041] Next, based on the asynchronous sampling results, an operation and maintenance management plan identification is carried out. The collected asynchronous data is input into a pre-constructed operation and maintenance management identification model to analyze and judge the engineering operation state. Relying on machine learning or rule matching techniques, the current structural state can be classified, such as normal, slightly abnormal, severely abnormal, etc. The identification model will comprehensively consider various parameters such as stress, water level, vibration, etc., and combine historical experience and expert knowledge to output a set of suggestions or decision-making paths. Finally, the target operation and maintenance management plan is determined, and a set of targeted engineering operation and maintenance strategies are recommended, including on-site manual inspections, starting backup pump stations, strengthening slope structures, adjusting the opening of sluice gates, etc., aiming to intervene in potential risks in a timely manner to prevent the problem from deteriorating further.

[0042] Furthermore, this application also includes: the multi-modal sensor is selected from at least one of the following sensors: fiber Bragg grating strain gauge, piezoelectric accelerometer, ultrasonic water level gauge, RTD temperature probe, smart meter.

[0043] Specifically, the sensors deployed in the water conservancy project monitoring are not of a single type, but include multiple devices that can sense different physical quantities. The multi-modal sensor is selected from at least one of the following sensors, and then one or more of them are flexibly selected and combined according to the actual monitoring requirements, which helps to obtain information on structural and environmental changes from multiple dimensions, so as to build a more comprehensive and refined digital twin model.

[0044] The fiber Bragg grating strain gauge is a sensor that measures the strain of an object by utilizing the wavelength change of light in an optical fiber. Based on the sensitivity of the grating reflection wavelength to stress changes, it is used to monitor the deformation of concrete or steel structures and is suitable for high-precision and long-distance monitoring. For example, fiber Bragg grating strain gauges can be embedded inside a dam structure for continuous stress observation. The piezoelectric accelerometer is a device that measures acceleration by generating electric charges when a piezoelectric material is stressed. It is used for vibration detection and can monitor the dynamic response of engineering structures under external disturbances (such as earthquakes and water hammers). It is installed at positions vulnerable to impact, such as bridge piers and gates. The ultrasonic water level gauge is a device that calculates the water level height by measuring the time difference between the ultrasonic wave emitted from the sensor and reflected by the water surface. It is not affected by water quality and is used for monitoring the water level changes in rivers, reservoirs, and gates. The RTD temperature probe, that is, the resistance temperature detector, is a sensor that senses temperature by the change of the metal resistance with temperature. It is used to monitor the temperature distribution during the operation of water bodies, structural materials, or equipment. For example, RTD probes can be arranged in a pump house to track the heating condition of the motor. The smart meter is a power monitoring device with data recording, communication, and remote control functions. It can not only record the power consumption in real time but also report abnormal power changes, and is used to determine whether electrical equipment such as pumps and gates is operating normally, playing a role in energy consumption analysis and equipment health assessment.

[0045] Furthermore, as Figure 2 shown, this application further includes: an associated traceability analysis unit 61, which is used to start from the multi-modal sensor anchor point set and perform an associated traceability analysis on the multi-modal sensor network to determine an associated multi-modal sensor group set; an asynchronous sampling unit 62, which is used to determine an operation and maintenance management sampling scale set based on the comparison loss value set, distribute the operation and maintenance management sampling scale set to the multi-modal sensor anchor point set and the associated multi-modal sensor group set for asynchronous sampling, and determine a target operation and maintenance management plan according to the asynchronous sampling results.

[0046] Specifically, starting from the multi-modal sensor anchor point set and the key sensor points identified in the previous analysis, an associated traceability analysis is performed on the multi-modal sensor network. In the entire sensor network, by combining information such as the physical location of the anchor points, the water flow direction, and the structural topology, other sensor nodes that have a correlation, similar trend, or causal relationship with the multi-modal sensor anchor points in the monitoring data are found to determine the associated multi-modal sensor group set, which is convenient for expanding the monitoring area in the spatial range later and realizing more comprehensive data analysis.

[0047] Based on the comparison loss value set, the operation and maintenance management sampling scale set is determined, and the deviation between the real-time state and the historical state of the digital twin model is quantified as the comparison loss value, and the sampling frequency, data accuracy or sensor activation strategy required for each monitoring area is calculated accordingly. The larger the loss value, the more drastic or abnormal the state change of the area or equipment, and the finer the required sampling scale, which requires higher frequency or more accurate monitoring. The operation and maintenance management sampling scale set refers to the sampling scale combination required for different locations or sensor points in the sensor network, which can be either different time intervals or changes in data resolution. The operation and maintenance management sampling scale set is distributed to the multimodal sensor anchor point set and the associated multimodal sensor group set for asynchronous sampling. Each point no longer collects data at a unified frequency, but updates data according to its required dynamic sampling scale, which saves energy and focuses on abnormal areas. Subsequently, the target operation and maintenance management plan can be determined by performing pattern analysis based on the asynchronous sampling results, such as whether to perform structural reinforcement, flood discharge regulation or equipment maintenance. Table 1 shows some records of the most recent associated traceability analysis and asynchronous sampling management.

[0048] Table 1: Partial records of the most recent correlation tracing analysis and asynchronous sampling management Sensor number Whether it is an anchor sensor Associated traceability sensor group Alignment loss value Operation and maintenance management coefficient Asynchronous sampling data feature summary Whether to trigger operation and maintenance response S001 Yes S002, S003 0.75 5 Large strain fluctuation (>5%) Yes S002 No - 0.42 10 Stable fluctuation (<1%) No S003 No - 0.66 6 Small change (2% - 3%) No S004 Yes S005 0.88 4 Vibration signal peak is significant Yes S005 No - 0.39 12 Normal current fluctuation No .

[0049] Furthermore, the present application also includes: a network retrieval unit, which is used to search the multimodal sensor network according to a preset association range based on the position of the multimodal sensor anchor point set and the water flow direction of the target water conservancy project to determine the associated multimodal sensor group set.

[0050] Specifically, based on the location of the multimodal sensor anchor point set and the flow direction of the target water conservancy project, when determining the relationship between the relevant sensors, not only the spatial location is considered, but also the direction and path of the water flow in the actual project. For example, in a dam or spillway, the water flows from upstream to downstream, so the water level changes sensed by the upstream anchor point may affect the stress of the downstream structure.

[0051] Retrieve the multi-modal sensor network according to the preset association range, which means that when identifying the associated sensor group, the search range is restricted according to the preset spatial or physical influence range. The preset association range is a specific distance threshold. For example, search for other sensors within a radius of 500 meters around the anchor point in all directions, or judge the influence transmission chain according to the logical order on the water flow path. Nodes directly or indirectly associated with the key anchor point can be efficiently screened out in the entire sensor network. Finally, determine the set of associated multi-modal sensor groups, that is, a set of sensor points selected near the anchor point, combined with the water flow direction and structural connection relationship, which are of support significance for analysis and can provide more comprehensive operating status information collaboratively.

[0052] Furthermore, this application also includes: a normalization processing unit for normalizing the set of comparison loss values respectively to obtain a set of normalized comparison loss feature values; an operation and maintenance management coefficient set obtaining unit for dividing each normalized comparison loss feature value in the set of normalized comparison loss feature values by the sum of the set of normalized comparison loss feature values to obtain an operation and maintenance management coefficient set; an operation and maintenance management sampling scale set obtaining unit for traversing and calculating the difference between the operation and maintenance management coefficient set and 1, and multiplying the calculation result by a preset standard sampling scale to obtain the operation and maintenance management sampling scale set.

[0053] Specifically, normalize the set of comparison loss values, standardize the numerical values of the comparison loss values generated by each sensor monitoring point, and make their ranges unified between 0 and 1, which is convenient for comparison and subsequent calculations. The normalization processing adopts the maximum-minimum normalization method, which helps to perform quantitative analysis on loss values of different orders of magnitude on the same scale.

[0054] Next, divide each normalized comparison loss feature value in the set of normalized comparison loss feature values by the sum of the set of normalized comparison loss feature values to obtain an operation and maintenance management coefficient set. The ratio operation is a weight distribution strategy used to measure the relative contribution of each sensor point to the overall anomaly. For example, if there are 3 values in the set of normalized values, which are 0.2, 0.3, and 0.5 respectively, and the sum is 1, then the operation and maintenance management coefficients are 0.2, 0.3, and 0.5 respectively. The operation and maintenance management coefficient set reflects the position with the most significant deviation, which is convenient for subsequent precise sampling and resource allocation.

[0055] Finally, traverse and calculate the difference between the operation and maintenance management coefficient set and 1, and multiply the calculation result by a preset standard sampling scale to obtain the operation and maintenance management sampling scale set, which reflects the importance of each monitoring point in the actual sampling frequency or accuracy. The larger the difference, the smaller the deviation of this point, and the lower the required sampling density; otherwise, sampling needs to be encrypted.

[0056] Furthermore, this application also includes: a data acquisition unit, which is used to collect data from the multi-modal sensor anchor set and the associated multi-modal sensor group set respectively according to the corresponding operation and maintenance management sampling scale set, and obtain the multi-modal sensor anchor sampling data sequence set and the associated multi-modal sensor group sampling data sequence set; an analysis unit, which is used to pre-construct an operation and maintenance management solution recognizer, and use the operation and maintenance management solution recognizer to analyze the multi-modal sensor anchor sampling data sequence set and the associated multi-modal sensor group sampling data sequence set to obtain the target operation and maintenance management solution.

[0057] Specifically, the multi-modal sensor anchor set and the associated multi-modal sensor group set collect data respectively according to the corresponding operation and maintenance management sampling scale set. According to the calculated different sampling frequency requirements (i.e., the operation and maintenance management sampling scale set), environmental or structural data is obtained in a non-fixed cycle manner. A multi-modal sensor refers to a device that can collect different physical quantities, such as simultaneously collecting strain, acceleration, water level, and temperature, etc.; the sampling data sequence set is a set of multiple groups of data continuously obtained by the sensor at specific time intervals, forming a time-series input for analysis. For example, the anchor sensor samples once every 2 minutes, while some sensors in the associated group may sample once every 5 minutes, thus forming two data sequences with different densities, reflecting the different importance levels of each monitoring point during the project operation.

[0058] Next, pre-construct an operation and maintenance management solution recognizer, that is, an intelligent model or algorithm module that has been designed and trained before the system is deployed. Its task is to receive the sensor sampling data and determine whether an operation and maintenance action needs to be performed currently. The operation and maintenance management solution recognizer can adopt technical forms such as a rule engine, a support vector machine, a decision tree, or a neural network, etc. According to historical data, a set of recognition logics is trained to determine whether an abnormality occurs or whether the operation and maintenance threshold is reached.

[0059] Then, use the operation and maintenance management solution recognizer to analyze the multi-modal sensor anchor sampling data sequence set and the associated multi-modal sensor group sampling data sequence set. The operation and maintenance management solution recognizer takes the previously collected data sequence as input, and automatically calculates and discriminates features such as trends, mutations, and abnormal amplitudes in the data. The analysis content may include indicators such as stress growth rate, water level change slope, and vibration frequency fluctuation. By cross-comparing, it can be judged whether there are structural risks, hydrological risks, or equipment state deterioration.

[0060] Finally, obtain the target operation and maintenance management solution through analysis, that is, the recognizer will output a specific countermeasure plan for the current project operation state, such as suggesting local structural reinforcement, drainage scheduling optimization, or monitoring point densification. The target operation and maintenance management solution is not a static standard process, but a strategy dynamically generated by combining real-time data characteristics and historical model deviations.

[0061] Furthermore, this application also includes: a preprocessing unit for preprocessing the real-time data collected in the multimodal sensor network in the industrial edge gateway by using Kalman filtering to obtain a set of preprocessed real-time data of the multimodal sensor; a transmission unit for the industrial edge gateway to transmit the set of preprocessed real-time data of the multimodal sensor to the digital twin synchronization engine according to the HTTP protocol; and a digital twin model construction unit for the digital twin synchronization engine to construct a digital twin model based on the set of preprocessed real-time data of the multimodal sensor to obtain the real-time digital twin model.

[0062] Specifically, preprocessing the real-time data collected in the multimodal sensor network in the industrial edge gateway by using Kalman filtering means using the Kalman filtering algorithm on the edge computing device near the sensor deployment location to remove noise and correct the estimation of the original data transmitted by the sensor. Kalman filtering is a recursive filtering algorithm based on the state space model, suitable for real-time estimation of data in dynamic systems, and can effectively reduce data fluctuations caused by sensor errors, external disturbances, etc. The industrial edge gateway is an edge computing device used in industrial scenarios, which processes data near the data source and can greatly reduce communication latency. The multimodal sensor network refers to a monitoring system composed of multiple types of sensors (such as fiber Bragg grating strain gauges, accelerometers, water level gauges, etc.), which can simultaneously obtain information in multiple physical dimensions. The set of preprocessed real-time data of the multimodal sensor refers to a set of data that is more smooth and reliable after filtering and is used by downstream modules.

[0063] Then, according to the HTTP protocol, the industrial edge gateway transmits the set of preprocessed real-time data of the multimodal sensor to the digital twin synchronization engine. The edge gateway packages and sends the data to the synchronization module in the remote server by using the communication method of the HyperText Transfer Protocol (HTTP). The HTTP protocol is an application layer communication protocol based on the request-response mode, used for data interaction between the client and the server. The digital twin synchronization engine refers to the core module for constructing and updating the digital twin model, which receives the real-time data collected by the sensor and maps it to the digital simulation system corresponding to the real system to ensure that the virtual model and the physical system are consistent in state and behavior.

[0064] Then, the digital twin synchronization engine constructs a digital twin model based on the real-time data set preprocessed by the multi-modal sensors to obtain the real-time digital twin model. Using the filtered sensor data from the field, it updates or creates a new digital twin model in real time, enabling the model to dynamically reflect the operating status of the real project. The digital twin model is a virtual object that integrates a structural model, a behavior model, and data-driven algorithms, fully replicating the state, change trend, and potential risks of the physical project in the digital space, facilitating remote monitoring, simulation prediction, and intelligent analysis.

[0065] Furthermore, this application also includes a simulation calculation unit, which is used for the digital twin synchronization engine to retrieve the finite element model and the fluid dynamics model, and perform simulation calculations on the real-time data set preprocessed by the multi-modal sensors to obtain the real-time digital twin model.

[0066] Specifically, during the process of constructing the real-time digital twin model, the digital twin synchronization engine retrieves the finite element model and the fluid dynamics model. Among them, the finite element model is a mathematical model for numerical analysis by discretizing a complex structure into many small elements, used to simulate the behaviors such as stress, deformation, and heat conduction of physical structures; while the fluid dynamics model is used to describe the flow characteristics of water bodies or gases under different boundaries and conditions, including water level changes, flow velocity distributions, and water pressure changes. The digital twin synchronization engine is the core operation module of the system, responsible for inputting real-time sensor data into the simulation model to generate a dynamically updated digital representation.

[0067] Next, the real-time data set preprocessed by the multi-modal sensors refers to high-quality data after removing noise through methods such as Kalman filtering in the edge device, including multiple dimensions such as strain data, water level data, flow velocity data, and temperature data. Simulation calculation means inputting the real-time data set preprocessed by the multi-modal sensors as boundary conditions or loads into the finite element and fluid models, and simulating the stress state and hydrodynamic response of the actual water conservancy project through numerical operations to ensure a large number of calculations can be completed in a short time.

[0068] Finally, obtaining the real-time digital twin model constructs a virtual model that is highly synchronized with the physical entity. It not only contains structural information and historical states but also can reflect the current operating state based on real-time data and has the ability to predict future states.

[0069] Furthermore, this application also includes: a 3D model construction unit for constructing a 3D model of the target water conservancy project using BIM technology and setting external load boundaries; a stress simulation unit for meshing the 3D model using ANSYS and performing stress simulation based on the external load boundaries to determine the structural stress distribution map; a finite element stress hot spot set acquisition unit for taking the points in the structural stress distribution map that exceed the preset stress threshold as the finite element stress hot spot set; and a water flow simulation unit for performing water flow simulation based on the 3D model to determine the hydrological sensitive point set.

[0070] Specifically, use BIM technology to construct a 3D model of the target water conservancy project, digitally model the water conservancy project using building information modeling technology, and generate a 3D visualization model containing geometric structures, physical properties, and construction details. BIM, that is, Building Information Modeling, is a technical means integrating design and construction information. In water conservancy projects, it can not only represent the structures of components such as dams, gates, and water channels, but also simulate the external environment. Setting external load boundaries means defining external physical action conditions such as water flow pressure, soil support, wind force, and gravity that may be applied to the engineering structure during the modeling process, providing a basis for subsequent simulation analysis.

[0071] Next, use ANSYS to mesh the 3D model, splitting the complex structure into many small cells so that the finite element software ANSYS can perform accurate numerical solutions for each small cell. ANSYS is an industrial-grade engineering simulation tool used for stress analysis, thermal analysis, and multi-physics field simulation. The fineness of the mesh division directly affects the accuracy of the simulation results. Subsequently, perform stress simulation based on the external load boundaries, input the load into the mesh model, and finally obtain the structural stress distribution map by calculating the stress response between nodes, showing the distribution of the forces borne by each part of the project under the action of external loads.

[0072] Then, take the points in the structural stress distribution map that exceed the preset stress threshold as the finite element stress hot spot set, find the areas or points in the stress distribution map that exceed the safety upper limit or critical value, and form the finite element stress hot spot set. The stress threshold is the maximum allowable stress value preset according to material strength, structural specifications, or safety factors. Areas exceeding this value may have a risk of damage and need to be focused on and sensors need to be arranged.

[0073] Finally, perform water flow simulation based on the 3D model to determine the hydrological sensitive point set. Import the 3D BIM model into the hydrodynamic simulation software, and identify the positions that are most sensitive to hydrological changes, such as points with sudden changes in flow velocity, areas with sudden changes in water level, or regions where backflows converge, by simulating the flow state of water inside and outside the structure.

[0074] Furthermore, this application also includes: a historical data acquisition unit for acquiring historical hydrological data and historical meteorological data of the area where the target water conservancy project is located; a flow velocity field distribution map generation unit for using the historical hydrological data and historical meteorological data as initial conditions, importing the three-dimensional model into water flow simulation software for water flow simulation, and generating a flow velocity field distribution map; and a hydrological sensitive point set determination unit for determining a set of hydrological sensitive points based on the flow velocity field distribution map.

[0075] Specifically, historical hydrological data and historical meteorological data of the area where the target water conservancy project is located are acquired, and hydrological information and meteorological information related to the water conservancy project in a past period of time are collected. Hydrological data includes values such as water level changes, flow rates, and rainfall amounts that reflect the characteristics and dynamics of water bodies, while meteorological data includes climate factors such as temperature, rainfall intensity, and wind speed that affect the water environment. Historical data usually comes from hydrological stations and meteorological stations and serves as the basic data for subsequent analysis.

[0076] Next, the historical hydrological data and historical meteorological data are used as initial conditions, and the historical data is input into the water flow simulation software so that the simulation process can reflect the real environmental state in the past. The water flow simulation software uses these input data in combination with the three-dimensional model for calculation and generates a flow velocity field distribution map. The three-dimensional model is a digital three-dimensional structure model of the project, and the flow velocity field distribution map shows the magnitude and direction of the water flow velocity at different positions in the water body, reflecting the hydrodynamic characteristics and variation laws.

[0077] Then, based on the flow velocity field distribution map, a set of hydrological sensitive points is determined, areas with obvious changes in flow velocity or complex hydrodynamic characteristics are analyzed, and the key points that are most sensitive to hydrological changes are identified. Hydrological sensitive points are positions where the water flow velocity suddenly changes or vortices concentrate, and are prone to water flow disorders, scouring, or sedimentation phenomena, so they are of great significance to project safety and operation management.

[0078] In summary, a water conservancy project operation and maintenance management system based on digital twin provided by this application has the following technical effects: By achieving the technical goal of intelligent sampling of multi-modal sensors driven by comparison loss and synchronous modeling linkage of digital twin, the technical effects of improving the acquisition accuracy of key data, optimizing system resource allocation, enhancing the perception ability of the operation state of water conservancy projects, and abnormal response ability are achieved.

[0079] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0080] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, this application is also intended to cover these changes and modifications.

Claims

1. A water conservancy project operation and maintenance management system based on digital twin, characterized in that The system includes: A hydrological sensitive point screening module, which is used to screen the finite element stress hotspots and hydrological sensitive points of the target water conservancy project to obtain a finite element stress hotspot set and a hydrological sensitive point set; A sensor deployment module, which is used to traverse the finite element stress hotspot set and the hydrological sensitive point set to deploy multi-modal sensors and obtain a deployed multi-modal sensor network; A digital twin model construction module, which is used to use an industrial edge gateway to push the real-time data collected in the multi-modal sensor network to a digital twin synchronization engine to construct a real-time digital twin model; A comparison loss value set determination module, which is used to perform comparison loss analysis on the real-time digital twin model and the historical digital twin model constructed in the previous synchronization to determine a comparison loss value set; A reverse mapping module, which is used to perform reverse mapping on the multi-modal sensor network based on the comparison loss value set to determine a multi-modal sensor anchor point set; An asynchronous sampling module, which is used to perform asynchronous sampling on the multi-modal sensor network according to the multi-modal sensor anchor point set and the comparison loss value set, and identify an operation and maintenance management plan according to the asynchronous sampling result to determine a target operation and maintenance management plan.

2. The operation and maintenance management system of a water conservancy project based on digital twin according to claim 1, characterized in that, The multi-modal sensor is selected from at least one of the following sensors: fiber Bragg grating strain gauge, piezoelectric accelerometer, ultrasonic water level gauge, RTD temperature probe, and smart meter.

3. The water conservancy project operation and maintenance management system based on digital twin according to claim 1, characterized in that, It includes: An association traceability analysis unit, which is used to start from the multi-modal sensor anchor point set to perform association traceability analysis on the multi-modal sensor network to determine an associated multi-modal sensor group set; An asynchronous sampling unit, which is used to determine an operation and maintenance management sampling scale set based on the comparison loss value set, and distribute the operation and maintenance management sampling scale set to the multi-modal sensor anchor point set and the associated multi-modal sensor group set for asynchronous sampling, and determine a target operation and maintenance management plan according to the asynchronous sampling result.

4. The water conservancy project operation and maintenance management system based on digital twin according to claim 3, characterized in that A network retrieval unit, which is used to retrieve the multi-modal sensor network according to a preset association range based on the position of the multi-modal sensor anchor point set and in combination with the water flow direction of the target water conservancy project to determine an associated multi-modal sensor group set.

5. The water conservancy project operation and maintenance management system based on digital twin according to claim 3, characterized in that It includes: A normalization processing unit, which is used to perform normalization processing on the comparison loss value set respectively to obtain a comparison loss feature normalization value set; An operation and maintenance management coefficient set obtaining unit, which is used to divide each comparison loss feature normalization value in the comparison loss feature normalization value set by the sum of the comparison loss feature normalization value set to obtain an operation and maintenance management coefficient set; An operation and maintenance management sampling scale set obtaining unit, which is used to traverse and calculate the difference between the operation and maintenance management coefficient set and 1, and multiply the calculation result by a preset standard sampling scale to obtain the operation and maintenance management sampling scale set.

6. The water conservancy project operation and maintenance management system based on digital twin according to claim 5, characterized in that It includes: A data acquisition unit, which is used to perform data acquisition on the multi-modal sensor anchor point set and the associated multi-modal sensor group set respectively according to the corresponding operation and maintenance management sampling scale set to obtain a multi-modal sensor anchor point sampling data sequence set and an associated multi-modal sensor group sampling data sequence set; An analysis unit is used to pre-build an operation and maintenance management solution recognizer, and the operation and maintenance management solution recognizer is used to analyze the multi-modal sensor anchor sampling data sequence set and the associated multi-modal sensor group sampling data sequence set to obtain the target operation and maintenance management solution.

7. The water conservancy project operation and maintenance management system based on digital twin according to claim 1, wherein, It includes: A preprocessing unit is used to preprocess the real-time data collected in the multi-modal sensor network in the industrial edge gateway by using Kalman filtering to obtain a set of preprocessed multi-modal sensor preprocessed real-time data; A transmission unit is used for the industrial edge gateway to transmit the set of preprocessed multi-modal sensor real-time data to the digital twin synchronization engine according to the HTTP protocol; A digital twin model construction unit is used for the digital twin synchronization engine to construct a digital twin model based on the set of preprocessed multi-modal sensor real-time data to obtain the real-time digital twin model.

8. A water conservancy project operation and maintenance management system based on digital twin according to claim 7, characterized in that, A simulation calculation unit is used for the digital twin synchronization engine to retrieve a finite element model and a fluid dynamics model to perform simulation calculations on the set of preprocessed multi-modal sensor real-time data to obtain the real-time digital twin model.

9. A water conservancy project operation and maintenance management system based on digital twin according to claim 1, characterized in that, It includes: A 3D model construction unit is used to construct a 3D model of the target water conservancy project by using BIM technology and set external load boundaries; A force simulation unit is used to perform mesh division on the 3D model by using ANSYS and perform force simulation based on the external load boundaries to determine a structural stress distribution map; A finite element stress hot spot set obtaining unit is used to use the points exceeding the preset stress threshold in the structural stress distribution map as the finite element stress hot spot set; A water flow simulation unit is used to perform water flow simulation based on the 3D model to determine a set of hydrological sensitive points.

10. A water conservancy project operation and maintenance management system based on digital twin as described in claim 9, characterized in that, It includes: A historical data acquisition unit is used to acquire historical hydrological data and historical meteorological data in the area where the target water conservancy project is located; A flow velocity field distribution map generation unit is used to use the historical hydrological data and historical meteorological data as initial conditions, import the 3D model into water flow simulation software to perform water flow simulation, and generate a flow velocity field distribution map; A hydrological sensitive point set determination unit is used to determine a set of hydrological sensitive points based on the flow velocity field distribution map.

Images