Simulation engine design method and device for digital twin intelligent pump station

Abstract

The invention provides a digital twin intelligent pump station simulation engine design method and device, relates to the technical field of hydraulic engineering operation management and digital twin, and solves the technical problems of difficult data integration, shallow analysis, weak interaction and insufficient optimization capability in the prior art. According to the method, pump station multi-source heterogeneous data are integrated, and total-factor digital representation is obtained; constructing a multi-dimensional intelligent analysis model group, and obtaining an equipment operation comprehensive analysis result; constructing a virtual-real fusion engine, and generating a real-time data bidirectional mapping relation between the pump station and the digital twin model; actual operation parameters and comprehensive analysis results are compared in real time, a self-adaptive feedback mechanism is established, and operation deviation dynamic correction and optimal energy consumption operation strategy iterative optimization are obtained; and pump station operation, water flow, environment and four-pre business data mimic simulation effects are dynamically presented. The method is used for pump station total factor perception, accurate prediction, intelligent optimization and risk intervention, the operation efficiency is remarkably improved, management is refined, and the safety guarantee capability is achieved.

Description

Technical Field

[0001] The present application relates to the fields of water conservancy project operation management and digital twin technology, and in particular to a digital twin intelligent pump station simulation engine design method and system. Background Art

[0002] As crucial hubs for water resource allocation, flood control and drainage, and irrigation and water supply, hydraulic pumping stations' operational efficiency and safety are directly linked to national economic development and the safety of people's lives and property. Traditional pumping station management relies primarily on manual inspections, empirical scheduling, and distributed monitoring systems. These approaches have ensured routine operation to a certain extent. However, as pumping stations grow in size and equipment becomes more complex, traditional management models face numerous challenges in terms of refined scheduling, equipment failure warnings, and risk prevention.

[0003] While existing technologies have introduced some informatization and automation, using various sensors to collect data for remote monitoring and basic scheduling, these systems often focus on monitoring a single indicator or localized functions, failing to effectively integrate multi-source, heterogeneous data and lacking the ability to conduct in-depth analysis and collaborative decision-making across specialized fields. Furthermore, most systems rely solely on static analysis of historical data, failing to provide a comprehensive, real-time overview of pumping station operations. Furthermore, they are unable to achieve dynamic interaction and adaptive optimization between the pumping station and digital models, resulting in low overall pumping station efficiency and delayed risk warning and emergency response. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art; to this end, this application proposes a digital twin intelligent pump station simulation engine design method and system to solve the technical problems in the prior art that pump station management relies heavily on manual experience and decentralized systems, resulting in difficulties in data integration and a lack of in-depth analysis, collaborative decision-making and real-time interaction capabilities across professional fields.

[0005] To achieve the above objectives, this application adopts the following technical solutions: The first aspect of the present application provides a digital twin intelligent pump station simulation engine design method, comprising: S1. Collect multi-source heterogeneous data from the pumping station and perform preprocessing to obtain a digital representation of all elements of the pumping station; wherein the digital representation of all elements of the pumping station is a comprehensive, digital description and representation of all relevant information and data involved in the operation of the pumping station; the preprocessing includes intelligent identification of gross errors, data cleaning, and normalization; S2. Construct a multidimensional intelligent analysis model group, and operate the multidimensional intelligent analysis model group based on the digital representation of all elements of the pump station to obtain a comprehensive analysis result of the equipment operation; The multi-dimensional intelligent analysis model group includes an electromechanical equipment health diagnosis model, a pump station variable angle and variable speed integrated optimization scheduling model, an engineering safety early warning model, and an incoming water quality forecast model. The comprehensive analysis results include equipment operating status assessment, optimal energy consumption operation strategy, building safety early warning, and water pollutant evolution trends. S3. Build a virtual-reality fusion engine based on the comprehensive analysis results to generate a bidirectional mapping relationship between the pump station and the digital twin model; S4. Using the bidirectional mapping relationship, the actual operating parameters of the pumping station are compared with the comprehensive analysis results of the equipment operation in real time, and an adaptive feedback mechanism is established to obtain dynamic correction of pumping station operation deviations and an optimal energy consumption operation strategy; S5. Utilize the digital representation of all elements of the pumping station and the comprehensive analysis results of equipment operation, integrate geographic space and BIM / GIS to construct a mimetic simulation.

[0006] Based on the above technical solution, a digital twin intelligent pump station simulation engine design method provided in this application has made a breakthrough in solving the dual challenges of low operating efficiency and weak risk response caused by the coexistence of data fragmentation and decision-making lag in traditional pump station management: by constructing a collaborative design method of "multi-source heterogeneous data integration-multi-dimensional intelligent analysis model group-virtual-reality bidirectional mapping-adaptive closed-loop optimization-mimetic simulation presentation", all the operational data of the pump station are uniformly digitally represented, and cross-domain in-depth analysis is carried out through a professional model group to achieve real-time interaction and dynamic synchronization between the pump station and the digital twin model; at the same time, the hierarchical deviation threshold and iterative optimization feedback mechanism are innovatively introduced to synchronously perform instruction correction and strategy adjustment during operation, effectively avoiding the response lag and resource waste caused by traditional manual intervention, and significantly improving the prediction accuracy and safety assurance capabilities of the pump station under complex working conditions.

[0007] In conjunction with the first aspect above, in a possible implementation, the multi-source heterogeneous data includes: operating status of electromechanical equipment, hydraulic engineering structure monitoring data, environmental quantities, and incoming water quality; The operating status of the electromechanical equipment is the vibration amplitude, swing, temperature, current, pressure and flow parameters of the pump when the electromechanical equipment of the pump station is running; The hydraulic engineering structure monitoring data is the engineering monitoring data of the horizontal and vertical displacement, seepage, structure and environmental quantities of the sluice; The inflow water quality is the inflow water quality monitoring data of national, provincial, county and self-owned water quality monitoring stations; The environmental quantities include water level, rainfall and air temperature.

[0008] In conjunction with the first aspect above, in one possible implementation, building a multi-dimensional intelligent analysis model group includes: Based on the digital representation of all elements of the pump station, a health diagnosis model for electromechanical equipment based on multi-information fusion is established; Adopting dynamic programming or large-scale system test optimization theory and integrating the dual adjustment mechanism of blade placement angle and pump speed, a pump station variable angle and variable speed integrated optimization scheduling model is constructed; Based on the digital representation of all elements of the pump station, an engineering safety monitoring and early warning model is obtained by using intelligent identification of gross errors, mathematical statistics and neural network analysis; Using the law of conservation of mass and advection diffusion, the hydrodynamic and water quality modules are integrated to obtain the incoming water quality forecast model; For indoor and outdoor scenes of the pump station, scene recognition and offline training are performed through offline training and online detection to build an artificial intelligence image recognition model.

[0009] In conjunction with the first aspect above, in one possible implementation, the method for obtaining the comprehensive analysis result of the device operation includes: Generate an equipment operation status assessment and health status through the electromechanical equipment health diagnosis model, wherein the health status includes good, available, and maintenance required; The optimal number of pumping units, blade placement angle and speed, and total energy consumption of the pumping station are calculated through the pumping station variable angle-speed integrated optimization scheduling model; Through the engineering safety monitoring and early warning model, the safety status and early warning information of the water conservancy project buildings are analyzed; The water quality prediction model is used to predict the water quality index values ​​and pollutant concentration change trends of the water in a specific river section; The artificial intelligence image recognition model is used to obtain real-time image recognition results of indoor and outdoor scenes of the pump station.

[0010] In conjunction with the first aspect above, in one possible implementation, the real-time image recognition result includes: Identify equipment operating status and visible smoke and flames in the main powerhouse and machine room of the pump station; Identify floating objects on the water surface, water gauges, vehicle and personnel intrusions, and gate opening and closing status in outdoor scenes of pump stations.

[0011] In conjunction with the first aspect above, in one possible implementation, building a virtual-reality fusion engine includes: Synchronize the real-time data of the pump station’s operating parameters with the digital twin model to achieve consistency between the physical entity and the digital model; Based on the state consistency between the physical entity and the digital model, a simulation driving logic is constructed, and the comprehensive analysis results of the device operation are used to drive the digital twin model to obtain simulation data; a bidirectional mapping relationship is established based on the real-time data and the simulation data to present a high-fidelity dynamic simulation effect; Through the high-fidelity dynamic simulation effect, a real-time data bidirectional mapping relationship is generated, and the digital twin model sends remote control instructions to the pump station to obtain the pump station's instruction response.

[0012] In conjunction with the first aspect above, in one possible implementation, establishing an adaptive feedback mechanism includes: According to the actual deviation between the comprehensive analysis result of the equipment operation and the actual operating parameters of the pump station, a multi-level deviation threshold is set, wherein the multi-level deviation threshold includes a low-level deviation threshold, a unit deviation threshold and a target deviation threshold; When the absolute value of the actual deviation is less than the low-level deviation threshold, a maintenance signal is generated to maintain the original instruction execution; When the absolute value of the actual deviation is greater than the low-level deviation threshold and less than the unit deviation threshold, adjusting the unit operation state of the pump station; When the absolute value of the actual deviation is greater than the unit deviation threshold and less than the target deviation threshold, adjusting the optimal energy consumption operation strategy of the pump station; When the absolute value of the deviation is greater than the target deviation threshold, an early warning signal is generated, an emergency mechanism is activated, and early warning and timely intervention measures are taken.

[0013] In combination with the first aspect above, in one possible implementation, constructing the mimicry simulation includes: Integrate terrain images, digital elevation, oblique photography, and laser point cloud data in BIM / GIS to build a visualization model of the natural background of the project; The water flow field is simulated by flowing particles, and the particles or fluid surface are colored according to the water level and sediment content information to construct a dynamic visual mimicry model of the upstream and downstream flow fields of the project; Construct a visualization model of the water conservancy project based on the geographic information system and building information of the pumping station; Carry out detailed modeling of components in the pump station and construct a visual model of hydraulic electromechanical equipment; The comprehensive analysis results of the equipment operation are input into the engineering natural background visualization model, dynamic visualization mimicry model, water conservancy project visualization model and water conservancy electromechanical equipment visualization model to obtain mimicry simulation, which is dynamically displayed in the form of data view, and mimicry simulation is performed on the previewed historical analysis data and calculation results.

[0014] In conjunction with the first aspect above, in a possible implementation, constructing a water conservancy project visualization model includes: Generate a digital twin scene using the pump station's architectural information, including BIM models, CAD drawings, flight data, videos, and photos. Based on the digital twin scenario, perform lighting calculations on the physical entity properties and environmental properties of the pump station and build a physically based material shading model. The digital twin scene is integrated with the physically based material shading model to construct a visualization model of the water conservancy project.

[0015] Secondly, a digital twin intelligent pump station simulation engine device is provided, including: a communication unit and a processing unit; the communication unit is used to integrate multi-source heterogeneous data such as the operation of electromechanical equipment of the pump station, structural monitoring of water conservancy projects, environmental quantities, incoming water quality and manual inspections, generate a real-time data bidirectional mapping relationship between the pump station and the digital twin model, and receive the actual operation parameters of the pump station; the processing unit is used to obtain a digital representation of all elements of the pump station, construct a multi-dimensional intelligent analysis model group, obtain a comprehensive analysis result of the equipment operation, construct a virtual-reality fusion engine, compare the actual operation parameters of the pump station with the comprehensive analysis result of the equipment operation in real time, establish an adaptive feedback mechanism, obtain dynamic correction of the pump station operation deviation and iterative optimization of the optimal energy consumption operation strategy, and dynamically present the simulation effect of the pump station operation, water flow dynamics, environmental changes and "four prediction" business data.

[0016] In a third aspect, the present application provides a digital twin intelligent pumping station simulation engine device, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is configured to execute the instructions to implement the method described in the first aspect and any possible implementation of the first aspect. The digital twin intelligent pumping station simulation engine device can be an electronic device or a chip within an electronic device.

[0017] Fourthly, the present application provides a digital twin intelligent pump station simulation engine system, including: a data acquisition module, a calculation and analysis module and a visualization presentation module; wherein, the data acquisition module is used to obtain multi-source heterogeneous data on the operation of pump station electromechanical equipment, water conservancy project structure monitoring, environmental quantities, incoming water quality and manual inspections; the calculation and analysis module is used to construct a multi-dimensional intelligent analysis model group, obtain comprehensive analysis results of equipment operation, and drive the digital twin model to perform dynamic simulation; the visualization presentation module is used to dynamically present the mimetic simulation effects of pump station operation, water flow dynamics, environmental changes and "four pre-" business data.

[0018] In the fifth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are run on a digital twin intelligent pumping station simulation engine device, the digital twin intelligent pumping station simulation engine device executes the method described in the first aspect and any possible implementation of the first aspect.

[0019] In the sixth aspect, the present application provides a computer program product comprising instructions, which, when run on a digital twin intelligent pumping station simulation engine device, enables the digital twin intelligent pumping station simulation engine device to execute the method described in the first aspect and any possible implementation of the first aspect.

[0020] This application provides a digital twin intelligent pump station simulation engine design method and system, which can realize full-factor perception, accurate prediction, intelligent optimization, and risk intervention of the pump station, significantly improving operational efficiency, refined management, and safety assurance capabilities.

[0021] Compared with the prior art, the present invention has the following advantages: 1. This application integrates heterogeneous data from multiple sources, including electromechanical equipment operation, water conservancy project structure monitoring, environmental quantities, incoming water quality, and manual inspections, to achieve a comprehensive, digital, and unified representation of the operating status of a pump station. On this basis, a multi-dimensional intelligent analysis model group has been constructed, including electromechanical equipment health diagnosis, integrated optimization scheduling of variable angle and variable speed pump stations, water conservancy project safety warnings, watershed incoming water quality forecasts, and artificial intelligence image recognition. This breaks through the limitations of traditional systems that focus on single functions or local analysis, and achieves in-depth intelligent analysis and comprehensive assessment of pump stations across professional fields, significantly improving the scientific nature of decision-making and the timeliness of warnings.

[0022] 2. This application generates a real-time, high-fidelity bidirectional mapping relationship between the pump station and the digital twin model by building a virtual-reality fusion engine. The system can compare the actual operating parameters of the pump station with the comprehensive analysis results in real time and establish an adaptive feedback mechanism. This mechanism triggers differentiated dynamic corrections and iterative optimization of strategies based on multi-level deviation thresholds. This enables the system to actively identify situations where water levels and flows are approaching warning values, generate early warning information, and activate emergency mechanisms, transforming traditional passive responses into active, intelligent process control and risk intervention, greatly improving the timeliness and effectiveness of risk response.

[0023] 3. This application integrates geospatial technology, BIM / GIS, and equipment component models, and through physics-based material shading and fluid simulation algorithms, dynamically presents the simulated effects of pump station operation, water flow dynamics, environmental changes, and "four pre-" business data. The system constructs a visualization model of the natural background of the project, flow field dynamics, water conservancy projects, and water conservancy electromechanical equipment, providing managers with an intuitive, realistic, and interactive decision-making support interface, achieving an end-to-end full-process management closed loop from data collection to intelligent analysis, virtual-reality interaction, optimization feedback, and visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the digital twin intelligent pump station simulation engine system architecture provided in an embodiment of the present application; Figure 2 A schematic diagram of the overall process of a digital twin intelligent pump station simulation engine design method provided in an embodiment of the present application; Figure 3 A schematic diagram of bidirectional mapping of virtual-reality fusion engine data provided in an embodiment of the present application; Figure 4 Schematic diagram of a deviation correction process of an adaptive feedback mechanism provided in an embodiment of the present application Figure 5 A schematic structural diagram of a digital twin intelligent pump station simulation engine device provided in an embodiment of the present application; Figure 6 A schematic diagram of the hardware structure of a digital twin intelligent pump station simulation engine device provided in an embodiment of the present application; DETAILED DESCRIPTION

[0025] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "a plurality" means two or more. Words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not limit them to be necessarily different.

[0027] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0028] The digital twin intelligent pump station simulation engine design method provided in the embodiment of the present application can be applied to Figure 1 In the digital twin intelligent pump station simulation engine system 100 shown in FIG. Figure 1As shown, the simulation engine system 100 includes: a data acquisition device 10 , a computing server 20 , a control executor 30 and a visualization terminal 40 .

[0029] Data acquisition equipment 10, such as vibration sensors, temperature sensors, flow meters, water quality monitoring stations, and IP cameras, is responsible for acquiring real-time, multi-source, heterogeneous data, including pump station electromechanical equipment operating parameters, water conservancy project structure monitoring data, environmental parameters, incoming water quality, and manual inspection data. After preliminary processing, this data is transmitted to computing server 20.

[0030] Computing server 20 receives data and is responsible for building and operating a multi-dimensional intelligent analysis model cluster, including electromechanical equipment health diagnosis, pump station optimization and scheduling, water conservancy project safety warnings, water quality forecasts for incoming water in the basin, and artificial intelligence image recognition. Computing server 20 builds a virtual-reality fusion engine to generate a real-time, bidirectional data mapping relationship between the pump station and the digital twin model. It also compares the actual operating parameters of the pump station with the comprehensive analysis results of equipment operation in real time, establishing an adaptive feedback mechanism to dynamically correct pump station operating deviations and iteratively optimize the optimal energy consumption operation strategy. When necessary, computing server 20 will issue remote control instructions to the control actuator 30 or generate warning information.

[0031] The control actuator 30, such as a programmable logic controller (PLC), intelligent gate controller, or frequency converter, receives remote control commands from the computing server 20. Based on the commands, the control actuator 30 adjusts the actual operation of physical devices such as the operating status of pump station units and the opening and closing of gates.

[0032] Visualization terminals 40, such as monitors, large-screen display systems, and consoles, are interconnected with computing servers 20 to receive digital representations of all pumping station elements, comprehensive equipment operation analysis results, and dynamically revised and optimized strategies. By integrating geospatial information, BIM / GIS, and equipment component models, and using physical rendering and dynamic effects, visualization terminals 40 dynamically present simulated data on pumping station operations, water flow dynamics, environmental changes, and the "four predictions" business data, providing managers with an intuitive decision-making support interface.

[0033] In order to solve the technical problems in the prior art that pump station management relies heavily on manual experience and decentralized systems, resulting in difficulties in data integration and a lack of in-depth analysis, collaborative decision-making, and real-time interaction capabilities across professional fields, the present application embodiment provides a digital twin intelligent pump station simulation engine design method, which includes: integrating multi-source heterogeneous data on pump station electromechanical equipment operation, water conservancy project structure monitoring, environmental quantities, incoming water quality, and manual inspections to obtain a digital representation of all elements of the pump station; based on the digital representation, using multi-information fusion, trend prediction, deep learning, and dynamics methods, a multi-dimensional intelligent analysis model group is constructed to obtain equipment operation data. Comprehensive analysis results; Based on the comprehensive analysis results, a virtual-reality fusion engine is constructed to generate a real-time data bidirectional mapping relationship between the pump station and the digital twin model; Through this bidirectional data mapping relationship, the actual operating parameters of the pump station are compared with the comprehensive analysis results in real time, and an adaptive feedback mechanism is established to obtain dynamic corrections to pump station operation deviations and iterative optimization of the optimal energy consumption operation strategy; Using this digital representation and comprehensive analysis results, the geographic space, BIM / GIS and equipment component models are integrated, and through physical rendering and dynamic special effects, the mimetic simulation effects of the pump station operation, water flow, environment and "four pre-" business data are dynamically presented. Based on this, this application can achieve full-factor perception, accurate prediction, intelligent optimization, and risk intervention of the pump station, significantly improving operational efficiency, refined management, and safety assurance capabilities.

[0034] like Figure 2 As shown, the digital twin intelligent pump station simulation engine design method provided in the embodiment of the present application includes: S1. Integrate multi-source heterogeneous data on pump station electromechanical equipment operation, water conservancy project structure monitoring, environmental parameters, incoming water quality, and manual inspections to obtain a digital representation of all elements of the pump station; Among them, the digital representation of all elements of the pumping station is a comprehensive, digital description and representation of all relevant information and data involved in the operation of the pumping station.

[0035] In some implementations, a unified access module is established to receive multiple heterogeneous data sources from inside and outside the pumping station to ensure comprehensive data aggregation. The access module supports multiple protocols and interface standards and can cope with complex and diverse data acquisition software and hardware and network environments. The acquired raw data will undergo unified preprocessing before being input into the subsequent analysis module, including intelligent identification of gross errors, data cleaning and normalization. These preprocessings are designed to filter out outliers, noise and redundant information caused by data source failures or transmission anomalies, and unify data of different dimensions into a comparable range, thereby improving the data quality and processing efficiency of subsequent intelligent analysis models.

[0036] For example, when this application collects PM2.5 concentration data and COD (Chemical Oxygen Demand) data from a water quality monitoring station, and obtains equipment dashboard video images from the pump room IP camera, the data base device will align the timestamps of these data from different sensors and devices, and automatically detect and mark abnormal data through the gross error intelligent recognition function; through the data cleaning process, these abnormal data or high-noise parts are removed or smoothed; each data is normalized, for example, flow data of different units are unified into cubic meters per second; for video image data, even if its resolution is low or there is fog, the data base device will optimize it through resolution enhancement and image defogging processing and other technologies; these processed electromechanical equipment operating parameters, engineering monitoring data, incoming water quality data, and video image data in a unified format together constitute a digital representation of all elements of the pump station during that period, and can be called by multi-dimensional intelligent analysis equipment.

[0037] S2. Based on the digital representation of all elements of the pumping station, we use multi-dimensional information fusion, trend prediction, deep learning and dynamic methods to build a multi-dimensional intelligent analysis model group to obtain comprehensive analysis results of equipment operation; Among them, the multi-dimensional intelligent analysis model group includes the electromechanical equipment health diagnosis model, the pump station variable angle and variable speed integrated optimization scheduling model, the engineering safety early warning model, the incoming water quality forecast model and the artificial intelligence image recognition model; the comprehensive analysis results are equipment operation status assessment, optimal energy consumption operation strategy, building safety early warning and water pollutant evolution trend.

[0038] In some implementations, a modular analysis framework is established to feed data from the digital representation of all pumping station elements into different analysis modules for processing. These modules operate independently but collaborate with each other at the data level to jointly process and analyze data to generate comprehensive, integrated analyses of equipment operations.

[0039] S3. Based on the comprehensive analysis results, a virtual-reality fusion engine is constructed to generate a real-time bidirectional mapping relationship between the pump station and the digital twin model; In some implementations, it is used to synchronize real-time operating parameters from the pump station with the digital twin model in real time to ensure the state consistency between the physical entity and the digital model. Based on this state consistency between the physical entity and the digital model, a set of comprehensive analysis results of equipment operation obtained by a multi-dimensional intelligent analysis model group is constructed to drive the driving logic of the digital twin model to perform working condition evolution and event simulation, thereby presenting a high-fidelity dynamic simulation effect. In order to achieve an interactive closed loop between the physical world and the digital world, the engine will also implement a two-way interactive interface to support the digital twin model to issue remote control instructions to the pump station, and can trigger the generation of early warning information for situations where water levels, flows, etc. are approaching warning values ​​based on the comprehensive analysis results, ultimately obtaining the pump station's command response and risk intervention capabilities.

[0040] For example, when the virtual-reality fusion engine receives a comprehensive equipment operation analysis result from the multi-dimensional intelligent analysis module, indicating that "the current vibration value of pump station unit A is abnormal and a failure is expected within the next 24 hours," the engine immediately updates the vibration status of unit A in the digital twin model and simulates its failure evolution, dynamically presenting the simulation effect of increased vibration and temperature rise in unit A. Furthermore, if the "pump station variable angle and speed integrated optimization scheduling model" calculates that the unit operation strategy needs to be adjusted to prevent the failure from escalating, the virtual-reality fusion engine will issue a remote control command to the pump station through a two-way interactive interface to adjust the operating load of unit A. If, after the command is issued, the monitoring system reports that the vibration value of unit A continues to deteriorate and approaches the warning value, the virtual-reality fusion engine will immediately trigger the generation of an early warning message and activate emergency response mechanisms. For example, in the digital twin scenario, the engine will simulate the shutdown of unit A and display the changes in water flow status after the shutdown and the evolution of the emergency plan to the management personnel.

[0041] S4. Through bidirectional data mapping, the actual operating parameters of the pumping station are compared with the comprehensive analysis results of equipment operation in real time, and an adaptive feedback mechanism is established to obtain dynamic correction of pumping station operation deviations and iterative optimization of the optimal energy consumption operation strategy; In some implementations, deviations between the actual pumping station operating parameters and the comprehensive analysis results of equipment operation are continuously monitored and analyzed. This mechanism can promptly detect deviations, summarize operating patterns, and dynamically adjust subsequent correction and optimization strategies based on the size and nature of the deviations. This feedback mechanism continuously learns and adapts to the complexity of pumping station operations, ensuring that deviations are dynamically and effectively corrected.

[0042] It should be noted that by establishing this adaptive feedback mechanism, this application can promptly detect deviations in pump station operation, summarize the patterns, and take differentiated corrective measures based on the level of deviation. This transforms pump station management from traditional passive response to active discovery and intelligent intervention, significantly improving the economic and safety of pump station operations.

[0043] S5. Utilize the digital representation of all elements of the pump station and the comprehensive analysis results, integrate geographic space, BIM / GIS and equipment component models, and through physical rendering and dynamic special effects, dynamically present the simulated effects of pump station operation, water flow dynamics, environmental changes and "four prediction" business data.

[0044] In some implementations, a multi-layered 3D visualization framework is constructed to integrate digital representations of all pumping station elements from diverse data sources with comprehensive analysis results generated by various models. This framework seamlessly integrates macroscopic geographic environmental information, mesoscopic hydraulic engineering structure information, and microscopic equipment component information. By applying high-fidelity physical rendering technology and rich dynamic effects, it simulates and presents the pumping station's operating status, dynamic changes in water flow, the impact of environmental factors, and "four prediction" business data in real time.

[0045] It's important to note that the visualization design of this application not only pursues accurate data presentation, but also focuses on providing an immersive experience with strong simulation capabilities, seamless integration of detail, realistic water representation, and physical material models. This can significantly enhance users' intuitive understanding of the overall operation and future trends of the pumping station, and improve decision-making efficiency.

[0046] Based on the above technical solution, the digital twin intelligent pump station simulation engine design method provided in this application has made a breakthrough in solving the dual challenges of low operating efficiency and weak risk response caused by the coexistence of data fragmentation and decision-making lag in traditional pump station management: by constructing a collaborative design method of "multi-source heterogeneous data integration-multi-dimensional intelligent analysis model group-virtual-reality bidirectional mapping-adaptive closed-loop optimization-mimetic simulation presentation", the full-factor data of the pump station operation are uniformly digitally represented, and cross-domain in-depth analysis is carried out through a professional model group to achieve real-time interaction and dynamic synchronization between the pump station and the digital twin model; at the same time, the hierarchical deviation threshold and iterative optimization feedback mechanism are innovatively introduced to synchronously perform instruction correction and strategy adjustment during operation, effectively avoiding the response lag and resource waste caused by traditional manual intervention, and significantly improving the prediction accuracy and safety assurance capabilities of the pump station under complex working conditions.

[0047] Furthermore, in the embodiments of this application, this method achieves full-factor perception, precise prediction, intelligent optimization, and risk intervention of the pump station's operating status, significantly improving the operational efficiency, refined management, and safety assurance capabilities of water conservancy pump stations. This transforms pump station management from a traditional passive response model to a modern model of active discovery and intelligent intervention, providing visual model support for engineering scheduling and control simulation, equipment operation and maintenance, fault diagnosis and analysis, and enhancing users' perception of the meaning of forecast and warning data, as well as their further understanding of solutions or conclusions.

[0048] In a possible implementation of the embodiment of the present application, combined with Figure 2 As shown, multi-source heterogeneous data includes the following data: S11. Collect the vibration, swing, temperature, current, pressure and flow parameters of the pump when the electromechanical equipment of the pump station is running.

[0049] In some implementations, the present application uses various sensors deployed at the Denglou Pumping Station to obtain real-time operating parameters such as pump vibration, swing, temperature, current, pressure, and flow. These parameters are key inputs for assessing equipment health and optimizing operation, and are transmitted to the data acquisition device 10 via a wired or wireless network for preliminary aggregation.

[0050] S12. Collect engineering monitoring data on the horizontal and vertical displacement, seepage, structure and environmental quantities of the sluice.

[0051] In some implementations, this application supports automated access to sluice gate horizontal and vertical displacement, seepage, structural, and environmental data using displacement sensors, seepage monitors, and structural stress gauges. Furthermore, to fully cover monitoring needs, this application also supports the entry of manual observation and inspection data. For example, specific sluice gate displacement data or abnormalities discovered during equipment inspections can be entered into the system through mobile terminal applications or manual report submission to fill in blind spots in automated monitoring.

[0052] S13. Collect incoming water quality monitoring data from own water quality monitoring stations.

[0053] S14: Collect video image data obtained through IP cameras, FTP or HTTP protocols, and perform gross error intelligent identification, data cleaning and normalization processing on the video image data.

[0054] In some implementations, this application supports access to multiple video image data sources. For existing video surveillance platforms, this application supports docking using the SDK interface to automatically obtain image information. In addition, for scenarios without cameras or third-party transmission, this application also supports file transfer based on FTP and HTTP protocols for accessing image data. The acquired raw video image data will undergo unified preprocessing before being input into the subsequent analysis module, including intelligent identification of gross errors, data cleaning, and normalization.

[0055] Based on the above technical solution, this application provides comprehensive integration and high-quality preprocessing of multi-source heterogeneous data, laying a solid data foundation for the construction of the digital twin intelligent pump station simulation engine, and significantly improving the accuracy and reliability of subsequent intelligent analysis.

[0056] In one possible implementation, combining Figure 2 As shown, the multi-dimensional intelligent analysis model group includes the following models: S21. Establish a health evaluation index system that integrates multiple information, and use the digital representation of all elements of the pump station to obtain a health diagnosis model for electromechanical equipment.

[0057] In some implementations, the electromechanical equipment health diagnosis model does not use a single measurement parameter in traditional monitoring models. Instead, it establishes a multi-information fusion electromechanical equipment health evaluation index system to comprehensively evaluate component status from multiple perspectives. The model input includes pump vibration, swing, temperature, current, pressure, flow index, weight information of each index, and the numerical range of various evaluation states. The comprehensive evaluation value of electromechanical equipment is calculated as follows:

[0058] Where, D represents the comprehensive evaluation value of the equipment; Indicates the weight value of the i-th indicator; In order to make the overall status of the on-site equipment easier to grasp, this application divides the overall indicators into three levels according to their value ranges: good, usable, and needs maintenance.

[0059] S22. Integrate the dual adjustment mechanism of blade placement angle and pump speed, use dynamic programming or large system test optimization theory to construct an optimization algorithm, and obtain the pump station variable angle and variable speed integrated optimization scheduling model.

[0060] In some implementations, the variable angle and variable speed integrated optimization scheduling model of the pump station aims to reduce energy consumption and ensure safety, and studies the scientific management optimization scheduling technology of the pump station. Under the premise of meeting all constraints, the determined optimal criteria are followed to make the objective function of the pump station optimization reach an extreme value. In the optimization operation of a single unit, the minimum energy consumption is used as the objective function, the total amount of water transfer and the water transfer time are used as constraints, and the blade angle, pump speed, and water level change of the single unit are used as state variables. The energy consumption of the pump station is calculated as follows:

[0061] Where, Indicates energy consumption; N indicates the total number of time periods divided according to the discrete conditions of the head; Refers to the water pump flow rate in the i-th period; represents the average lift in the i-th period; Indicates the power-on time of the i-th period; It is a power-related item, and its calculation involves the actual operating power and rated power ; represents the specific gravity of water; g represents the acceleration due to gravity; Indicates the efficiency of hydraulic devices; Indicates the motor efficiency; Indicates the transmission efficiency.

[0062] S23. Based on the digital representation of all elements of the pump station, the engineering safety monitoring and early warning model is obtained by using intelligent identification of gross errors, mathematical statistics and neural network analysis.

[0063] In some implementations, the engineering safety monitoring and early warning model supports the automatic access of displacement, seepage, structural, and environmental data, as well as manual observations of sluice horizontal and vertical displacements and inspection data. The model combines data mining techniques based on unsupervised or semi-supervised knowledge discovery with gross error detection methods based on statistical regression analysis and engineering experience to automatically identify abnormal measurements in single measurement points and in data series with one- and two-dimensional distributed measurement points. Furthermore, using mathematical statistics models and neural network technology, it reveals the changing patterns of monitoring effect quantities and the degree to which environmental quantities influence them, thereby evaluating the safety status of buildings and providing forecasts and early warnings.

[0064] S24. Integrate the hydrodynamic and water quality modules and use the law of mass conservation and advection diffusion to obtain the incoming water quality forecast model.

[0065] In some implementations, the incoming water quality forecasting model primarily simulates the temporal and spatial migration and transformation of pollutants. It consists of a hydrodynamic simulation module and a water quality simulation module. Based on the EFDC hydrodynamic model, it covers simulations of one- to three-dimensional flow fields, material transport, and pollutant migration and transformation processes. The model utilizes the governing hydrodynamic equations for conservation of mass, momentum, and energy, as well as the governing equations for water quality variables.

[0066] S25. Identify the indoor and outdoor scenes of the pump station through offline training and online detection to obtain an artificial intelligence image recognition model.

[0067] In some implementations, this AI image recognition model identifies different objects in both indoor and outdoor scenarios, tailored to the business needs of daily pump station management. Indoors, it primarily monitors equipment operating status and visible smoke and flames, while outdoor recognition focuses on identifying floating objects on the water surface, water gauges, vehicle and human intrusions, and gate opening and closing status.

[0068] Based on the above technical solution, this application realizes a comprehensive, in-depth and intelligent analysis of the operating status of the pumping station through the refined construction of a multi-dimensional intelligent analysis model group, significantly improving the prediction accuracy, diagnostic accuracy, warning timeliness and optimization decision-making level, and providing solid technical support for the safe and efficient operation of the pumping station.

[0069] In one possible implementation, combining Figure 2 As shown, the comprehensive analysis results of the equipment operation can be obtained through the following S31, S32, S33, S34 and S35, which are specifically described below: S31. Generate equipment operation status assessment and health level through the electromechanical equipment health diagnosis model; Among them, the health levels include good, usable and needing maintenance; the electromechanical equipment health diagnosis model is a health evaluation index system based on the fusion of multiple information, which comprehensively evaluates the status of components from multiple angles.

[0070] In some implementations, the model monitors pump parameters such as vibration, swing, temperature, current, pressure, and flow in real time and calculates a comprehensive equipment evaluation value. Based on the equipment's comprehensive evaluation value and its range, the health level is classified into three levels. Furthermore, the model predicts the future operation of electromechanical equipment and performs fault diagnosis, providing data support for condition-based maintenance and enabling predictive maintenance.

[0071] S32. Calculate the optimal number of pumping units, blade placement angle and speed, and total energy consumption of the pumping station using the pumping station variable angle and speed integrated optimization scheduling model. Among them, the pump station variable angle and variable speed integrated optimization scheduling model aims to reduce energy consumption and ensure safety.

[0072] In some implementations, the model uses real-time or predicted net head and pumping flow operating parameters, combined with the operating characteristic curves of multiple pumping units in the pumping station, to calculate the optimal unit combination, as well as the optimal blade angle and speed for each unit, while meeting water transfer requirements. Using dynamic programming or large-scale system test optimization algorithms, the model can determine the minimum energy consumption required to complete the required total water transfer within a specific time period and provide a corresponding operating strategy. This directly outputs the optimal number of pumping units in operation, blade angle, and speed, as well as the total energy consumption of the pumping station under this optimization strategy.

[0073] S33. Analyze and obtain the safety status and early warning information of water conservancy project buildings through the engineering safety monitoring and early warning model; Among them, the engineering safety monitoring and early warning model can support the automatic access of data such as displacement, seepage, structure and environmental quantities, as well as the access of manual observation data and inspection data.

[0074] In some implementations, the model uses intelligent gross error recognition technology to automatically identify and eliminate abnormal measurements in collected displacement, seepage, structural, and environmental monitoring data. Using mathematical statistics and neural network techniques, it analyzes the changing patterns of monitoring effect quantities and their relationships with independent variables such as water level, rainfall, and temperature. Through these analyses, the model can assess the current safety status of water conservancy project structures and generate corresponding safety status reports and warning information based on preset thresholds or abnormal patterns.

[0075] S34. Using the inflow water quality prediction model, predict the predicted index values ​​of the inflow water quality and the trend of pollutant concentration changes in a specific river section; Among them, the incoming water quality prediction model is used to simulate the migration and transformation process of pollutants in time and space, and consists of a hydrodynamic simulation module and a water quality simulation module.

[0076] In some implementations, the model is based on the EFDC hydrodynamic model and water quality module, integrating historical and real-time data from national, provincial, county, and in-house water quality monitoring stations. The model applies the governing hydrodynamic equations for conservation of mass, momentum, and energy, as well as the governing equations for water quality variables, to simulate the advection, physical transport, and migration and transformation of multiple water quality variables within the river, including cyanobacteria, diatoms, ammonia nitrogen, COD, and dissolved oxygen. Through parameter calibration and validation, the model can predict future water quality indicators for specific river sections and the temporal trends of these pollutants, providing forward-looking forecasts for water quality safety.

[0077] S35. Using an artificial intelligence image recognition model, real-time image recognition results of indoor and outdoor scenes of the pumping station are obtained.

[0078] Among them, the artificial intelligence image recognition model identifies different objects in indoor and outdoor scenes based on the business needs of daily management of pumping stations.

[0079] In some implementations, the model accesses video image data obtained through IP cameras, FTP, or HTTP protocols, and performs resolution enhancement, defogging / rain removal, reflection removal, and ripple processing on the images to optimize recognition quality. For indoor scenarios, the model can identify the operating status of equipment in areas such as the main plant and computer room in real time. For outdoor scenarios, the model can identify floating objects on the water surface to avoid water pollution risks; identify physical water gauges or manually calibrate water levels without water gauges to obtain water level data; detect vehicle and personnel intrusions, and issue alerts for illegal entry into key prevention areas; and identify the open and closed status of gates, automatically analyzing changes in gate openings to address the limitations of traditional detection switches.

[0080] Based on the above technical solution, this application realizes a comprehensive, in-depth and intelligent analysis of the operating status of the pumping station through the refined construction of a multi-dimensional intelligent analysis model group, significantly improving the prediction accuracy, diagnostic accuracy, warning timeliness and optimization decision-making level, and providing solid technical support for the safe and efficient operation of the pumping station.

[0081] In one possible implementation, combining Figure 2 As shown, the real-time image recognition result can be obtained specifically through the following S41, S42 and S43, which are specifically described below: S41. Identify the equipment operating status, smoke and fire in the main factory building and computer room.

[0082] In some implementations, an AI image recognition model uses deployed video surveillance systems to capture real-time images of key indoor locations, including the main plant building, capacitor room, protection room, and computer room. Using deep learning algorithms, the model analyzes video streams to accurately identify instrument readings and indicator light status, thereby determining the current operating status of the equipment. The model is also specifically designed to detect potential smoke or flames indoors. If such detection occurs, the system immediately issues an alert, outputting an alarm image, target area, alarm type, and target ID to prevent fires and other safety incidents.

[0083] It should be pointed out that through real-time identification of the operating status of indoor scene equipment and open smoke and flames, the intelligence level of internal safety monitoring of the pump station and the response speed to abnormal events have been significantly improved.

[0084] For example, if video surveillance captures an abnormal reading on a dashboard in the main plant, the AI ​​image recognition model immediately identifies the abnormal reading and, based on pre-set rules, determines it as an equipment anomaly, issuing a real-time alert and warning. Furthermore, if the model detects a flame in the machine room video, it immediately triggers an open flame alarm, delineates the flame area using the image, and reports the alarm to the management platform.

[0085] S42. Identify floating objects on the water surface, water gauges, vehicle and human intrusions, and gate opening and closing status in outdoor scenes.

[0086] It should be pointed out that the intelligent identification of multiple types of targets in outdoor scenes has greatly improved the efficiency of safety monitoring, hydrological information acquisition and operation management of the pump station's peripheral environment.

[0087] For example, if the model detects large accumulations of floating debris in a water channel video feed, it will immediately identify and issue a "Floating Debris Alert." If unauthorized entry into a restricted area around a pump station is detected, the system will immediately trigger a "Personnel Intrusion Alert." Furthermore, if a gate opening monitoring video shows the gate half-open, the model will automatically identify the opening scale and send this status information to the control system.

[0088] S43. Optimize the quality of real-time image recognition results through resolution enhancement, defogging, rain removal, reflection removal, and ripple processing.

[0089] It should be pointed out that optimizing the quality of real-time image recognition results is a key step in improving the performance of artificial intelligence image recognition models, especially in complex and changeable environments such as water conservancy projects, which can significantly improve the recognition accuracy and robustness of the model.

[0090] For example, in rainy or foggy scenes, the system first removes rain or fog from the received video stream, making the originally blurry image clear. If strong reflections or ripples on the water surface affect the identification of water gauge scales or floating objects, the system applies reflection and ripple removal algorithms to eliminate the interference, making the water gauge numbers or the outlines of floating objects clearly discernible, ultimately improving the accuracy of water gauge water level recognition or surface floating object detection.

[0091] Based on the above technical solution, this application realizes comprehensive, accurate and intelligent recognition of indoor and outdoor scenes of pumping stations by optimizing the quality of real-time image recognition results, significantly improving the intelligence level of equipment status monitoring, environmental safety warning and hydrological information acquisition, and providing important visual data support for the safe and efficient operation of pumping stations.

[0092] In one possible implementation, combining Figure 2 , Figure 3 As shown, the virtual-reality fusion engine can be specifically constructed through the following S51, S52 and S53, which are specifically described below: S51. Synchronize the real-time data of the pump station's operating parameters with the digital twin model to obtain state consistency between the physical entity and the digital model.

[0093] In some implementations, the virtual-reality fusion engine continuously receives multi-source heterogeneous data from the data acquisition device 10, including the operation of electromechanical equipment in the pump station, structural monitoring of water conservancy projects, environmental quantities, incoming water quality, and manual inspections. These real-time data will be transmitted immediately and synchronously updated to the corresponding parameters and components in the digital twin model. In order to ensure the efficiency and reliability of data synchronization, lightweight, high-throughput message queue protocols such as MQTT and Kafka can be used for data transmission, and timestamp alignment, data verification, and fault-tolerant processing mechanisms can be introduced to ensure a high degree of consistency in the dimensions, timing, and values ​​of the data between the physical entity and the digital model.

[0094] It should be pointed out that this real-time data synchronization is the basis for building a virtual-reality fusion engine. It makes the digital twin model no longer a static copy of the physical entity, but a living digital mirror that can dynamically and accurately reflect the instantaneous operating status of the pumping station.

[0095] For example, when a main pump at the Denglou Pumping Station is operating and its vibration sensor detects a fluctuation in real-time vibration from the normal range to a specific value (e.g., 3.5 mm / s), this vibration parameter is immediately transmitted via the communication network to the virtual-reality fusion engine. The engine's core module immediately receives this data and updates the corresponding vibration state parameters for the main pump in the digital twin model. Simultaneously, if the pump's real-time flow meter data indicates a flow rate of 33.5 m³ / s, this data is also synchronously updated to the flow parameters in the digital twin model, thereby presenting a real-time operating status consistent with the pump station in the digital space.

[0096] S52. Based on the state consistency between the physical entity and the digital model, construct the simulation driving logic, use the comprehensive analysis results of the equipment operation to drive the digital twin model, and present a high-fidelity dynamic simulation effect.

[0097] In some implementations, under the premise of ensuring the state consistency between the physical entity and the digital model, the virtual-reality fusion engine will build a set of precise simulation drive logic. This logic module receives the comprehensive analysis results of the equipment operation obtained by the multi-dimensional intelligent analysis model group in step S2, and uses these analysis results as the input to drive the digital twin model, triggering the corresponding simulation module in the digital twin model to perform working condition evolution and event simulation. When the pump station variable angle-speed integrated optimization scheduling model gives a new optimal operation strategy, the digital twin model will simulate the start and stop of the unit, blade angle adjustment and speed change, and display high-fidelity dynamic simulation effects such as water flow status and energy consumption changes in real time. In addition, for water quality forecasts or safety warning information, the simulation logic can drive the water color change, warning sign flashing or simulate the occurrence of safety events in the digital twin scene.

[0098] It should be pointed out that this simulation-driven logic makes the digital twin model no longer a simple static display, but a dynamic platform that can perform predictive simulation and event evolution simulation based on intelligent analysis results, greatly enhancing the system's predictability and decision-making support capabilities.

[0099] S53. Through high-fidelity dynamic simulation effects, a two-way mapping relationship of real-time data is generated. The digital twin model sends remote control instructions to the pump station and obtains the command response from the pump station.

[0100] In some implementations, the virtual-reality fusion engine further generates a bidirectional mapping relationship of real-time data by presenting a high-fidelity dynamic simulation effect. This means that the digital twin model not only receives data from the pump station, but can also issue remote control instructions to the pump station based on its internal intelligent analysis results and simulation deductions. In addition, when the engineering safety monitoring and early warning model or the artificial intelligence image recognition model detects that the water level and flow are approaching the warning value, or identifies an emergency situation such as human intrusion, open smoke and fire, the interface will also trigger the generation of early warning information and issue emergency intervention instructions to the pump station according to the preset emergency plan. The pump station's response to these instructions will again undergo real-time data synchronization through the S51 step to form a complete, adaptive closed-loop control chain.

[0101] It should be pointed out that this two-way interactive interface enables the digital twin system to actively intervene in the operation of the pump station, realizing intelligent management of the entire process from "perception-analysis-decision-execution-feedback", greatly improving the intelligence, visualization and risk proactive intervention capabilities of the pump station operation.

[0102] Based on the above technical solution, this application realizes seamless connection, real-time interaction and intelligent linkage between the physical world and the digital world by building a virtual-reality fusion engine, significantly improving the intelligence, visualization and proactive intervention capabilities of pump station management.

[0103] In one possible implementation, combining Figure 2 , Figure 4 As shown, the adaptive feedback mechanism can be established in the following ways, which are described in detail below: Multi-level deviation thresholds are set based on the deviation between the comprehensive analysis results of equipment operation and the actual operating parameters of the pump station.

[0104] Among them, the multi-level deviation threshold includes low-level deviation threshold, unit deviation threshold and target deviation threshold.

[0105] In some implementations, the system continuously obtains the real-time operating parameters of the pump station provided by the virtual-reality fusion engine, and the comprehensive analysis results of the equipment operation output by the multi-dimensional intelligent analysis model group, and calculates the deviation between the two; on this basis, the management personnel or the system will set multi-level deviation thresholds based on historical data, expert experience, and the safety and economic requirements of the pump station operation; when the absolute value of the deviation is less than the smaller deviation threshold, the original instruction operation is maintained; when the absolute value of the deviation is greater than the smaller deviation threshold and less than the unit deviation threshold, the unit operation status of the pump station is adjusted; when the absolute value of the deviation is greater than the unit deviation threshold and less than the target deviation threshold, the optimal energy consumption operation strategy of the pump station is adjusted; when the absolute value of the deviation is greater than the target deviation threshold, the emergency mechanism is activated, and early warning and timely intervention measures are taken.

[0106] For example, assume that the optimal energy consumption operation strategy of the pump station indicates that the ideal flow rate of a unit in the current period is 30m³ / s. If the system compares the actual flow rate monitored in real time: When the actual flow rate is 29.9 m³ / s and the smaller deviation threshold is set to 0.2 m³ / s, the system determines that the deviation is less than the smaller deviation threshold, maintains the original instruction, and continues to execute the next stage of the scheduling plan; When the actual flow rate is 29.6 m³ / s, the minimum deviation threshold is 0.2 m³ / s, and the unit deviation threshold is 0.5 m³ / s, the system determines that the deviation is slightly large and adjusts the unit operating status of the pump station, such as fine-tuning the blade placement angle of the unit to make its flow rate closer to 30 m³ / s; When the actual flow rate is 28.0 m³ / s, the unit deviation threshold is 0.5 m³ / s, and the target deviation threshold is 2.0 m³ / s, the system determines that the deviation is too large and adjusts the target value of the pump station's optimal energy consumption operation strategy. For example, it recalculates the optimal flow target under the current operating conditions or considers starting a standby unit to help achieve the new target. When the actual flow rate is only 25.0 m³ / s and the target deviation threshold is 2.0 m³ / s, the system determines that the deviation is too large, and there may be a serious fault or external interference. It immediately activates the emergency mechanism, such as issuing a high-level warning information to management personnel, simulating the possible risk evolution process in the digital twin model, and even preparing to shut down or switch to other operating plans.

[0107] In one possible implementation, combining Figure 2 As shown in the figure, the mimetic simulation effects of pump station operation, water flow dynamics, environmental changes and "four prediction" business data can be dynamically presented through S61, S62, S63, S64 and S65, which are explained in detail below: S61. Integrate terrain imagery, digital elevation, oblique photography, and laser point cloud data to construct a visualization model of the natural background of the project.

[0108] It should be pointed out that the construction of a natural background visualization model of the project provides a highly realistic and spatially accurate digital foundation for the dynamic simulation of pumping stations and water conservancy projects, and is the key to achieving an immersive digital twin experience.

[0109] S62. Use flowing particles to simulate the water flow field, and color the particles or fluid surface according to the water level and sediment content information to construct a dynamic visualization mimicry model of the upstream and downstream flow fields of the project.

[0110] It should be pointed out that this flow field dynamic visualization model converts the calculation results of abstract mathematical models into intuitive and interactive three-dimensional animations, which greatly enhances decision makers' ability to understand the laws of water flow movement and the details of the flow field under different water diversion conditions.

[0111] S63. Construct a visualization model of water conservancy projects based on geographic information systems and building information.

[0112] In some implementations, the model makes full use of existing water conservancy project data to generate high-precision digital twin scenarios.

[0113] It should be pointed out that the water conservancy project visualization model provides comprehensive and detailed visual model support for pump station scheduling and control simulation, engineering maintenance simulation, engineering simulation training, and pump station fault diagnosis and analysis.

[0114] S64. Carry out detailed modeling of components in the pump station and construct a visual model of hydraulic electromechanical equipment.

[0115] It should be pointed out that the construction of a visualization model for water conservancy electromechanical equipment provides intuitive and visual support for the full life cycle management of the equipment, significantly improving the efficiency and accuracy of equipment operation and maintenance.

[0116] For example, a manager can select a pump in the 3D visualization scene, and the system will immediately display detailed asset information for the pump, including its model, manufacturer, and last maintenance date, and even provide access to the corresponding design drawings. When the pump starts or stops, its digital model dynamically simulates the corresponding operating status within the scene. Based on the output of the electromechanical equipment health diagnostic model, the system can also use color coding or special effects to display its health level or potential fault points.

[0117] S65. Dynamically display the comprehensive analysis results of equipment operation in the form of data views, and perform simulated simulation of the previewed historical analysis data and calculation results.

[0118] It should be pointed out that this visual presentation of the "four prediction" business data transforms abstract data and complex analysis results into intuitive and vivid simulation scenarios, greatly improving the efficiency and accuracy of decision-making support and realizing the intelligent management of water conservancy project operations.

[0119] For example, when the water quality forecast model predicts that the COD concentration in a certain river section will reach a light pollution level within the next 24 hours, the visualization system will dynamically color the water in the corresponding river section in a specific color in the three-dimensional scene, and display the predicted concentration value floating above the river section. If a human intrusion warning occurs, in addition to displaying the alarm point on the map, the system can also simulate the intruder's movement trajectory in the three-dimensional scene and display an animation effect of the virtual warning line being triggered. For a historical flood control plan drill, the system can replay the simulation process of all scheduling operations at that time, such as water level changes, gate opening and closing, and unit operation, allowing managers to review the process intuitively.

[0120] Based on the above technical solution, this application provides an intuitive, realistic and interactive decision support interface by dynamically presenting the simulated effects of pump station operation, water flow dynamics, environmental changes and "four prediction" business data, which significantly improves the user's intuitive understanding of the overall picture of pump station operation and future trends and decision-making efficiency.

[0121] In one possible implementation, combining Figure 2 As shown, the water conservancy project visualization model can be constructed through S71, S72 and S73, which are described in detail below: S71. Generate digital twin scenarios using BIM models, CAD drawings, flight data, videos, and photos.

[0122] Among them, the digital twin scene is a high-precision three-dimensional mapping of water conservancy projects in digital space.

[0123] It should be pointed out that the comprehensive use of multiple data ensures the comprehensiveness, accuracy and realism of the digital twin scene, laying a solid foundation for subsequent physical rendering and simulation.

[0124] S72. Based on the digital twin scenario, perform lighting calculations on the physical entity properties and environmental properties of the water conservancy project, and build a physically based material shading model.

[0125] It should be pointed out that the physically based material shading model is one of the core technologies for improving the realism of digital twin scenes, which makes the virtual model visually closer to the real world.

[0126] S73. Integrate digital twin scenes with physically based material shading models to construct visualization models of water conservancy projects.

[0127] Among them, the water conservancy project visualization model is the digital twin water conservancy project entity that is finally presented to the user with high realism and interactivity.

[0128] It should be pointed out that the construction of a visualization model of a water conservancy project provides intuitive, comprehensive, and highly realistic visual model support for the dispatching and control simulation, equipment operation and maintenance, and fault diagnosis and analysis of pump stations.

[0129] Based on the above technical solution, this application constructs a visualization model of the water conservancy project, uses BIM models, CAD drawings, flight data, videos, and photo materials to generate a digital twin scene, and performs lighting calculations on the physical entity properties and environmental properties of the water conservancy project based on the scene, constructs a physics-based material shading model, and finally integrates the two to achieve a refined, realistic and integrated visualization presentation of the water conservancy project, providing strong visual support for the intelligent management and decision-making of the pump station.

[0130] The above mainly introduces the scheme of the embodiment of the present application from the perspective of device implementation. It can be understood that each device, for example, the digital twin intelligent pump station simulation engine device, includes at least one of the hardware structure and software modules corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should easily realize that, in combination with the units and steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0131] The embodiment of the present application can divide the digital twin intelligent pump station simulation engine device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0132] In the case of an integrated unit, Figure 5 A possible structural diagram of the digital twin intelligent pump station simulation engine device (denoted as simulation engine device 50 ) involved in the above embodiment is shown. The simulation engine device 50 includes a processing unit 501 and a communication unit 502 , and may also include a storage unit 503 . Figure 5 The structural schematic diagram shown can be used to illustrate the structure of the digital twin intelligent pump station simulation engine device involved in the above embodiments.

[0133] when Figure 5 The structural schematic diagram shown is used to illustrate the structure of the digital twin intelligent pump station simulation engine device involved in the above embodiment. The processing unit 501 is used to control and manage the actions of the simulation engine device, the communication unit 502 is used for the simulation engine device to communicate with other devices, and the storage unit 503 is used to store the program code and data of the simulation engine device.

[0134] For example, the communication unit 502 is used to integrate multi-source heterogeneous data such as the operation of electromechanical equipment in the pumping station, structural monitoring of water conservancy projects, environmental quantities, incoming water quality, and manual inspections; generate a real-time bidirectional mapping relationship between the pumping station and the digital twin model; and receive the actual operating parameters of the pumping station.

[0135] Processing unit 501 is used to obtain a digital representation of all elements of the pumping station; build a multi-dimensional intelligent analysis model group; obtain comprehensive analysis results of equipment operation; build a virtual-reality fusion engine; compare the actual operating parameters of the pumping station with the comprehensive analysis results of equipment operation in real time; establish an adaptive feedback mechanism; obtain dynamic correction of pumping station operation deviations and iterative optimization of the optimal energy consumption operation strategy; use the digital representation of all elements of the pumping station and the comprehensive analysis results to integrate geographic space, BIM / GIS and equipment component models, and through physical rendering and dynamic special effects, dynamically present the simulated simulation effects of pumping station operation, water flow dynamics, environmental changes and "four prediction" business data.

[0136] In one possible implementation, the processing unit 501 is further used to utilize the digital representation of all elements of the pumping station to establish a health evaluation index system integrating multi-element information and obtain a health diagnosis model for electromechanical equipment; to utilize dynamic programming or large-system test optimization theory to construct an optimization algorithm, and to integrate the dual adjustment mechanism of blade placement angle and water pump speed to obtain an integrated optimization scheduling model for the pumping station with variable angle and variable speed; to utilize the digital representation of all elements of the pumping station to utilize the intelligent identification of gross errors, mathematical statistics, and neural network analysis to obtain an engineering safety monitoring and early warning model; to utilize the law of conservation of mass and the law of horizontal diffusion to integrate the hydrodynamics and water quality modules and obtain an incoming water quality forecast model; to identify the indoor and outdoor scenes of the pumping station through offline training and online detection to obtain an artificial intelligence image recognition model.

[0137] In one possible implementation, the communication unit 502 is also used to collect the vibration, swing, temperature, current, pressure, and flow parameters of the pump when the electromechanical equipment of the pump station is running; collect engineering monitoring data on the horizontal and vertical displacement, seepage, structure, and environmental quantities of the sluice; collect incoming water quality monitoring data from national, provincial, county, and self-owned water quality monitoring stations; collect video image data obtained through IP cameras, FTP, or HTTP protocols, and perform gross error intelligent identification, data cleaning, and normalization processing on the video image data. The processing unit 501 is also used to generate an equipment operation status assessment and health level through an electromechanical equipment health diagnosis model, where the health levels include good, available, and maintenance-required; calculate the optimal number of pumping units, blade placement angle and speed, and total energy consumption of the pumping station through a pump station variable angle-speed integrated optimization scheduling model; analyze the safety status and warning information of water conservancy project buildings through an engineering safety monitoring and early warning model; predict the predicted index value and pollutant concentration change trend of the incoming water quality of a specific river section through an incoming water quality forecast model; identify real-time image recognition results of indoor and outdoor scenes of the pumping station through an artificial intelligence image recognition model; synchronize the real-time operating parameters of the pumping station with the digital twin model in real time; construct a simulation drive logic based on the state consistency of the physical entity and the digital model, and use the comprehensive analysis results of the equipment operation to drive the digital twin model to present a high-fidelity dynamic simulation effect; generate a two-way mapping relationship of real-time data through the high-fidelity dynamic simulation effect, and send remote control instructions to the pumping station by the digital twin model to obtain the instruction response of the pumping station; and When the absolute value of the deviation is greater than the unit deviation threshold and less than the target deviation threshold, the pump station's unit operating status is adjusted. When the absolute value of the deviation is greater than the unit deviation threshold and less than the target deviation threshold, the pump station's optimal energy consumption operation strategy is adjusted. When the absolute value of the deviation is greater than the unit deviation threshold, the pump station's optimal energy consumption operation strategy is adjusted. When the absolute value of the deviation is greater than the target deviation threshold, the emergency mechanism is activated, and early warning and timely intervention measures are taken. A natural background visualization model of the project is constructed by integrating terrain imagery, digital elevation, oblique photography, and laser point cloud data. The water flow field is simulated by flowing particles, and the particles or fluid surface are colored according to the water level and sediment content information to construct a dynamic visualization model of the upstream and downstream flow fields of the project. A visualization model of the water conservancy project is constructed based on geographic information systems and building information. Components in the pump station are refined and modeled to construct a visualization model of water conservancy electromechanical equipment. The comprehensive analysis results of equipment operation are dynamically displayed in the form of data views, and simulated historical analysis data and calculation results are simulated.

[0138] The processing unit 501 may be a processor or controller, and the communication unit 502 may be a communication interface, a transceiver, a transceiver, a transceiver circuit, a transceiver device, or the like. The term "communication interface" is a general term and may include one or more interfaces. The storage unit 503 may be a memory. When the simulation engine device 50 is a chip, the processing unit 501 may be a processor or controller, and the communication unit 502 may be an input interface and / or output interface, a pin, or a circuit, or the like. The storage unit 503 may be a storage unit within the chip, or a storage unit or random access memory located external to the chip.

[0139] Among them, the communication unit can also be called a transceiver unit. The antenna and control circuit with transceiver functions in the digital twin intelligent pumping station simulation engine device 50 can be regarded as the communication unit 502 of the digital twin intelligent pumping station simulation engine device 50, and the processor with processing function can be regarded as the processing unit 501 of the digital twin intelligent pumping station simulation engine device 50. Optionally, the device used to implement the receiving function in the communication unit 502 can be regarded as a receiving unit, and the receiving unit is used to perform the receiving steps in the embodiment of the present application. The receiving unit can be a receiver, a receiver, a receiving circuit, etc. The device used to implement the sending function in the communication unit 502 can be regarded as a sending unit, and the sending unit is used to perform the sending steps in the embodiment of the present application. The sending unit can be a transmitter, a transmitter, a sending circuit, etc.

[0140] Figure 5 If the integrated units are implemented in the form of software function modules 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 the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device or processor to execute all or part of the steps of the various embodiments of the present application. The storage medium for storing computer software products includes various media that can store program codes, such as USB flash drives, mobile hard drives, read-only memories, random access memories, magnetic disks or optical disks.

[0141] Figure 5 A unit in a can also be called a module, for example, a processing unit can be called a processing module.

[0142] The embodiment of the present application also provides a hardware structure diagram of a digital twin intelligent pump station simulation engine device (denoted as simulation engine device 60), see Figure 6 The simulation engine device 60 includes a processor 601 and, optionally, a memory 602 connected to the processor 601 .

[0143] In the first possible implementation, see Figure 6 The simulation engine device 60 further includes a transceiver 603. The processor 601, the memory 602, and the transceiver 603 are connected via a bus. The transceiver 603 is used to communicate with other devices or a communication network. Optionally, the transceiver 603 may include a transmitter and a receiver. The device used to implement the receiving function in the transceiver 603 may be considered a receiver, and the receiver is used to perform the receiving step in the embodiment of the present application. The device used to implement the transmitting function in the transceiver 603 may be considered a transmitter, and the transmitter is used to perform the transmitting step in the embodiment of the present application.

[0144] Based on the first possible implementation, Figure 6 The structural schematic diagram shown can be used to illustrate the structure of the digital twin intelligent pump station simulation engine device involved in the above embodiments.

[0145] in, Figure 6 The system chip in the digital twin intelligent pump station simulation engine device can also be illustrated. In this case, the actions performed by the digital twin intelligent pump station simulation engine device can be implemented by the system chip. The specific actions performed can be found above and will not be repeated here.

[0146] During implementation, each step of the method provided in this embodiment can be completed by hardware integrated logic circuits in a processor or by software instructions. The steps of the method disclosed in the embodiments of this application can be directly implemented as execution by a hardware processor, or as a combination of hardware and software modules in a processor.

[0147] The processor in this application may include but is not limited to at least one of the following: a central processing unit, a microprocessor, a digital signal processor, a microcontroller, or an artificial intelligence processor, etc., various types of computing devices that run software, each of which may include one or more cores for executing software instructions to perform operations or processing. The processor may be a separate semiconductor chip, or it may be integrated into a semiconductor chip together with other circuits, for example, it may form an SoC with other circuits, or it may be integrated into an ASIC as a built-in processor of an ASIC. The ASIC with an integrated processor may be packaged separately or together with other circuits. In addition to including a core for executing software instructions to perform operations or processing, the processor may further include necessary hardware accelerators, such as a field programmable gate array, PLD, or logic circuits that implement dedicated logic operations.

[0148] The memory in the embodiments of the present application may include at least one of the following types: a read-only memory or other type of static storage device capable of storing static information and instructions, a random access memory or other type of dynamic storage device capable of storing information and instructions, or an electrically erasable programmable read-only memory. In some scenarios, the memory may also be a read-only optical disc or other optical disc storage, optical disc storage, magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0149] An embodiment of the present application also provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enables the computer to execute any of the above methods.

[0150] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above methods.

[0151] An embodiment of the present application also provides a chip, which includes a processor and an interface circuit, the interface circuit is coupled to the processor, the processor is used to run a computer program or instruction to implement the above method, and the interface circuit is used to communicate with other modules outside the chip.

[0152] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using a software program, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present 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 computer-readable storage medium. 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 means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more servers that can be integrated with the medium. The available medium can be a magnetic medium, an optical medium or a semiconductor medium, etc.

[0153] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0154] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

Claims

1. A digital twin intelligent pump station simulation engine design method, characterized in that: include: After collecting multi-source heterogeneous data of the pumping station, pre-processing is performed to obtain a digital representation of all elements of the pumping station; Constructing a multi-dimensional intelligent analysis model group, and running the multi-dimensional intelligent analysis model group based on the digital representation of all elements of the pump station to obtain comprehensive analysis results of equipment operation; Build a virtual-reality fusion engine based on the comprehensive analysis results of the equipment operation to generate a bidirectional mapping relationship between the pump station and the digital twin model; Through the bidirectional mapping relationship, the actual operating parameters of the pumping station are compared with the comprehensive analysis results of the equipment operation in real time; an adaptive feedback mechanism is established to obtain dynamic correction of pumping station operation deviations and optimal energy consumption operation strategies; Based on the digital representation of all elements of the pumping station and the comprehensive analysis results of equipment operation, a mimetic simulation is constructed by integrating BIM / GIS.

2. A digital twin intelligent pump station simulation engine design method according to claim 1, characterized in that: The multi-source heterogeneous data of the pump station includes: operating status of electromechanical equipment, hydraulic engineering structure monitoring data, environmental quantities and incoming water quality; The operating status of the electromechanical equipment is the vibration amplitude, swing, temperature, current, pressure and flow parameters of the pump when the electromechanical equipment of the pump station is running; The hydraulic engineering structure monitoring data is the engineering monitoring data of the horizontal and vertical displacement, seepage and structure of the sluice; The incoming water quality is the water quality monitoring data of the water quality monitoring station; The environmental quantities include water level, rainfall and air temperature.

3. A digital twin intelligent pump station simulation engine design method according to claim 1, characterized in that: The construction of a multi-dimensional intelligent analysis model group includes: Based on the digital representation of all elements of the pump station, a health diagnosis model for electromechanical equipment based on multi-information fusion is established; Adopting dynamic programming or large-scale system test optimization theory and integrating the dual adjustment mechanism of blade placement angle and pump speed, a pump station variable angle and variable speed integrated optimization scheduling model is constructed; Based on the digital representation of all elements of the pump station, an engineering safety monitoring and early warning model is obtained by using intelligent identification of gross errors, mathematical statistics and neural network analysis; Using the law of conservation of mass and advection diffusion, the hydrodynamic and water quality modules are integrated to obtain the incoming water quality forecast model; For indoor and outdoor scenes of the pump station, scene recognition and offline training are performed through online detection to build an artificial intelligence image recognition model.

4. A digital twin intelligent pump station simulation engine design method according to claim 3, characterized in that: The method for obtaining the comprehensive analysis result of the equipment operation includes: Generate an equipment operation status assessment and health status through the electromechanical equipment health diagnosis model, wherein the health status includes good, available, and maintenance required; The optimal number of pumping units, blade placement angle and speed, and total energy consumption of the pumping station are calculated through the pumping station variable angle-speed integrated optimization scheduling model; Through the engineering safety monitoring and early warning model, the safety status and early warning information of the water conservancy project buildings are analyzed; The water quality prediction model is used to predict the water quality index values ​​and pollutant concentration change trends of the water in a specific river section; The artificial intelligence image recognition model is used to obtain real-time image recognition results of indoor and outdoor scenes of the pump station.

5. A digital twin intelligent pump station simulation engine design method according to claim 4, characterized in that: The real-time image recognition result includes: Identify the equipment operating status, visible smoke and flames in the pump station scene; Identify floating objects on the water surface, water gauges, vehicle and personnel intrusions, and gate opening and closing status in outdoor scenes of pump stations.

6. A digital twin intelligent pump station simulation engine design method according to claim 1, characterized in that: The method for obtaining the bidirectional mapping relationship includes: Synchronize the real-time data of the pump station’s operating parameters with the digital twin model to achieve consistency between the physical entity and the digital model; Based on the state consistency between the physical entity and the digital model, a simulation driving logic is constructed; based on the comprehensive analysis results of the equipment operation, the digital twin model is driven to obtain simulation data; and a bidirectional mapping relationship is established based on real-time data and simulation data.

7. A digital twin intelligent pump station simulation engine design method according to claim 1, characterized in that: The establishing of the adaptive feedback mechanism includes: According to the actual deviation between the comprehensive analysis result of the equipment operation and the actual operating parameters of the pump station, a multi-level deviation threshold is set; wherein the multi-level deviation threshold includes a low-level deviation threshold, a unit deviation threshold and a target deviation threshold; generating a maintenance signal when the absolute value of the actual deviation is less than the low-level deviation threshold; When the absolute value of the actual deviation is greater than the low-level deviation threshold and less than the unit deviation threshold, adjusting the unit operation state of the pump station; When the absolute value of the actual deviation is greater than the unit deviation threshold and less than the target deviation threshold, adjusting the optimal energy consumption operation strategy of the pump station; When the absolute value of the deviation is greater than the target deviation threshold, an early warning signal is generated.

8. A digital twin intelligent pump station simulation engine design method according to claim 1, characterized in that: The method of constructing mimicry simulation includes: Integrate terrain images, digital elevation, oblique photography, and laser point cloud data in BIM / GIS to build a visualization model of the natural background of the project; The water flow field is simulated by flowing particles, and the particles or fluid surface are colored according to the water level and sediment content information to construct a dynamic visual mimicry model of the upstream and downstream flow fields of the project; Build a visualization model of the water conservancy project based on the geographic information and building information of the pumping station; Carry out detailed modeling of components in the pump station and construct a visual model of hydraulic electromechanical equipment; The comprehensive analysis results of the equipment operation are input into the engineering natural background visualization model, the dynamic visualization mimicry model, the water conservancy project visualization model and the water conservancy electromechanical equipment visualization model to obtain mimicry simulation.

9. A digital twin intelligent pump station simulation engine design method according to claim 8, characterized in that: The construction of the water conservancy project visualization model includes: Generate digital twin scenarios based on the pump station's architectural information; Based on the digital twin scenario, perform lighting calculations on the physical entity properties and environmental properties of the pumping station and construct a material shading model; The digital twin scene is integrated with the physically based material shading model to construct a visualization model of the water conservancy project.

10. A digital twin intelligent pump station simulation engine device, characterized in that: include: a communication unit and a processing unit; The communication unit is used to collect multi-source heterogeneous data on the operation of electromechanical equipment in the pumping station, structural monitoring of water conservancy projects, environmental quantities, incoming water quality, and manual inspections, and to generate a real-time bidirectional mapping relationship between the pumping station and the digital twin model, as well as to receive the actual operating parameters of the pumping station; The processing unit is used to obtain a digital representation of all elements of the pumping station, build a multi-dimensional intelligent analysis model group, obtain comprehensive analysis results of equipment operation, build a virtual-reality fusion engine, compare the actual operating parameters of the pumping station with the comprehensive analysis results of the equipment operation in real time, establish an adaptive feedback mechanism, obtain dynamic correction of pumping station operation deviations and iterative optimization of the optimal energy consumption operation strategy, and utilize the digital representation of all elements of the pumping station and the comprehensive analysis results to integrate geographic space and BIM / GIS to construct a mimetic simulation.

Images