CN119476939B - An intelligent seepage monitoring system for water conservancy projects - Google Patents

An intelligent seepage monitoring system for water conservancy projects

Info

Publication number
CN119476939B
CN119476939B CN202411549596.0A CN202411549596A CN119476939B CN 119476939 B CN119476939 B CN 119476939B CN 202411549596 A CN202411549596 A CN 202411549596A CN 119476939 B CN119476939 B CN 119476939B
Authority
CN
China
Prior art keywords
seepage
unit
module
real
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411549596.0A
Other languages
Chinese (zh)
Other versions
CN119476939A (en
Inventor
丰焕平
侯冠宇
王茂华
王泽�
石洋
李照会
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Yellow River Water Conservancy Project Quality Inspection Center
China Institute of Water Resources and Hydropower Research
Original Assignee
Shandong Yellow River Water Conservancy Project Quality Inspection Center
China Institute of Water Resources and Hydropower Research
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong Yellow River Water Conservancy Project Quality Inspection Center, China Institute of Water Resources and Hydropower Research filed Critical Shandong Yellow River Water Conservancy Project Quality Inspection Center
Priority to CN202411549596.0A priority Critical patent/CN119476939B/en
Publication of CN119476939A publication Critical patent/CN119476939A/en
Application granted granted Critical
Publication of CN119476939B publication Critical patent/CN119476939B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Quality & Reliability (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Educational Administration (AREA)
  • Mathematical Optimization (AREA)
  • Molecular Biology (AREA)
  • Primary Health Care (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)

Abstract

The invention relates to the technical field of hydraulic engineering management and discloses a hydraulic engineering seepage intelligent monitoring system which comprises a multi-sensor sensing module, a data acquisition module, a data fusion and processing module, a machine learning prediction module, an intelligent decision module, a self-adaptive monitoring and scheduling module, an automatic inspection and response module, a digital twin and simulation analysis module and a communication module, wherein the multi-sensor sensing module is responsible for acquiring seepage-related multi-dimensional data in real time. Compared with the traditional monitoring method based on the preset threshold value, the method can automatically identify the complex seepage mode penguin to predict the future risk in advance through learning historical data and real-time data, realize prospective management of the seepage risk of the hydraulic engineering and remarkably improve the prediction precision and the response speed of the system.

Description

Hydraulic engineering seepage flow intelligent monitoring system
Technical Field
The invention relates to the technical field of hydraulic engineering management, in particular to an intelligent hydraulic engineering seepage monitoring system.
Background
Seepage monitoring in hydraulic engineering is one of important means for ensuring the safety of a dam structure, a traditional seepage monitoring system generally depends on a fixed threshold early warning and sensor monitoring method, and the prior art has defects when dealing with complex and dynamic hydraulic engineering seepage, and cannot meet the requirements of modern hydraulic engineering on real-time monitoring, intelligent prediction and automatic response. The following specific problems are illustrated by comparing the prior art.
The traditional seepage monitoring method is mainly based on a preset threshold value, parameters such as soil humidity, groundwater level and water pressure are monitored in real time through a sensor, when certain parameters exceed the threshold value, the system performs early warning, in addition, the system based on the fixed threshold value is difficult to predict potential risks when the threshold value is not exceeded, so that early warning cannot be performed, the monitoring system in the contrast file hydraulic engineering seepage intelligent monitoring system and the monitoring method mainly depends on the traditional threshold value monitoring mode, learning of historical data is lacked, trend analysis based on time sequences is lacked, and future seepage risks cannot be predicted through an intelligent means;
The inspection work in the traditional seepage monitoring system is usually carried out by relying on manpower or equipment, particularly manual inspection is required to be arranged after an early warning signal is perceived, inspection efficiency in other modes is low, particularly in an emergency seepage event, the manual inspection cannot rapidly cover all high-risk areas, the inspection system in the hydraulic engineering seepage intelligent monitoring system and the inspection method relies on manual operation, and automatic inspection and emergency response capabilities of the unmanned aerial vehicle and the ground robot are lacked, and in the emergency situation, the emergency response capability of the system and the processing efficiency of the seepage event are limited by the hysteresis of the manual inspection;
The existing hydraulic engineering monitoring system cannot provide visual three-dimensional visual monitoring means, particularly for complex seepage behaviors, the traditional monitoring data and two-dimensional graphic display are difficult to help management staff to accurately judge the seepage diffusion path and future potential risk areas, and compared files are a hydraulic engineering seepage intelligent monitoring system and technology in the monitoring method, three-dimensional simulation analysis is not carried out on the seepage behaviors by utilizing digital twin or virtual reality technology, comprehensiveness and accuracy of management staff in decision making are limited, and a visual decision support means cannot be provided.
Therefore, a person skilled in the art provides an intelligent monitoring system for hydraulic engineering seepage to solve the problems set forth in the background art.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent hydraulic engineering seepage monitoring system, which solves the problems of low prediction precision, low inspection efficiency, delayed emergency response and lack of dynamic simulation and three-dimensional visualization support of the conventional hydraulic engineering seepage monitoring system.
The hydraulic engineering seepage intelligent monitoring system comprises a multi-sensor sensing module, a data acquisition module, a data fusion and processing module, a machine learning prediction module, an intelligent decision module, a self-adaptive monitoring and scheduling module, an automatic inspection and response module, a digital twin and simulation analysis module and a communication module;
the multi-sensor sensing module is responsible for collecting multidimensional data related to seepage in real time;
The data acquisition module is responsible for acquiring real-time monitoring data into the system;
the data fusion and processing module fuses, filters and preprocesses multi-source data acquired by different sensors;
the machine learning prediction module predicts seepage trend by utilizing a machine learning algorithm based on historical monitoring data and real-time acquisition data;
the intelligent decision module combines the machine learning prediction result and the real-time monitoring data to calculate the current seepage risk level;
the self-adaptive monitoring scheduling module dynamically adjusts the monitoring frequency, the sensor acquisition period and the inspection scheduling of the system to generate a risk assessment result;
the automatic inspection and response module is responsible for automatic inspection and emergency response;
the digital twin and simulation analysis module builds a digital twin model of the dam body and the surrounding environment through real-time monitoring data, and performs simulation analysis of seepage and soil erosion;
The communication module is responsible for smooth data transmission among the sensor nodes, the automatic inspection equipment and the control center.
Preferably, the machine learning prediction module comprises a training unit, a model determining unit and a real-time prediction unit;
the training unit trains a machine learning model based on the historical monitoring data and the real-time data;
the model determining unit determines an optimal model for real-time prediction after training is completed;
the real-time prediction unit predicts the trend of seepage, soil erosion and groundwater level change by using a trained model based on current real-time monitoring data.
Preferably, the intelligent decision module comprises a risk assessment unit, an early warning unit and an emergency response unit;
The risk assessment unit calculates the current seepage risk according to the real-time data and the prediction result of the machine learning model;
the early warning unit automatically generates an early warning signal according to the result of the risk assessment unit;
and the emergency response unit automatically starts an emergency response program in a high risk or early warning state.
Preferably, the adaptive monitoring and scheduling module comprises a monitoring frequency control unit and a resource scheduling unit;
the monitoring frequency control unit dynamically adjusts the monitoring frequency of the sensor based on the risk assessment result;
and the resource scheduling unit manages resource allocation in the system.
Preferably, the automatic inspection and response module comprises an unmanned aerial vehicle inspection unit, a ground robot inspection unit, a path planning unit and an image recognition unit;
the unmanned aerial vehicle inspection unit is responsible for managing unmanned aerial vehicle inspection tasks;
The ground robot inspection unit is responsible for the ground robot inspection task and monitoring the dam body;
The path planning unit adopts a path optimization algorithm to intelligently plan the routing inspection routes of the unmanned aerial vehicle and the ground robot;
The image recognition unit analyzes images acquired by the unmanned aerial vehicle and the ground robot by using the convolutional neural network, and automatically detects structural abnormality of the dam body.
Preferably, the digital twin and simulation analysis module comprises a digital twin modeling unit, a seepage simulation unit and a virtual reality integration unit;
The digital twin modeling unit builds a digital twin model of the dam body and the surrounding environment based on real-time monitoring data, and dynamically simulates seepage and soil erosion conditions of the dam body;
The seepage simulation unit utilizes a simulation technology to analyze and predict dynamic processes of seepage diffusion paths, soil erosion and groundwater penetration;
The virtual reality integration unit combines the digital twin model with a virtual reality technology, and a manager can check the real-time seepage state of the dam body through VR equipment.
Preferably, in the training unit, the random forest training algorithm is to construct multiple decision trees and combine the prediction results of each tree to optimize the performance of the model in the training process, wherein the random forest training algorithm is as follows:
decision tree training assuming a dataset of (x, y), where x is the input eigenvector and y is the output target value, each decision tree is minimized based on the following loss function L:
Wherein T i (x) represents the predicted result of the ith tree on the input x, and y i is the actual target value;
The overall prediction of the random forest, wherein the final prediction result of the random forest is the average value of all the prediction results of the decision tree or the voting result:
wherein N is the number of decision trees, Is the predicted value after synthesis, T i (x) is the output of each tree;
In the model determining unit, an optimal model is determined for real-time prediction by evaluating the performances of the multiple training models, wherein model evaluation indexes comprise mean square error and average absolute error;
mean square error formula:
Wherein y i is a true value, N is the number of samples, which is the predicted value of the model;
average absolute error formula:
Wherein y i is a true value, For the model predictor, n is the number of samples.
Preferably, the risk assessment unit combines the real-time data and the prediction data, calculates the current comprehensive risk index R t of the system, and judges the level of the seepage risk according to the index;
The risk assessment formula is R t＝α1Sxs+α2Qxs+α3 Txs,
Wherein Sxs is a water body safety coefficient, qxs is an erosion safety coefficient, txs is a weather condition coefficient, and alpha 1、α2、α3 is a weight coefficient;
the water body safety coefficient Sxs is calculated according to the formula:
Wherein, sy is the monitored water pressure value, S threshold is the preset water pressure safety threshold, and beta 1 is the adjustment parameter;
erosion safety Qxs calculation formula:
wherein, ts is the soil moisture content, T threshold is a preset threshold value of the soil moisture content, and beta 2 is an adjustment parameter;
weather condition coefficient Txs formula Txs =α rRt+αgGq,
Wherein R t is the current rainfall, G q is the current illumination intensity, and alpha r and alpha g are adjustment parameters;
The early warning unit judges whether to trigger an early warning signal or not according to the comprehensive risk index R t calculated by the risk assessment unit, and determines the early warning level;
Early warning judgment formula:
wherein, R t is the currently calculated comprehensive risk index, R threshold is a preset risk threshold, exceeding the threshold triggers an early warning signal, the sign is 1, otherwise, the sign is 0;
early warning level formula:
Wherein R low、Rmedium、Rhigh is the risk index demarcation value of the early warning level.
Preferably, the digital twin modeling unit constructs a digital model corresponding to the physical world by combining real-time monitoring data, historical data and geometric structures of hydraulic engineering;
The digital twin model uses a three-dimensional finite element model to describe stress, strain and seepage behaviors in a physical system by collecting geometric information, physical state and real-time monitoring data;
The control equation of the seepage problem is based on Darcy's law in the seepage process, the relation between the seepage speed v s and the hydraulic gradient i is that v s = -k.i,
Wherein v s is seepage velocity, k is permeability coefficient, i is hydraulic ramp down;
discretization of finite element model, namely discretizing a digital twin geometric model by a finite element method, expressing stress-strain relation to any space domain V by using weak form of the finite element method, and expressing weak form of seepage as follows according to a physical mechanical equation:
Wherein h is the water head height, Is a water head gradient, phi is a shape function, and q is a water source item;
Boundary conditions the digital twin modeling unit needs to meet the boundary conditions, which include:
h (x) =h 0, at boundary Γ D,q(x)＝q0, at boundary Γ N
Wherein Γ D and Γ N are a head fixed boundary and a water flux fixed boundary.
Preferably, the virtual reality integration unit integrates the digital twin model and the simulation result into a virtual reality platform, and provides simulation effects of three-dimensional visualized dam seepage conditions and future risks;
The three-dimensional scene generation formula is P VR＝M·Pworld,
Wherein P VR is the display coordinates in the virtual reality, P world is the three-dimensional coordinates of points in the world coordinate system, and M is the projection matrix of the scene;
The real-time data updating formula is P VR(t)＝PVR (t-1) +delta P (t),
Wherein P VR (t) is the display coordinate at the current moment, P VR (t-1) is the display coordinate at the previous moment, and DeltaP (t) is the position or attribute change value brought by the real-time monitoring data;
VR user interaction formula:
Wherein d interact is the distance between the user and the interactive object, (x u,yu,zu) is the virtual position coordinate of the user, (x o,yo,zo) is the coordinate of the interactive object in the virtual reality scene;
if the distance d interact is smaller than the preset interaction threshold, the system agrees that the user interacts with the virtual object.
The invention provides an intelligent monitoring system for hydraulic engineering seepage. The beneficial effects are as follows:
1. Compared with the traditional monitoring method based on the preset threshold value, the method can automatically identify the complicated seepage mode penguin to predict the future risk in advance through learning historical data and real-time data, realize prospective management of the seepage risk of the hydraulic engineering and remarkably improve the prediction precision and the response speed of the system.
2. According to the invention, the unmanned aerial vehicle and the ground robot are used for cooperative work, so that automatic inspection and emergency response are realized, an unmanned inspection mode is adopted, the monitoring efficiency is improved, manual intervention is greatly reduced, the comprehensiveness and timeliness of inspection are ensured, particularly in a sudden seepage event, the unmanned aerial vehicle and the robot can respond rapidly, and the high-risk area is subjected to key inspection through automatic path planning.
3. According to the invention, a three-dimensional digital twin model is constructed by combining a digital twin technology with real-time seepage simulation, dynamic simulation is carried out on the seepage behavior of the dam body, a visual three-dimensional scene is provided by combining a virtual reality technology, a manager can check the seepage situation of the dam body in real time in a virtual environment, and a future risk diffusion path is predicted, so that visual support is provided for decision making.
Drawings
FIG. 1 is a system frame diagram of the present invention;
FIG. 2 is a schematic diagram of a machine learning prediction module according to the present invention;
FIG. 3 is a schematic diagram of an intelligent decision module according to the present invention;
FIG. 4 is a schematic diagram of an adaptive monitoring and scheduling module according to the present invention;
FIG. 5 is a schematic diagram of an automatic inspection and response module according to the present invention;
FIG. 6 is a schematic diagram of a digital twinning and simulation analysis module according to the present invention.
Detailed Description
In order for those skilled in the art to understand the present invention, the following description will clearly and fully describe the technical solutions of the embodiments of the present invention with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, other embodiments that may be obtained by those of ordinary skill in the art without making any inventive effort should fall within the scope of the present invention.
The invention is described in detail below with reference to the attached drawing figures:
Examples:
Referring to fig. 1-6, an embodiment of the present invention provides an intelligent monitoring system for hydraulic engineering seepage, which includes a multi-sensor sensing module, a data acquisition module, a data fusion and processing module, a machine learning prediction module, an intelligent decision module, an adaptive monitoring and scheduling module, an automatic inspection and response module, a digital twin and simulation analysis module, and a communication module;
the multi-sensor sensing module is responsible for collecting multi-dimensional data related to seepage in real time;
the data acquisition module is responsible for acquiring real-time monitoring data into the system;
The data fusion and processing module fuses, filters and preprocesses multi-source data acquired by different sensors;
the machine learning prediction module predicts the seepage trend by utilizing a machine learning algorithm based on the historical monitoring data and the real-time acquisition data;
the intelligent decision module combines the machine learning prediction result and the real-time monitoring data to calculate the current seepage risk level;
The self-adaptive monitoring scheduling module dynamically adjusts the monitoring frequency, the sensor acquisition period and the inspection scheduling of the system to generate a risk assessment result;
the automatic inspection and response module is responsible for automatic inspection and emergency response;
The digital twin and simulation analysis module builds a digital twin model of the dam body and the surrounding environment through real-time monitoring data, and carries out simulation analysis of seepage and soil erosion;
The communication module is responsible for smooth data transmission among the sensor nodes, the automatic inspection equipment and the control center.
The multi-sensor sensing module has the advantages that the comprehensiveness and the instantaneity of data acquisition are guaranteed, the accuracy of system monitoring is improved, and no blind area coverage is guaranteed;
The data acquisition module has the advantages that the data of the sensor can be acquired into the system rapidly and efficiently, the continuity and timeliness of the monitoring data are guaranteed, the seepage risk is timely perceived, and the rapid response to the hydraulic engineering state is realized;
The data fusion and processing module has the advantages of eliminating data noise, improving the accuracy and consistency of data, and simultaneously, fusing multidimensional data can provide more accurate monitoring information, thereby being beneficial to comprehensively analyzing seepage conditions;
the machine learning prediction module has the advantages that potential risks can be identified in advance, the limitation of relying on a fixed threshold monitoring method is avoided, the prediction precision of the system is improved, and management staff is helped to make prospective seepage management decisions;
The intelligent decision module has the advantages that the current seepage risk level can be dynamically calculated, counter measures are automatically generated, delay of human decision is reduced, and speed and accuracy of emergency response are improved;
the self-adaptive monitoring scheduling module has the advantages of realizing the optimal utilization of resources, saving energy consumption in a low-risk state and ensuring that key areas are monitored in a key way in a high-risk state;
The automatic inspection and response module has the advantages that the inspection efficiency is improved, particularly in high-risk and difficult-to-reach areas, the automatic inspection reduces the dependence on manpower, and meanwhile, the emergency can be responded rapidly, so that the comprehensiveness and timeliness of inspection are ensured;
the digital twin and simulation analysis module has the advantages that management staff is helped to more intuitively understand seepage dynamics and future diffusion trends, three-dimensional visual analysis of seepage behaviors is realized, and intuitiveness and accuracy of decisions are improved;
the benefit of the communication module is that the manager can acquire the latest monitoring information at any time.
The training unit trains a machine learning model based on the historical monitoring data and the real-time data;
The model determining unit determines an optimal model for real-time prediction after training is completed;
the real-time prediction unit predicts the trend of seepage, soil erosion and groundwater level change by using a trained model based on the current real-time monitoring data;
the risk assessment unit calculates the current seepage risk according to the real-time data and the prediction result of the machine learning model;
The early warning unit automatically generates an early warning signal according to the result of the risk assessment unit;
The emergency response unit automatically starts an emergency response program in a high risk or early warning state;
the monitoring frequency control unit dynamically adjusts the monitoring frequency of the sensor based on the risk assessment result;
Resource allocation in a resource scheduling unit management system;
The unmanned aerial vehicle inspection unit is responsible for managing unmanned aerial vehicle inspection tasks;
the ground robot inspection unit is responsible for the ground robot inspection task and monitoring the dam body;
the path planning unit adopts a path optimization algorithm to intelligently plan the routing inspection routes of the unmanned aerial vehicle and the ground robot;
The image recognition unit analyzes images acquired by the unmanned aerial vehicle and the ground robot by using a convolutional neural network and automatically detects structural abnormality of the dam body;
The digital twin modeling unit builds a digital twin model of the dam body and the surrounding environment based on real-time monitoring data, and dynamically simulates seepage and soil erosion conditions of the dam body;
the seepage simulation unit utilizes simulation technology to analyze and predict dynamic processes of seepage diffusion paths, soil erosion and groundwater penetration;
the virtual reality integration unit combines the digital twin model with the virtual reality technology, and a manager can check the real-time seepage state of the dam body through VR equipment.
The training unit has the advantages of learning rules under different seepage modes and environmental conditions, providing a solid foundation for subsequent accurate prediction and improving the seepage risk prediction precision;
The model determining unit has the advantages that a prediction model with the best effect can be used in actual monitoring, so that high-precision seepage, soil erosion and groundwater level change trend prediction can be realized;
the benefits of the real-time prediction unit can identify seepage, soil erosion and groundwater change trend in advance, ensure that the system can react rapidly, and prevent potential risks from evolving into actual accidents;
The risk assessment unit has the advantages of calculating the seepage risk level in real time, providing accurate risk assessment and preventing risks in advance;
The early warning unit has the advantages that related personnel can be timely notified when seepage risks or abnormal conditions occur, hysteresis of manual intervention is reduced, and potential safety problems are timely processed;
the emergency response unit has the advantages that the emergency response program can be automatically started, preventive or remedial measures are rapidly implemented, safety is guaranteed, the possibility of accidents is reduced, and the emergency treatment efficiency is improved;
the monitoring frequency control unit has the advantages that energy consumption is saved when the risk is low, monitoring force is improved when the risk is high, and the energy utilization efficiency and the monitoring flexibility of the system are ensured;
the resource scheduling unit has the advantages that monitoring resources are preferentially deployed in a high-risk area, the utilization efficiency of the monitoring resources is optimized, and the important areas are timely and accurately inspected and monitored;
the unmanned aerial vehicle inspection unit has the advantages that the time and cost of manual inspection are reduced, meanwhile, the comprehensive information of the dam body is obtained through a high-altitude visual angle, and the unmanned aerial vehicle inspection unit is particularly effective in dangerous areas or places which are difficult to reach;
the ground robot inspection unit has the advantages that the comprehensiveness and the accuracy of the inspection process are ensured, and the workload of manual inspection is greatly reduced;
the benefit of the path planning unit ensures that the high-risk area is monitored in a key way, and the execution efficiency of the inspection task is optimized;
the image recognition unit has the advantages of improving recognition accuracy, reducing subjective errors and time cost of manual analysis, and ensuring real-time early warning of structural problems;
the digital twin modeling unit has the advantages that a manager is provided with a real virtual mapping model, so that the manager can better understand and manage the running condition of hydraulic engineering;
the seepage simulation unit has the advantages that the system can simulate future seepage development trend in advance, so that management staff can be helped to evaluate potential risks and make proper countermeasures;
the visual ability of the monitoring system is enhanced by the benefits of the virtual reality integrated unit, and the decision support effect of the manager is improved.
In the training unit, the random forest training algorithm is to construct multiple decision trees and combine the prediction results of each tree to optimize the performance of the model in the training process, wherein the random forest training algorithm is as follows:
decision tree training assuming a dataset of (x, y), where x is the input eigenvector and y is the output target value, each decision tree is minimized based on the following loss function L:
Wherein T i (x) represents the predicted result of the ith tree on the input x, and y i is the actual target value;
The overall prediction of the random forest, wherein the final prediction result of the random forest is the average value of all the prediction results of the decision tree or the voting result:
wherein N is the number of decision trees, Is the predicted value after synthesis, T i (x) is the output of each tree;
In the model determining unit, an optimal model is determined for real-time prediction by evaluating the performance of a plurality of training models, wherein model evaluation indexes comprise mean square error and average absolute error;
mean square error formula:
Wherein y i is a true value, N is the number of samples, which is the predicted value of the model;
average absolute error formula:
Wherein y i is a true value, For the model predictor, n is the number of samples.
Action of decision tree training describes the training process of a single decision tree, which can learn the mapping relationship between input features and output targets, specifically, the loss function, by minimizing the loss function The method is used for measuring the fitting effect of the decision tree T i on the data set D, and the purpose of minimizing the loss function is to enable the predicted result T i (x) of the model to be close to the real target value y i so as to improve the prediction performance of a single tree;
The effect of random forest integral prediction represents that the random forest performs final prediction through a plurality of decision trees, and the prediction results of the plurality of trees are integrated The method can reduce the deviation generated by a single tree, improve the stability and accuracy of the model, and the final prediction of the random forest is obtained by averaging or voting of a plurality of trees, so that the mechanism enhances the overfitting resistance of the model and improves the overall prediction performance;
The deviation between the predicted value and the true value of the model is measured by the action of a mean square error formula, the precision of the model prediction is reflected by calculating the square of the error between the predicted value and the true value and taking an average value, the square error in the formula enables the model to be more sensitive to large deviation, the performance of the model is more beneficial to optimization, the mean square error is small, the predicted result of the model is close to the true value, and the method is an important standard for evaluating the regression model;
The mean absolute deviation between the model predicted value and the true value is measured by the action of the mean absolute error formula, and the mean absolute error is different from the mean square error in that the processing of the error by the mean absolute error has no square term, so that the robustness of the model to the whole error can be reflected.
The risk assessment unit combines the real-time data and the prediction data, calculates the current comprehensive risk index R t of the system, and judges the seepage risk according to the index;
The risk assessment formula is R t＝α1Sxs+α2Qxs+α3 Txs,
Wherein Sxs is a water body safety coefficient, qxs is an erosion safety coefficient, txs is a weather condition coefficient, and alpha 1、α2、α3 is a weight coefficient;
the water body safety coefficient Sxs is calculated according to the formula:
Wherein, sy is the monitored water pressure value, S threshold is the preset water pressure safety threshold, and beta 1 is the adjustment parameter;
erosion safety Qxs calculation formula:
wherein, ts is the soil moisture content, T threshold is a preset threshold value of the soil moisture content, and beta 2 is an adjustment parameter;
weather condition coefficient Txs formula Txs =α rRt+αgGq,
Wherein R t is the current rainfall, G q is the current illumination intensity, and alpha r and alpha g are adjustment parameters;
The early warning unit judges whether an early warning signal is triggered or not according to the comprehensive risk index R t calculated by the risk assessment unit, and determines the early warning level;
Early warning judgment formula:
wherein, R t is the currently calculated comprehensive risk index, R threshold is a preset risk threshold, exceeding the threshold triggers an early warning signal, the sign is 1, otherwise, the sign is 0;
early warning level formula:
Wherein R low、Rmedium、Rhigh is the risk index demarcation value of the early warning level.
The comprehensive risk index formula is used for evaluating the seepage risk of the current hydraulic engineering through the comprehensive water safety coefficient, the corrosion safety coefficient and the weather condition coefficient, each coefficient reflects different seepage influence factors according to different environmental parameters, the weight coefficient adjusts the influence degree of each factor on the overall risk, each influence factor can be effectively synthesized, and a unified risk evaluation result is generated and is used for judging the seepage risk level of the current system;
The influence of the current water body on the stability of the dam body is calculated through the monitored water pressure value and the preset water pressure threshold value by the action of the water body safety coefficient calculation formula, and if the water pressure value is close to or exceeds the threshold value, the water body safety coefficient is obviously increased by using the function form of the formula, so that the threat degree of the water body on the engineering can be sensitively reflected;
the erosion safety coefficient calculation formula is used for evaluating the erosion risk of the soil moisture content on the dam structure, and the formula can rapidly increase the coefficient value when the soil moisture exceeds the threshold value by comparing the monitored moisture content with the set safety threshold value so as to reflect the erosion degree of the soil on the dam;
The influence of weather conditions on seepage is estimated by combining the current rainfall and illumination intensity, the rainfall reflects the direct influence on water level and seepage, the illumination intensity influences soil evaporation and water loss, the formula integrates the influence of weather factors on risks, and the weight in risk estimation is adjusted by adjusting parameters;
The action of the early warning judgment formula is used for judging whether an early warning signal is triggered or not, the early warning signal is triggered if R t exceeds a threshold value by comparing the currently calculated comprehensive risk index with a preset risk threshold value, otherwise, the early warning signal is marked as 1, and the early warning signal is marked as 0, so that the formula ensures that the system can automatically send out the early warning signal under the condition that the risk threshold value is exceeded is detected, and the manager is helped to timely cope with potential risks;
The effect of the early warning level formula determines the severity level of early warning according to the magnitude of the comprehensive risk index, the early warning is divided into low, medium and high levels according to the comprehensive risk index R t and a preset level demarcation value, and the early warning of different levels corresponds to different countermeasures, so that the system can take proper preventive or emergency response actions according to the severity of the risk.
The digital twin modeling unit constructs a digital model corresponding to the physical world by combining the real-time monitoring data, the historical data and the geometric structure of the hydraulic engineering;
The digital twin model uses a three-dimensional finite element model to describe stress, strain and seepage behaviors in a physical system by collecting geometric information, physical state and real-time monitoring data;
The control equation of the seepage problem is based on Darcy's law in the seepage process, the relation between the seepage speed v s and the hydraulic gradient i is that v s = -k.i,
Wherein v s is seepage velocity, k is permeability coefficient, i is hydraulic ramp down;
discretization of finite element model, namely discretizing a digital twin geometric model by a finite element method, expressing stress-strain relation to any space domain V by using weak form of the finite element method, and expressing weak form of seepage as follows according to a physical mechanical equation:
Wherein h is the water head height, Is a water head gradient, phi is a shape function, and q is a water source item;
Boundary conditions the digital twin modeling unit needs to meet the boundary conditions, which include:
h (x) =h 0, at boundary Γ D,q(x)＝q0, at boundary Γ N
Wherein Γ D and Γ N are a head fixed boundary and a water flux fixed boundary.
The function control equation of the seepage problem is based on Darcy's law, describes the linear relation between seepage velocity and hydraulic gradient, the permeability coefficient is a characteristic parameter of a medium material, characterizes the permeability of soil or other mediums to water, is used for calculating the seepage velocity flowing through a dam body or soil under the action of hydraulic gradient, and ensures that a model can accurately reflect the physical behavior in the seepage process;
the discretization function of the finite element model expresses the weak form of the seepage problem based on the finite element method, and the finite element method converts a continuous seepage equation into a discrete algebraic equation by discretizing the space domain, so that numerical solution is conveniently carried out in the digital twin model, and the numerical simulation of seepage can be ensured to accurately describe the seepage condition in engineering;
The condition that the water head fixing boundary condition acts on the defined water head fixing is that the water head is constant in a specific boundary area, and the condition is used for simulating the fixed water head boundary existing in actual engineering, such as water level control at the bottom of a dam body, so that the model can accurately reflect the actual boundary condition;
The effect of the water flux fixation boundary conditions is that boundary conditions describing the water flux fixation, i.e. at a certain boundary, the water flux is constant. This boundary condition is used to simulate a fixed water flow situation, such as a water flow into or out of an area, ensuring that the model takes into account the specific flow conditions at the water flow boundary.
The virtual reality integration unit integrates the digital twin model and the simulation result into a virtual reality platform, and provides simulation effects of three-dimensional visualized dam seepage conditions and future risks;
The three-dimensional scene generation formula is P VR＝M·Pworld,
Wherein P VR is the display coordinates in the virtual reality, P world is the three-dimensional coordinates of points in the world coordinate system, and M is the projection matrix of the scene;
The real-time data updating formula is P VR(t)＝PVR (t-1) +delta P (t),
Wherein P VR (t) is the display coordinate at the current moment, P VR (t-1) is the display coordinate at the previous moment, and DeltaP (t) is the position or attribute change value brought by the real-time monitoring data;
VR user interaction formula:
Wherein d interact is the distance between the user and the interactive object, (x u,yu,zu) is the virtual position coordinate of the user, (x o,yo,zo) is the coordinate of the interactive object in the virtual reality scene;
if the distance d interact is smaller than the preset interaction threshold, the system agrees that the user interacts with the virtual object.
The three-dimensional scene generation formula is used for converting the three-dimensional coordinates of the physical world into display coordinates in the virtual reality, the projection matrix is responsible for mapping points in the three-dimensional space onto a two-dimensional screen of the virtual reality environment, the process ensures that dam seepage conditions in the physical world can be accurately displayed in the virtual reality system, and a basis for visual interaction of a user is provided;
The display coordinates in the virtual reality scene are dynamically updated under the action of a real-time data updating formula, the scene in the virtual reality can be updated by the system according to the current monitoring data change through the position or attribute change value brought by the real-time monitoring data, so that the dynamic change of a physical system can be reflected by the virtual environment, the dam body seepage simulation in the virtual reality can be kept synchronous with the actual environment, and a manager can observe the latest seepage situation in real time through VR equipment;
the interaction of the VR user interaction formula calculates the distance between the user and the interaction object in the virtual reality environment, and the three-dimensional distance between the virtual position of the user and the position of the interaction object is calculated, if the distance is smaller than the set interaction threshold, the system agrees to perform interactive operation between the user and the virtual object, and the formula ensures that the user can interact with the virtual object in the scene in a natural mode in the virtual reality environment, so that the immersion feeling and the operation experience of the user are improved.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (6)

1.一种水利工程渗流智能监测系统，其特征在于，包括多传感器感知模块、数据采集模块、数据融合与处理模块、机器学习预测模块、智能决策模块、自适应监测调度模块、自动巡检与响应模块、数字孪生与仿真分析模块、通信模块；1. An intelligent water conservancy project seepage monitoring system, characterized by including a multi-sensor perception module, a data acquisition module, a data fusion and processing module, a machine learning prediction module, an intelligent decision-making module, an adaptive monitoring and scheduling module, an automatic inspection and response module, a digital twin and simulation analysis module, and a communication module; 所述多传感器感知模块负责实时采集渗流相关的多维度数据；The multi-sensor perception module is responsible for collecting multi-dimensional data related to seepage in real time; 所述数据采集模块负责将实时监测数据采集到系统内部；The data acquisition module is responsible for collecting real-time monitoring data into the system; 所述数据融合与处理模块将不同传感器采集的多源数据进行融合、过滤与预处理；The data fusion and processing module fuses, filters and preprocesses multi-source data collected by different sensors; 所述机器学习预测模块基于历史监测数据和实时采集数据，利用机器学习算法进行渗流趋势的预测；The machine learning prediction module uses a machine learning algorithm to predict the seepage trend based on historical monitoring data and real-time collected data; 所述智能决策模块结合机器学习预测结果和实时监测数据，计算当前的渗流风险水平；The intelligent decision-making module combines machine learning prediction results and real-time monitoring data to calculate the current seepage risk level; 所述智能决策模块包括风险评估单元、预警单元、应急响应单元；The intelligent decision-making module includes a risk assessment unit, an early warning unit, and an emergency response unit; 所述风险评估单元根据实时数据和机器学习模型的预测结果，计算当前的渗流风险；The risk assessment unit calculates the current seepage risk based on real-time data and prediction results of the machine learning model; 所述预警单元根据风险评估单元的结果，自动生成预警信号；The early warning unit automatically generates an early warning signal based on the results of the risk assessment unit; 所述应急响应单元在高风险或预警状态时，自动启动应急响应程序；The emergency response unit automatically initiates the emergency response procedure when in a high-risk or warning state; 所述风险评估单元结合实时数据和预测数据，计算系统当前的综合风险指数Rt，且根据该指数判断渗流风险的高低；The risk assessment unit combines real-time data and forecast data to calculate the current comprehensive risk index R t of the system and determines the level of seepage risk based on the index; 风险评估公式为：Rt＝α1Sxs+α2Qxs+α3Txs，The risk assessment formula is: R t = α 1 Sxs + α 2 Qxs + α 3 Txs, 其中，Sxs为水体安全系数，Qxs为侵蚀安全系数，Txs为天气条件系数，α1、α2、α3为权重系数；Among them, Sxs is the water safety factor, Qxs is the erosion safety factor, Txs is the weather condition coefficient, and α 1 , α 2 , and α 3 are weight coefficients; 水体安全系数Sxs计算公式： Calculation formula for water safety factor Sxs: 其中，Sy为监测的水压值，Sthreshold为预设的水压安全阈值，β1为调整参数；Wherein, Sy is the monitored water pressure value, S threshold is the preset water pressure safety threshold, and β 1 is the adjustment parameter; 侵蚀安全系数Qxs计算公式： Calculation formula for erosion safety factor Qxs: 其中，Ts为土壤含水量，Tthreshold为土壤含水量的预设阈值，β2为调整参数；Where Ts is the soil moisture content, T threshold is the preset threshold of soil moisture content, and β 2 is the adjustment parameter; 天气条件系数Txs计算公式：Txs＝αrRt+αgGq，The calculation formula of weather condition coefficient Txs is: Txs＝α r R t +α g G q , 其中，Rt为当前的降雨量，Gq为当前的光照强度，αr和αg为调整参数；Among them, Rt is the current rainfall, Gq is the current light intensity, αr and αg are adjustment parameters; 所述预警单元根据风险评估单元计算的综合风险指数Rt，判断是否触发预警信号，且决定预警的级别；The early warning unit determines whether to trigger an early warning signal and determines the level of the early warning based on the comprehensive risk index R t calculated by the risk assessment unit; 预警判断公式： Early warning judgment formula: 其中，Rt为当前计算出的综合风险指数，Rthreshold为预设的风险阈值，超出阈值会触发预警信号，标识为1，否则为0；Where Rt is the currently calculated comprehensive risk index, Rthreshold is the preset risk threshold, exceeding the threshold will trigger an early warning signal, marked as 1, otherwise it is 0; 预警级别公式： Warning level formula: 其中，Rlow、Rmedium、Rhigh为预警级别的风险指数分界值；Among them, R low , R medium , and R high are the risk index cutoff values of the warning level; 所述自适应监测调度模块动态调整系统的监测频率、传感器采集周期和巡检调度，以生成的风险评估结果；The adaptive monitoring and scheduling module dynamically adjusts the system's monitoring frequency, sensor acquisition cycle, and inspection scheduling to generate risk assessment results; 所述自动巡检与响应模块负责自动化巡检和应急响应；The automatic inspection and response module is responsible for automatic inspection and emergency response; 所述数字孪生与仿真分析模块通过实时监测数据构建坝体及周围环境的数字孪生模型，且进行渗流和土壤侵蚀的仿真分析；The digital twin and simulation analysis module constructs a digital twin model of the dam and its surrounding environment through real-time monitoring data, and performs simulation analysis of seepage and soil erosion; 所述数字孪生与仿真分析模块包括数字孪生建模单元、渗流仿真单元、虚拟现实集成单元；The digital twin and simulation analysis module includes a digital twin modeling unit, a seepage simulation unit, and a virtual reality integration unit; 所述数字孪生建模单元基于实时监测数据，构建坝体及周边环境的数字孪生模型，动态模拟坝体的渗流和土壤侵蚀情况；The digital twin modeling unit constructs a digital twin model of the dam body and surrounding environment based on real-time monitoring data, and dynamically simulates the seepage and soil erosion of the dam body; 所述渗流仿真单元利用仿真技术分析和预测渗流扩散路径、土壤侵蚀和地下水渗透的动态过程；The seepage simulation unit uses simulation technology to analyze and predict the dynamic process of seepage diffusion path, soil erosion and groundwater infiltration; 所述虚拟现实集成单元将数字孪生模型与虚拟现实技术结合，管理人员能通过VR设备查看坝体实时的渗流状态；The virtual reality integration unit combines the digital twin model with virtual reality technology, allowing managers to view the real-time seepage status of the dam body through VR equipment; 所述数字孪生建模单元通过将实时监测数据、历史数据与水利工程的几何结构相结合，构建与物理世界相对应的数字模型；The digital twin modeling unit constructs a digital model corresponding to the physical world by combining real-time monitoring data, historical data and the geometric structure of the water conservancy project; 数字孪生模型通过集合几何信息、物理状态和实时监测数据，使用三维有限元模型描述物理系统中的应力、应变和渗流行为；The digital twin model uses a three-dimensional finite element model to describe the stress, strain, and permeation behavior in the physical system by integrating geometric information, physical state, and real-time monitoring data; 渗流问题的控制方程：基于渗流过程中的达西定律，渗流速度vs与水力坡降i的关系为：vs＝-k·i，The governing equation of the seepage problem: Based on Darcy's law in the seepage process, the relationship between the seepage velocity vs and the hydraulic gradient i is: vs = -k·i, 其中，vs为渗流速度，k为渗透系数，i为水力坡降；Among them, vs is the seepage velocity, k is the permeability coefficient, and i is the hydraulic gradient; 有限元模型的离散化：数字孪生的几何模型通过有限元法进行离散化，对任意空间域V，使用有限元法的弱形式表达应力-应变关系，根据物理力学方程，渗流的弱形式表示为：Discretization of the finite element model: The geometric model of the digital twin is discretized using the finite element method. For any spatial domain V, the weak form of the finite element method is used to express the stress-strain relationship. According to the physical mechanics equation, the weak form of seepage is expressed as: 其中，h为水头高度，为水头梯度，φ为形函数，q为水源项，dV为微元积分；Where h is the water head height, is the head gradient, φ is the shape function, q is the water source term, and dV is the differential integral; 边界条件：数字孪生建模单元需满足边界条件，边界条件包括：Boundary conditions: The digital twin modeling unit must meet boundary conditions, including: h(x)＝h0，在边界ΓD，q(x)＝q0，在边界ΓN h(x)＝h 0 , at the boundary Γ D , q(x)＝q 0 , at the boundary Γ N 其中，h(x)为在边界特定位置x上的水头高度，h0为初始的水头高度，ΓD和ΓN为水头固定边界和水流通量固边界，q(x)为在边界ΓN上的特定位置x处的流量值，q0为初始的流量值；Where h(x) is the hydraulic head height at a specific position x on the boundary, h 0 is the initial hydraulic head height, Γ D and Γ N are the hydraulic head fixed boundary and the water flux fixed boundary, q(x) is the flow value at a specific position x on the boundary Γ N , and q 0 is the initial flow value; 所述通信模块负责各传感器节点、自动巡检设备与控制中心间的数据传输通畅。The communication module is responsible for the smooth data transmission between each sensor node, automatic inspection equipment and the control center. 2.根据权利要求1所述的一种水利工程渗流智能监测系统，其特征在于，所述机器学习预测模块包括训练单元、模型确定单元、实时预测单元；2. The water conservancy project seepage intelligent monitoring system according to claim 1, wherein the machine learning prediction module includes a training unit, a model determination unit, and a real-time prediction unit; 所述训练单元基于历史监测数据和实时数据，训练机器学习模型；The training unit trains a machine learning model based on historical monitoring data and real-time data; 所述模型确定单元在训练完成后，确定最优模型用于实时预测；After the training is completed, the model determination unit determines the optimal model for real-time prediction; 所述实时预测单元基于当前实时监测数据，使用已训练的模型预测渗流、土壤侵蚀、地下水位变化的趋势。The real-time prediction unit uses the trained model to predict the trends of seepage, soil erosion, and groundwater level changes based on the current real-time monitoring data. 3.根据权利要求1所述的一种水利工程渗流智能监测系统，其特征在于，所述自适应监测调度模块包括监测频率控制单元、资源调度单元；3. The water conservancy project seepage intelligent monitoring system according to claim 1, wherein the adaptive monitoring and scheduling module includes a monitoring frequency control unit and a resource scheduling unit; 所述监测频率控制单元基于风险评估结果，动态调整传感器的监测频率；The monitoring frequency control unit dynamically adjusts the monitoring frequency of the sensor based on the risk assessment result; 所述资源调度单元管理系统中的资源调配。The resource scheduling unit manages resource allocation in the system. 4.根据权利要求1所述的一种水利工程渗流智能监测系统，其特征在于，所述自动巡检与响应模块包括无人机巡检单元、地面机器人巡检单元、路径规划单元、图像识别单元；4. The intelligent monitoring system for water conservancy project seepage according to claim 1, wherein the automatic inspection and response module includes an unmanned aerial vehicle inspection unit, a ground robot inspection unit, a path planning unit, and an image recognition unit; 所述无人机巡检单元负责管理无人机巡检任务；The drone inspection unit is responsible for managing drone inspection tasks; 所述地面机器人巡检单元负责地面机器人巡检任务，进行坝体的监测；The ground robot inspection unit is responsible for ground robot inspection tasks and monitors the dam body; 所述路径规划单元采用路径优化算法对无人机和地面机器人的巡检路线进行智能规划；The path planning unit uses a path optimization algorithm to intelligently plan the inspection routes of the drone and ground robot; 所述图像识别单元利用卷积神经网络对无人机和地面机器人采集的图像进行分析，自动检测坝体的结构异常。The image recognition unit uses a convolutional neural network to analyze images collected by drones and ground robots to automatically detect structural abnormalities of the dam body. 5.根据权利要求2所述的一种水利工程渗流智能监测系统，其特征在于，所述训练单元中，随机森林训练算法是通过构建多决策树，且在训练过程中结合各棵树的预测结果来优化模型的性能，其中，随机森林训练算法如下：5. The intelligent water conservancy project seepage monitoring system according to claim 2, characterized in that, in the training unit, the random forest training algorithm optimizes the performance of the model by constructing multiple decision trees and combining the prediction results of each tree during the training process, wherein the random forest training algorithm is as follows: 决策树训练：假设数据集为(x，y)，其中，x是输入特征向量，y是输出目标值，各决策树是基于如下损失函数L进行最小化：Decision tree training: Assume that the data set is (x, y), where x is the input feature vector and y is the output target value. Each decision tree is based on minimizing the following loss function L: 其中，Ti(x)表示第i棵树对输入x的预测结果，yi是实际目标值；Where Ti (x) represents the prediction result of the i-th tree for input x, and yi is the actual target value; 随机森林整体预测：随机森林的最终预测结果为所有决策树预测结果的平均值或投票结果： Random Forest Ensemble Prediction: The final prediction of the random forest is the average or voting result of all the decision tree predictions: 其中，N为决策树的数量，是综合后的预测值，Ti(x)是各棵树的输出；Where N is the number of decision trees, is the combined prediction value, and T i (x) is the output of each tree; 所述模型确定单元中，通过评估多训练模型的表现，确定最优模型用于实时预测，其中，模型评估指标包括均方误差、平均绝对误差；In the model determination unit, the optimal model is determined for real-time prediction by evaluating the performance of multiple training models, wherein the model evaluation indicators include mean square error and mean absolute error; 均方误差公式： Mean square error formula: 其中，yi为真实值，为模型的预测值，n为样本数量；Among them, yi is the true value, is the predicted value of the model, and n is the number of samples; 平均绝对误差公式： Mean absolute error formula: 其中，yi为真实值，为模型预测值，n为样本数量。Among them, yi is the true value, is the model prediction value, and n is the number of samples. 6.根据权利要求1所述的一种水利工程渗流智能监测系统，其特征在于，所述虚拟现实集成单元将数字孪生模型与仿真结果集成到虚拟现实平台中，提供三维可视化的坝体渗流情况和未来风险的仿真效果；6. The intelligent water conservancy project seepage monitoring system according to claim 1, wherein the virtual reality integration unit integrates the digital twin model and simulation results into the virtual reality platform to provide a three-dimensional visualization of the dam body seepage situation and simulation effects of future risks; 三维场景生成公式：PVR＝M·Pworld，3D scene generation formula: P VR = M·P world , 其中，PVR为虚拟现实中的显示坐标，Pworld为世界坐标系下的点的三维坐标，M为场景的投影矩阵；Where P VR is the display coordinate in virtual reality, P world is the three-dimensional coordinate of the point in the world coordinate system, and M is the projection matrix of the scene; 实时数据更新公式：PVR(t)＝PVR(t-1)+ΔP(t)，Real-time data update formula: P VR (t) = P VR (t-1) + ΔP (t), 其中，PVR(t)为当前时刻的显示坐标，PVR(t-1)为前一时刻的显示坐标，ΔP(t)为实时监测数据带来的位置或属性变化值；Wherein, P VR (t) is the display coordinate at the current moment, P VR (t-1) is the display coordinate at the previous moment, and ΔP(t) is the position or attribute change value brought by the real-time monitoring data; VR用户交互公式：VR user interaction formula: 其中，dinteract为用户与交互对象间的距离，(xu，yu，zu)为用户的虚拟位置坐标，(xo，yo，zo)为虚拟现实场景中交互物体的坐标；Where dinteract is the distance between the user and the interactive object, ( xu , yu , zu ) is the user's virtual position coordinate, and ( xo , yo , zo ) is the coordinate of the interactive object in the virtual reality scene; 若距离dinteract小于预设的交互阈值时，系统同意用户与虚拟对象进行交互。If the distance dinteract is less than the preset interaction threshold, the system allows the user to interact with the virtual object.
CN202411549596.0A 2024-11-01 2024-11-01 An intelligent seepage monitoring system for water conservancy projects Active CN119476939B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411549596.0A CN119476939B (en) 2024-11-01 2024-11-01 An intelligent seepage monitoring system for water conservancy projects

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411549596.0A CN119476939B (en) 2024-11-01 2024-11-01 An intelligent seepage monitoring system for water conservancy projects

Publications (2)

Publication Number Publication Date
CN119476939A CN119476939A (en) 2025-02-18
CN119476939B true CN119476939B (en) 2025-09-12

Family

ID=94570857

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411549596.0A Active CN119476939B (en) 2024-11-01 2024-11-01 An intelligent seepage monitoring system for water conservancy projects

Country Status (1)

Country Link
CN (1) CN119476939B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119691409A (en) * 2025-02-24 2025-03-25 华能澜沧江水电股份有限公司 A dam leakage intelligent monitoring and prediction early warning method and system
CN119861186B (en) * 2025-03-22 2025-06-27 北京益邦达科技发展有限公司 Soil moisture content monitoring method, system, program product and storage medium
CN120235457A (en) * 2025-04-15 2025-07-01 广东省水利水电科学研究院 Intelligent early warning and disposal decision-making system and method for flood storage and detention area embankment leakage risk
CN120026919B (en) * 2025-04-18 2025-06-20 山东黄金矿业科技有限公司充填工程实验室分公司 Intelligent control system for deep well exploitation equipment
CN120387146A (en) * 2025-06-30 2025-07-29 中铁十九局集团有限公司 A method and device for monitoring underground water seepage
CN120736301B (en) * 2025-09-03 2026-01-02 华能上海石洞口发电有限责任公司 Unmanned screw ship unloader material and ship control method and system
CN121146233A (en) * 2025-11-17 2025-12-16 四川省紫坪铺开发有限责任公司 Multimodal sensing-based automatic inspection path optimization method and system for flood discharge tunnels

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116629602A (en) * 2023-05-10 2023-08-22 中国三峡建工(集团)有限公司 Seepage safety dynamic monitoring and disaster early warning system of earth-rock dam based on digital twin technology and its construction method

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11069082B1 (en) * 2015-08-23 2021-07-20 AI Incorporated Remote distance estimation system and method
CN110191988A (en) * 2016-11-18 2019-08-30 中国电建集团贵阳勘测设计研究院有限公司 A kind of cushion of dam with face slab material safety appraisement of structure method
CN114707227B (en) * 2022-04-28 2024-10-08 水利部南京水利水文自动化研究所 Dam safety early warning and alarm eliminating method and system based on digital twinning
CN115688227B (en) * 2022-10-13 2023-06-09 长江空间信息技术工程有限公司(武汉) Digital twin hydraulic engineering operation safety monitoring system and operation method
CN116291352B (en) * 2023-03-06 2025-05-16 成都理工大学 Method and system for real-time evaluation of potential catastrophe risk to optimize fracturing construction parameters
CN117789434A (en) * 2023-06-05 2024-03-29 黄河水利职业技术学院 Hydraulic engineering seepage intelligent monitoring system and monitoring method
CN116882211B (en) * 2023-09-06 2023-12-19 珠江水利委员会珠江水利科学研究院 Reservoir water condition forecasting simulation method and system based on digital twin
CN117994728B (en) * 2024-02-21 2024-08-13 北京中瀚润淇科技有限公司 Intelligent operation and maintenance management system for high-speed rail motor car based on digital twin
CN118822307A (en) * 2024-07-02 2024-10-22 江苏智水智能科技有限责任公司 A water conservancy information management method and management system based on digital twin technology

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116629602A (en) * 2023-05-10 2023-08-22 中国三峡建工(集团)有限公司 Seepage safety dynamic monitoring and disaster early warning system of earth-rock dam based on digital twin technology and its construction method

Also Published As

Publication number Publication date
CN119476939A (en) 2025-02-18

Similar Documents

Publication Publication Date Title
CN119476939B (en) An intelligent seepage monitoring system for water conservancy projects
CN106593534B (en) A kind of intelligent tunnel construction safety monitoring system
CN111409788B (en) A method and system for testing the autonomous navigation capability of an unmanned vessel
CN105758450B (en) Met an urgent need based on multisensor the fire-fighting early warning sensory perceptual system construction method of robot
CN119647981B (en) A construction safety prompting method and system
CN115392708A (en) Fire risk assessment and early warning method and system for building fire protection
CN114547759B (en) Creeping formwork construction monitoring method, creeping formwork construction monitoring system and computer readable storage medium
JP7166498B1 (en) Wind condition learning device, wind condition prediction device, and drone system
CN116931448A (en) Intelligent ship state monitoring and control system based on digital twin
CN119147048B (en) An environmental monitoring method and system based on digital twin technology
CN106989778A (en) A kind of Tailings Dam on-line monitoring system
CN118607065A (en) Building structure deformation prediction system based on fuzzy logic control algorithm
CN118641083A (en) Real-time bridge stress detection method and system based on big data
CN120063364A (en) Bridge structure health monitoring method based on big data and cloud computing
CN104778331B (en) A kind of Loads of Long-span Bridges Monitoring Data spatial interpolation methods
CN120726559A (en) Intelligent safety management method and system for wind power construction based on intelligent AI monitoring
CN119593303A (en) A construction monitoring method and system for a cross-railway rotating bridge based on digital twin
CN120911978B (en) Method and Device for Monitoring Substations Based on Multi-Data Sources of Power Distribution
CN117540850A (en) Building-based virtual power plant load prediction method
CN115830807A (en) Mine safety early warning method, system, equipment and medium
CN120724411A (en) A water quality concentration collection and real-time detection system and method
CN120671399A (en) Hydraulic engineering construction safety abnormity monitoring method and system based on digital twinning
CN120012432A (en) A multi-scenario simulation method and system based on digital twin technology
CN117291293B (en) Tunnel fire scene disaster perception and situation development prediction method
CN120009136A (en) Air pollution prediction system and method based on meteorological data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant