Water conservancy gate multi-parameter cooperative intelligent monitoring system

Abstract

The invention specifically relates to the technical field of big data analysis, and discloses a water conservancy gate multi-parameter cooperative intelligent monitoring system, which comprises a multi-parameter acquisition module, a multi-parameter processing module, a comprehensive analysis module, an intelligent decision module, an operation and maintenance early warning module and a man-machine interaction module, the multi-parameter processing module is used for calculating flood control and discharge indexes, structure safety indexes and equipment health indexes; the comprehensive analysis module is used for judging gate risk levels; the intelligent decision-making module is used for generating an optimal gate scheduling scheme; the operation and maintenance early warning module is used for constructing a multi-level early warning mechanism; according to the method, parameter coverage is comprehensive, a gate digital twinborn model and a gate opening comprehensive evaluation model are constructed, the gate risk level is evaluated, an optimization strategy is dynamically adjusted through an intelligent decision module, the accuracy of gate risk judgment is improved, and the self-adaptive capacity of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and more specifically, to a multi-parameter collaborative intelligent monitoring system for water conservancy gates. Background Art

[0002] With the intensification of global climate change and the acceleration of urbanization, the management of traditional water conservancy facilities faces multiple challenges, including outdated monitoring methods, aging facilities, and decentralized management. The traditional passive response model cannot meet the needs of flood control and water supply. The maturity of the Internet of Things, big data, and artificial intelligence technologies has provided strong technical support for the multi-parameter coordinated intelligent monitoring of water conservancy gates. Digital twin technology achieves "virtual-real" mapping by constructing a three-dimensional model of the sluice gate, assisting in intelligent decision-making and promoting the transformation of water conservancy management from experience-driven to data-driven. The existing intelligent monitoring system for water conservancy gates specifically includes a data acquisition module, a data preprocessing module, an intelligent analysis module, an early warning module, and a remote control module. It enables real-time perception of the gate's operating status and accurate risk warning, effectively improving the efficiency and safety of water conservancy management.

[0003] However, in actual use, it still has some shortcomings. First, the data collection dimension is single. The existing intelligent monitoring system for water conservancy gates only covers the basic parameters of water level, flow and gate opening, lacks in-depth mining of structural and environmental parameters. The deployment of sensors is limited to single-point monitoring, and no global perception network has been formed, making it impossible to fully perceive the gate operation status.

[0004] Second, the depth of intelligent analysis is insufficient. The existing intelligent monitoring system for water conservancy gates has difficulty in implementing multi-parameter fusion analysis and fault tracing. It is unable to combine multi-parameter data to specifically analyze the cause of the fault. Moreover, lacking the support of digital twin technology, it is unable to resolve the invisible correlation between parameters, resulting in delayed or erroneous warnings.

[0005] Third, there is a lack of dynamic regulation capabilities. The data collection, analysis, and control modules of the existing water conservancy gate intelligent monitoring system operate independently, and there is an island effect in data intercommunication, making it impossible to dynamically adjust strategies based on real-time monitored parameters. Summary of the Invention

[0006] In view of this, an embodiment of the present invention provides a multi-parameter collaborative intelligent monitoring system for water conservancy gates, which achieves comprehensive parameter coverage through multi-dimensional sensing terminals, constructs flood control and discharge assessment models, structural safety assessment models and equipment health assessment models through multi-parameter processing modules, constructs gate digital twin models and gate opening comprehensive assessment models through comprehensive analysis modules, evaluates gate risk levels, and dynamically adjusts optimization strategies through intelligent decision-making modules, effectively solving the problems of single data collection dimensions, insufficient intelligent analysis depth and lack of dynamic regulation capabilities raised in the background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solutions: a multi-parameter collaborative intelligent monitoring system for water conservancy gates, comprising a multi-dimensional sensing terminal, an edge computing gateway, and a cloud server database, as well as a multi-parameter acquisition module, a multi-parameter processing module, a comprehensive analysis module, an intelligent decision-making module, an operation and maintenance warning module, and a human-computer interaction module:

[0008] The multi-parameter acquisition module is used to receive multi-dimensional data of water conservancy gates transmitted by the edge computing gateway, including water conservancy environment parameters, gate structure parameters and equipment status parameters, construct a multi-dimensional data set of water conservancy gates, and transmit it to the comprehensive analysis module;

[0009] The multi-parameter processing module is used to construct a flood control and discharge assessment model, a structural safety assessment model, and an equipment health assessment model. Based on the multi-dimensional data set of the hydraulic gate, the flood control and discharge index, the structural safety index, and the equipment health index are calculated and transmitted to the comprehensive analysis module.

[0010] The comprehensive analysis module is used to construct a gate digital twin model and a gate opening comprehensive evaluation model, calculate the gate opening comprehensive evaluation index, determine the gate risk level, and pass it to the intelligent decision-making module;

[0011] The intelligent decision-making module is used to make intelligent decisions based on the gate opening comprehensive evaluation index and the gate risk level results, obtain emergency response plans, generate optimal gate scheduling plans, generate intelligent scheduling instructions, and pass them to the operation and maintenance warning module;

[0012] The operation and maintenance warning module is used to build a multi-level warning mechanism, trigger the corresponding warning mechanism according to the gate risk level, perform fault diagnosis, control the gate to perform corresponding operations according to the intelligent scheduling instructions generated by the intelligent decision-making module, and transmit warning information to the human-computer interaction module;

[0013] The human-computer interaction module is used to receive early warning information, execute the early warning interaction process, and provide a visual interactive interface to display the gate digital twin model, multi-dimensional data of the water conservancy gate, gate opening and closing status and data trends in real time, providing human-computer interaction functions.

[0014] Technical effects and advantages of the present invention:

[0015] 1. The present invention achieves comprehensive parameter coverage through multi-dimensional sensing terminals, collects water conservancy environment parameters, gate structure parameters, and equipment status parameters in real time, forms a trinity data system of water conservancy environment, gate structure, and equipment health, and synchronizes and structures multi-source data, providing a complete and accurate data foundation for subsequent analysis;

[0016] 2. The present invention uses a multi-parameter processing module to construct a flood control and discharge assessment model, a structural safety assessment model, and an equipment health assessment model. Through a weighted algorithm and normalization processing, the multi-dimensional parameters are converted into quantitative indices. The comprehensive analysis module constructs a gate digital twin model and a gate opening comprehensive assessment model. The physical entity status is synchronized in real time, and the gate risk level is comprehensively assessed, thereby improving the accuracy of gate risk judgment.

[0017] 3. The present invention realizes dynamic response of the entire process from monitoring to control through data collaboration and intelligent decision-making. The intelligent decision-making module is based on the comprehensive evaluation index of gate opening and risk level, combined with the reinforcement learning algorithm, to dynamically optimize the scheduling strategy. The human-computer interaction module supports operators to view data in real time, allows manual intervention in intelligent decision-making, and improves the system's adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0019] Figure 2 Schematic diagram of the method steps of the present invention.

[0020] Figure 3 Schematic diagram of the steps of the gate risk level judgment method of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] As attached Figure 1 The multi-parameter collaborative intelligent monitoring system for water conservancy gates shown in the figure includes a multi-dimensional sensing terminal, an edge computing gateway and a cloud server database, as well as a multi-parameter acquisition module, a multi-parameter processing module, a comprehensive analysis module, an intelligent decision-making module, an operation and maintenance warning module and a human-computer interaction module.

[0023] In a more specific application of the present invention, the multi-dimensional sensing terminal is used to obtain multi-dimensional data of water conservancy gates in real time, including environmental parameters, structural parameters and equipment status. The multi-dimensional sensing terminal specifically includes a radar water level meter, an ultrasonic flow meter, a fiber grating strain sensor, a resistance strain gauge, a MEMS accelerometer, a laser displacement sensor, a water quality sensor, a temperature sensor and a current transformer. The multi-dimensional sensing terminal is connected to the edge computing gateway via industrial Ethernet to upload the collected multi-dimensional data of water conservancy gates in real time.

[0024] The edge computing gateway is used to perform real-time noise filtering, missing value completion, and data format standardization on the multi-dimensional data of water conservancy gates uploaded by multi-dimensional sensing terminals. It also stores historical data locally, is compatible with heterogeneous communication protocols of sensors, and presets local thresholds to trigger local decisions. The edge computing gateway connects to the multi-parameter acquisition module via the MQTT protocol and to the cloud server database via the 5G network.

[0025] The cloud server database is responsible for storing and managing all monitoring data, supporting remote access, big data analysis, and cloud collaboration. It is used for multi-source data storage management, data interaction and collaboration, cloud computing and analysis support, as well as data security and disaster recovery.

[0026] The specific implementation of the present invention includes the following contents:

[0027] Multi-parameter acquisition module: Receives multi-dimensional water conservancy gate data from the edge computing gateway, including water conservancy environment parameters, gate structure parameters, and equipment status parameters, constructs a multi-dimensional water conservancy gate data set, and passes it to the comprehensive analysis module;

[0028] Furthermore, water level environmental parameters specifically include water level height, flow, flood frequency, and upstream and downstream water level difference; gate structure parameters specifically include gate strain value, displacement, and material stress; and equipment status parameters specifically include equipment temperature, equipment current, degree of wear, and operating time.

[0029] In this embodiment, it should be specifically explained that the water level height in the water level environmental parameters is measured in real time by the radar water level meter in the multi-dimensional sensing terminal, and the flow rate is measured by the ultrasonic flow meter; the gate strain value is measured by the fiber Bragg grating strain sensor, the displacement is measured by the laser displacement sensor, the vibration frequency is measured by the MEMS accelerometer, the equipment temperature is measured by the temperature sensor, and the equipment current is measured by the current transformer.

[0030] Furthermore, the construction of a multi-dimensional data set of water conservancy gates requires a multi-dimensional sensing terminal to collect multi-dimensional data of water conservancy gates in real time and upload it to the edge computing gateway. The edge computing gateway preprocesses the received multi-dimensional data of water conservancy gates and passes it to the multi-parameter acquisition module. The multi-parameter acquisition module performs parameter structured classification and metadata annotation on the pre-processed multi-dimensional data of water conservancy gates to construct a three-dimensional multi-dimensional data set of water conservancy gates including time dimension, space dimension and parameter type dimension.

[0031] In this embodiment, it should be specifically explained that parameter classification storage establishes a data cache area according to three categories: environment, structure, and device status. Metadata annotation refers to adding metadata such as sensor location, acquisition frequency, and confidence level to each data point. Integrity verification is required to construct a multi-dimensional data set to check whether the data point contains all required fields, mark abnormal data as "pending confirmation", and trigger the edge computing gateway to retransmit.

[0032] Multi-parameter processing module: Builds flood control and discharge assessment models, structural safety assessment models, and equipment health assessment models. Based on the multi-dimensional data set of hydraulic gates, it calculates the flood control and discharge index, structural safety index, and equipment health index, and transmits them to the comprehensive analysis module.

[0033] Furthermore, the calculation of the flood control and discharge index requires obtaining the water level h, flow Q, flood frequency F, and upstream and downstream water level difference Δh from the multi-dimensional data set of the hydraulic gate collected in real time, importing them into the flood control and discharge evaluation model, and using the formula:

[0034]

[0035] Calculate the flood control and discharge index I F , where h n Indicates normal water level, h w Indicates the warning water level, Q max represents the designed maximum flood discharge, α F represents the flood frequency correction factor, Δh s represents the safe water level difference threshold, a1, a2, and a3 represent the weight coefficients of water level height, flow rate, and upstream and downstream water level difference, respectively, and the sum of a1, a2, and a3 is 1;

[0036] In this embodiment, it should be specifically explained that the flood control and discharge index is used to quantify the current flood risk and flood discharge demand. The real-time water level refers to the water level value actually monitored at present, reflecting the real-time flood situation. The normal water level refers to the safe water level baseline of the river or reservoir. It is necessary to be vigilant when it approaches the warning water level. After exceeding the warning water level, the flood risk increases significantly, triggering flood discharge preparation. The actual flow refers to the amount of water passing through the gate per unit time, reflecting the intensity of the flood. The larger the flood frequency correction coefficient, the rarer the flood, the greater the difference in upstream and downstream water levels, and the stronger the flood discharge capacity. The safe water level difference threshold refers to the safe potential energy difference allowed by the project. The weight coefficient reflects the degree of influence of the parameters on the flood discharge demand, which requires engineering optimization. The risks in the three dimensions of water level, flow and water level difference are integrated in multiple dimensions, so that the flood discharge decision is transformed from empirical judgment to data quantification drive.

[0037] The calculation of the structural safety index requires obtaining the gate strain value ε, displacement S, and material stress σ from the multi-dimensional data set of the hydraulic gate collected in real time, importing them into the structural safety assessment model, and using the formula:

[0038]

[0039] Calculate the structural safety index I S , where ε0 represents the initial strain value of the gate, ε l Indicates the ultimate strain value of the gate, S max Indicates the maximum allowable displacement of the gate, σ a represents the allowable stress of the material, b1, b2 and b3 represent the weight coefficients of gate strain value, displacement and material stress respectively, and the sum of b1, b2 and b3 is 1;

[0040] In this embodiment, it should be specifically explained that the structural safety index is used to quantify the health of the gate structure. The higher the value, the safer the gate. The real-time strain value indicates the current deformation degree of the gate. The larger the strain, the closer the structure is to the deformation limit. The initial strain value indicates the strain baseline of the gate under normal conditions. The ultimate strain value indicates the critical strain at which the gate material is about to fail. Exceeding this value indicates that the gate structure is about to be destroyed. The real-time displacement indicates the actual displacement of the gate, reflecting whether the gate structure is deformed too much. The maximum allowable displacement is the safe displacement threshold of the engineering design. Exceeding this value indicates that the gate structure is unstable. The real-time material stress is the actual stress of the key parts of the gate, reflecting the degree of stress on the material. The allowable material stress refers to the upper limit of the engineering safety stress, which is determined based on the material strength and safety factor. The displacement correction coefficient is used to adjust the weight of the impact of the displacement on safety. The displacement may be affected by temperature, installation error, etc., and the weight coefficient requires engineering optimization.

[0041] The calculation of the equipment health index requires obtaining the equipment temperature T, equipment current I, and wear degree W from the multi-dimensional data set of the water conservancy gate collected in real time, importing them into the equipment health assessment model, and using the formula:

[0042]

[0043] Calculate the equipment health index I E , where T n Indicates the standard temperature of the equipment, T c represents the critical temperature of the equipment, σ I Indicates the standard deviation of the device current, μ I Indicates the average current of the device, W max Indicates the maximum wear degree of the device, where c1, c2, and c3 represent the weight coefficients of device temperature, device current, and wear degree, respectively, and the sum of c1, c2, and c3 is 1.

[0044] In this embodiment, it should be specifically explained that the equipment health index is used to quantify the health of the gate. The larger the value, the safer the gate. The real-time equipment temperature indicates the current temperature of key components such as the motor and the gate opening and closing machine, reflecting the degree of heat generation of the equipment. The equipment standard temperature indicates the reference temperature when the equipment is operating normally. The equipment critical temperature is the temperature threshold at which the equipment is about to fail. The real-time equipment current refers to the current current of the motor and the drive mechanism, reflecting the equipment load. The equipment current standard deviation indicates the statistic of current fluctuations, reflecting the current stability. If the fluctuation is large, the equipment operating condition is abnormal. The equipment current mean indicates the average current over a period of time, reflecting the typical load of the equipment. The maximum wear degree of the equipment indicates the upper limit of safe wear allowed for the equipment. If this value is exceeded, the component needs to be replaced, and the weight coefficient requires engineering optimization.

[0045] Comprehensive analysis module: Build a gate digital twin model and a gate opening comprehensive evaluation model, calculate the gate opening comprehensive evaluation index, determine the gate risk level, and pass it to the intelligent decision-making module;

[0046] Furthermore, the construction of the gate digital twin model requires the use of three-dimensional modeling tools to build a high-precision model of the gate, river channel and surrounding terrain, integrating multi-dimensional data in the multi-dimensional data set of the water conservancy gate, driving the dynamic simulation of the gate digital twin model, and reproducing the operating status of the gate at any time based on the historical data stored in the cloud service database, and performing predictive deductions.

[0047] In this embodiment, it should be specifically explained that the three-dimensional modeling tool specifically refers to BIM+GIS technology, and the real-time data stream is called through Python, and the finite element analysis algorithm is used to simulate the structural stress, wherein the prediction and deduction specifically refers to the simulation of the structural stress and equipment load changes under different gate openings, flow rates and water level scenarios.

[0048] Furthermore, the calculation of the gate opening comprehensive evaluation index requires importing the flood control and discharge index, structural safety index and equipment health index transmitted by the multi-parameter processing module into the gate opening comprehensive evaluation model, using the formula The flood control and discharge index, structural safety index and equipment health index are normalized and the normalized flood control and discharge index, structural safety index and equipment health index are calculated using the formula I = ω1I Fnorm +ω2I Snorm +ω3I Enorm The comprehensive evaluation index I of the gate opening is calculated, where ω1, ω2, and ω3 represent the weight coefficients of the flood control and discharge index, the structural safety index, and the equipment health index, respectively, and the total is 1.

[0049] In this embodiment, it should be specifically explained that the flood control and discharge index, structural safety index, and equipment health index are normalized so that their values ​​fall within the range of 0 to 1.min Indicates the minimum value of the parameter, X max It represents the maximum value of the parameter. The staff determines the weight coefficients of the flood control and discharge index, structural safety index and equipment health index based on relevant historical data and experience. The weight coefficients can be dynamically adjusted according to environmental changes. When the comprehensive evaluation index of gate opening is closer to 1, it means that under the current gate opening, the flood control, structure and equipment are in a safe state. In order to maintain or fine-tune the opening, when the comprehensive evaluation index of gate opening is closer to 0, it means that the current opening is at high risk and the opening needs to be adjusted urgently.

[0050] Furthermore, the judgment of the gate risk level requires risk level classification, which is divided into four levels, from low to high risk, namely the first risk level, the second risk level, the third risk level and the fourth risk level. The gate risk level is judged according to the size of the comprehensive evaluation index of the gate opening.

[0051] In this embodiment, it should be specifically explained that when the comprehensive evaluation index of the gate opening is greater than 0.8, the gate risk is at the first risk level, indicating that the gate is in a safe state, and the current opening is maintained or the gate opening is fine-tuned as needed; when the comprehensive evaluation index of the gate opening is less than 0.8 and greater than 0.6, the gate risk is at the second risk level, indicating that the gate is in an alert state, and the gate opening needs to be slightly adjusted, and real-time monitoring is carried out; when the comprehensive evaluation index of the gate opening is less than 0.6 and greater than 0.3, the gate risk is at the third risk level, indicating that the gate is in a dangerous state, and the gate opening needs to be forcibly adjusted to a safe range, and an early warning is triggered; when the comprehensive evaluation index of the gate opening is less than 0.3, the gate risk is at the fourth risk level, indicating that the gate is in an extremely dangerous state, and the gate needs to be fully opened or closed immediately, and the emergency plan is activated.

[0052] Intelligent decision-making module: Make intelligent decisions based on the gate opening comprehensive evaluation index and gate risk level results, obtain emergency response plans, generate optimal gate scheduling plans, generate intelligent scheduling instructions, and pass them to the operation and maintenance early warning module;

[0053] Furthermore, the formulation of intelligent decisions requires clarifying the current core risk type based on the comprehensive evaluation index of the gate opening and the corresponding gate risk level, obtaining the emergency response plan library preset in the cloud server database, and matching the emergency response plan with the gate risk level one by one. According to the plan execution logic, based on the plan library, multiple groups of candidate scheduling instructions are generated, and simulation verification is carried out through the gate digital twin model to generate the optimal gate scheduling plan and generate standardized scheduling instructions.

[0054] In this embodiment, it should be specifically explained that the current core risk type can be clarified based on the comprehensive evaluation index of the gate opening and the corresponding gate risk level. Specifically, a "risk level-plan trigger" mapping rule can be established based on a rule engine, according to engineering specifications and expert experience; the plan execution logic specifically includes plan matching, dynamic optimization and conflict detection, among which plan matching refers to automatically matching the corresponding plan according to the risk level, dynamic optimization refers to calling the digital twin model to simulate the risk changes after the plan is executed, and conflict detection refers to checking the conflicts between multiple plans; standardized scheduling instructions specifically include scheduling type, specific parameters and priority.

[0055] Operation and maintenance warning module: Build a multi-level warning mechanism, trigger the corresponding warning mechanism according to the gate risk level, perform fault diagnosis, control the gate to perform corresponding operations according to the intelligent scheduling instructions generated by the intelligent decision-making module, and transmit warning information to the human-computer interaction module;

[0056] Furthermore, the construction of a multi-level early warning mechanism requires the construction of a four-level early warning mechanism based on the gate risk level obtained by the comprehensive analysis module, and the triggering of early warning operations based on the gate risk level obtained by real-time judgment. Fault diagnosis specifically refers to the use of a preset machine learning model to train the mapping relationship between "parameter anomaly-fault type" based on the data collected in real time by the multi-parameter module and the historical fault cases in the cloud server database, to determine the fault type, fault location and fault level, accept and parse the scheduling instructions transmitted by the intelligent decision-making module, and control the gate through the intelligent actuator to complete the specified operation.

[0057] In this embodiment, it should be specifically explained that the four-level warning mechanism specifically means that when it is in the first risk level, no warning is required, inspections are maintained and operating data are recorded; when it is in the second risk level, a yellow warning is issued, and warning information is pushed to the human-computer interaction module, suggesting manual attention; when it is in the third risk level, an orange warning is issued, automatic scheduling is triggered, and equipment inspections are started; when it is in the fourth risk level, the human-computer interaction module is notified to execute the emergency plan and link the emergency system; the push of warning information includes the warning level, fault location and disposal suggestions, and the scheduling instruction execution progress is pushed to the human-computer interaction module in real time.

[0058] Human-computer interaction module: Receives early warning information, executes early warning interaction processes, and provides a visual interactive interface to display the gate digital twin model, multi-dimensional data of the water conservancy gate, gate opening and closing status, and data trends in real time, providing human-computer interaction functions.

[0059] Furthermore, the execution of the early warning interaction process refers to the human-computer interaction terminal confirming the warning information transmitted by the operation and maintenance early warning module, handling the dispatch and manual intervention. The visual interactive interface specifically includes three-dimensional model display, real-time data monitoring and equipment status monitoring, operation records, support historical data query, and provide staff with manual operation permissions and intelligent decision-making intervention functions.

[0060] In this embodiment, it should be specifically explained that information confirmation specifically refers to the operator clicking the confirmation button, the system records the confirmation time and the operator, unconfirmed warnings will continue to pop up prompts, disposal dispatch specifically refers to the warning-related maintenance work order, manual intervention means that in an emergency, the operator can forcibly interrupt automatic scheduling and switch to manual control, and the intervention record is synchronized to the intelligent decision-making module for model optimization; three-dimensional model display specifically refers to the 1:1 restoration of the three-dimensional model of the gate, river channel, and surrounding facilities, real-time synchronization of the physical gate status, and highlighting of abnormal parts. Real-time data monitoring refers to the dashboard displaying core parameters and trend curves. Equipment status monitoring refers to the real-time display of equipment topology diagrams; manual operation permissions include gate opening control and equipment start and stop. Intelligent intervention decision-making refers to scheduling intervention and feedback loop. According to the operator's score on the scheduling effect, the parameters of the flood control and discharge assessment model, structural safety assessment model, equipment health assessment model and gate opening comprehensive assessment model are dynamically optimized.

[0061] like Figure 2 As shown, the present invention provides a multi-parameter collaborative intelligent monitoring method for water conservancy gates, which specifically includes the following steps:

[0062] S1: Receive multi-dimensional water conservancy gate data transmitted by the edge computing gateway through the multi-parameter acquisition module, including water conservancy environment parameters, gate structure parameters, and equipment status parameters, and construct a multi-dimensional water conservancy gate data set;

[0063] S2: Based on the flood control and discharge assessment model, structural safety assessment model, and equipment health assessment model of the multi-parameter processing module, combined with the multi-dimensional data set of hydraulic gates, the flood control and discharge index, structural safety index, and equipment health index are calculated;

[0064] S3: Based on the gate digital twin model and gate opening comprehensive evaluation model constructed by the comprehensive analysis module, the gate opening comprehensive evaluation index is obtained to determine the gate risk level. The gate risk level is determined according to the gate opening comprehensive evaluation index.

[0065] S4: The intelligent decision-making module makes intelligent decisions based on the gate opening comprehensive evaluation index and gate risk level results, obtains emergency response plans, generates optimal gate scheduling plans, and generates intelligent scheduling instructions;

[0066] S5: Build a multi-level early warning mechanism based on the operation and maintenance early warning module. Trigger the corresponding early warning mechanism according to the gate risk level, perform fault diagnosis, and control the gate to perform corresponding operations according to the intelligent scheduling instructions generated by the intelligent decision-making module;

[0067] S6: Receives warning information through the human-computer interaction module, executes the warning interaction process, and provides a visual interactive interface to display the gate digital twin model, multi-dimensional data of the water conservancy gate, gate opening and closing status, and data trends in real time;

[0068] like Figure 3 As shown, the present invention provides a method for determining the risk level of a gate, which specifically includes the following steps:

[0069] A1: When the gate opening comprehensive assessment index is greater than 0.8, the gate risk is at the first risk level, indicating that the gate is in a safe state;

[0070] A2: When the gate opening comprehensive assessment index is less than 0.8 and greater than 0.6, the gate risk is at the second risk level, indicating that the gate is in an alert state;

[0071] A3: When the gate opening comprehensive assessment index is less than 0.6 and greater than 0.3, the gate risk is at the third risk level, indicating that the gate is in a dangerous state;

[0072] A4: When the comprehensive evaluation index of gate opening is less than 0.3, the gate risk is at the fourth risk level, indicating that the gate is in an extremely dangerous state.

[0073] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict.

[0074] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-parameter collaborative intelligent monitoring system for water conservancy gates, characterized by: It includes multi-dimensional perception terminals, edge computing gateways, and cloud server databases, as well as multi-parameter acquisition modules, multi-parameter processing modules, comprehensive analysis modules, intelligent decision-making modules, operation and maintenance warning modules, and human-computer interaction modules: The multi-parameter acquisition module is used to receive multi-dimensional data of water conservancy gates transmitted by the edge computing gateway, including water conservancy environment parameters, gate structure parameters and equipment status parameters, construct a multi-dimensional data set of water conservancy gates, and transmit it to the comprehensive analysis module; The multi-parameter processing module is used to construct a flood control and discharge assessment model, a structural safety assessment model, and an equipment health assessment model. Based on the multi-dimensional data set of the hydraulic gate, the flood control and discharge index, the structural safety index, and the equipment health index are calculated and transmitted to the comprehensive analysis module. The comprehensive analysis module is used to construct a gate digital twin model and a gate opening comprehensive evaluation model, calculate the gate opening comprehensive evaluation index, determine the gate risk level, and pass it to the intelligent decision-making module; The intelligent decision-making module is used to make intelligent decisions based on the gate opening comprehensive evaluation index and the gate risk level results, obtain emergency response plans, generate optimal gate scheduling plans, generate intelligent scheduling instructions, and pass them to the operation and maintenance warning module; The operation and maintenance warning module is used to build a multi-level warning mechanism, trigger the corresponding warning mechanism according to the gate risk level, perform fault diagnosis, control the gate to perform corresponding operations according to the intelligent scheduling instructions generated by the intelligent decision-making module, and transmit warning information to the human-computer interaction module; The human-computer interaction module is used to receive early warning information, execute the early warning interaction process, and provide a visual interactive interface to display the gate digital twin model, multi-dimensional data of the water conservancy gate, gate opening and closing status and data trends in real time, providing human-computer interaction functions.

2. A multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1, characterized in that: The water level environmental parameters specifically include water level height, flow, flood frequency and upstream and downstream water level difference; the gate structure parameters specifically include gate strain value, displacement and material stress; the equipment status parameters specifically include equipment temperature, equipment current, degree of wear and operating time.

3. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The construction of the multidimensional data set of water conservancy gates requires the multidimensional sensing terminal to collect the multidimensional data of water conservancy gates in real time and upload it to the edge computing gateway. The edge computing gateway preprocesses the received multidimensional data of water conservancy gates and passes it to the multi-parameter acquisition module. The multi-parameter acquisition module performs parameter structured classification and metadata annotation on the preprocessed multidimensional data of water conservancy gates to construct a three-dimensional multidimensional data set of water conservancy gates including time dimension, space dimension and parameter type dimension.

4. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The calculation of the flood control and discharge index requires obtaining the water level h, flow Q, flood frequency F and upstream and downstream water level difference Δh in the multi-dimensional data set of the hydraulic gate collected in real time, importing them into the flood control and discharge evaluation model, and using the formula: Calculate the flood control and discharge index I F , where h n Indicates normal water level, h w Indicates the warning water level, Q max represents the designed maximum flood discharge, α F represents the flood frequency correction factor, Δh s represents the safe water level difference threshold, a1, a2, and a3 represent the weight coefficients of water level height, flow rate, and upstream and downstream water level difference, respectively, and the sum of a1, a2, and a3 is 1; The calculation of the structural safety index requires obtaining the gate strain value ε, displacement S, and material stress σ from the multi-dimensional data set of the hydraulic gate collected in real time, importing them into the structural safety assessment model, and using the formula: Calculate the structural safety index I S , where ε0 represents the initial strain value of the gate, ε l Indicates the ultimate strain value of the gate, S max Indicates the maximum allowable displacement of the gate, σ a represents the allowable stress of the material, b1, b2 and b3 represent the weight coefficients of gate strain value, displacement and material stress respectively, and the sum of b1, b2 and b3 is 1; The calculation of the equipment health index requires obtaining the equipment temperature T, equipment current I, and wear degree W from the multi-dimensional data set of the water conservancy gate collected in real time, importing them into the equipment health assessment model, and using the formula: Calculate the equipment health index I E , where T n Indicates the standard temperature of the equipment, T c represents the critical temperature of the equipment, σ I Indicates the standard deviation of the device current, μ I Indicates the average current of the device, W max Indicates the maximum wear degree of the device, where c1, c2, and c3 represent the weight coefficients of device temperature, device current, and wear degree, respectively, and the sum of c1, c2, and c3 is 1.

5. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The construction of the gate digital twin model requires the use of three-dimensional modeling tools to build a high-precision model of the gate, river channel and surrounding terrain, integrating multi-dimensional data in the multi-dimensional data set of the water conservancy gate, driving the dynamic simulation of the gate digital twin model, and reproducing the operating status of the gate at any time based on the historical data stored in the cloud service database, and performing prediction and deduction.

6. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The calculation of the gate opening comprehensive evaluation index requires importing the flood control and discharge index, structural safety index and equipment health index transmitted by the multi-parameter processing module into the gate opening comprehensive evaluation model, using the formula The flood control and discharge index, structural safety index and equipment health index are normalized and the normalized flood control and discharge index, structural safety index and equipment health index are calculated using the formula I = ω1I Fnorm +ω2I Snorm +ω3I Enorm The comprehensive evaluation index I of the gate opening is calculated, where ω1, ω2, and ω3 represent the weight coefficients of the flood control and discharge index, the structural safety index, and the equipment health index, respectively, and the total is 1.

7. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The judgment of the gate risk level requires risk level classification, which is divided into four levels, from low to high risk, namely the first risk level, the second risk level, the third risk level and the fourth risk level. The gate risk level is judged according to the size of the comprehensive evaluation index of the gate opening.

8. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The formulation of the intelligent decision-making requires clarifying the current core risk type based on the comprehensive evaluation index of the gate opening and the corresponding gate risk level, obtaining the emergency response plan library preset in the cloud server database, and matching the emergency response plan with the gate risk level one by one. According to the plan execution logic, based on the plan library, multiple groups of candidate scheduling instructions are generated, and simulation verification is carried out through the gate digital twin model to generate the optimal gate scheduling plan and generate standardized scheduling instructions.

9. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The construction of the multi-level early warning mechanism requires the construction of a four-level early warning mechanism based on the gate risk level obtained by the comprehensive analysis module, and triggering the early warning operation based on the gate risk level obtained by real-time judgment. Fault diagnosis specifically refers to the use of a preset machine learning model to train the mapping relationship of "parameter anomaly-fault type" based on the data collected in real time by the multi-parameter module and the historical fault cases in the cloud server database, to determine the fault type, fault location and fault level, accept and parse the scheduling instructions transmitted by the intelligent decision-making module, and control the gate through the intelligent actuator to complete the specified operation.

10. The multi-parameter collaborative intelligent monitoring system for water conservancy gates according to claim 1 is characterized by: The execution of the early warning interaction process refers to the human-computer interaction terminal confirming the information, handling the dispatch and manual intervention after receiving the early warning information transmitted by the operation and maintenance early warning module. The visual interactive interface specifically includes three-dimensional model display, real-time data monitoring and equipment status monitoring, operation records, support historical data query, and provide staff with manual operation permissions and intelligent decision-making intervention functions.

Images