Hydraulic engineering construction safety abnormity monitoring method and system based on digital twinning

Abstract

The invention discloses a hydraulic engineering construction safety abnormity monitoring method and system based on digital twinning, and relates to the technical field of hydraulic engineering. The method comprises the steps that geographic engineering data, environmental equipment data and personnel data of a construction site are simulated, a twinborn difference network is used for constructing and optimizing a digital twinborn model, and dynamic tracking and simulation model display are achieved; performing data optimization perception and processing on the geographic engineering data, the environmental equipment data and the personnel data by using a digital twinborn model to obtain first feature data, second feature data and third feature data; the first feature data, the second feature data and the third feature data are optimized and fused through a digital twinborn model, a comprehensive feature value is obtained, an optimization coefficient is obtained through calculation, dynamic simulation analysis is conducted through a multi-time-sequence method according to the construction stage, and a time window is adjusted; and determining a grade by using the optimization coefficient, automatically adjusting the construction engineering maintenance progress according to the grade, performing real-time prediction, and sending a result to a construction personnel visual interface.

Description

Technical Field

[0001] The present invention relates to the technical field of water conservancy projects, and specifically to a method and system for monitoring water conservancy project construction safety anomalies based on digital twins. Background Art

[0002] In the field of water conservancy projects, with the continuous advancement of technology, monitoring models and methods are also being continuously optimized and verified, but some problems still exist.

[0003] Current construction site inspections primarily rely on building digital twin models of the construction site, simulating facilities and environments, and dynamically tracking and displaying site data in three dimensions. This simulation optimizes resource management. However, using a single digital twin model to inspect data often fails to yield diverse data analysis results. Combining multi-time series analysis methods with digital twin models allows for data verification, enabling accurate and efficient comprehensive analysis and prediction. This predicted data can provide timely solutions and allow effective preventive measures to be taken in advance.

[0004] To this end, a water conservancy project construction safety anomaly monitoring method and system based on digital twins is proposed. Summary of the Invention

[0005] The present invention aims to provide a digital twin-based water conservancy project construction safety anomaly monitoring method and system for monitoring and handling safety anomalies at water conservancy project construction sites. The specific implementation steps include: simulating the construction site's geographic engineering data, environmental equipment data, and personnel data; using a twin difference network to construct and optimize a digital twin model to achieve dynamic tracking and simulation model display; secondly, using the digital twin model to optimize data perception and processing of the geographic engineering data, environmental equipment data, and personnel data to obtain first, second, and third feature data; optimizing and fusing the first, second, and third feature data using the digital twin model to obtain a comprehensive feature value, and optimizing them using a multi-time series analysis method to obtain an optimization coefficient; determining a level using the optimization coefficient; and automatically adjusting the maintenance schedule of the construction project based on the level, performing real-time prediction, and transmitting the results to a visualization interface for construction personnel. The present invention can accurately collect data from water conservancy project construction sites, achieve real-time monitoring, and promptly propose countermeasures, thereby improving the safety and monitoring efficiency of water conservancy project construction.

[0006] A digital twin-based water conservancy project construction safety anomaly monitoring method includes: simulating the geographic engineering data, environmental equipment data, and personnel data of the construction site, using a twin difference network to build and optimize a digital twin model to achieve dynamic tracking and simulation model display; using the digital twin model to optimize the data perception and processing of the geographic engineering data, environmental equipment data, and personnel data to obtain first feature, second feature, and third feature data; optimizing and fusing the first feature, second feature, and third feature data through the digital twin model to obtain a comprehensive feature value, and using a multi-time series method to analyze and optimize to obtain an optimization coefficient; using the optimization coefficient to determine the level; automatically adjusting the maintenance progress of the construction project according to the level, performing real-time prediction, and sending the results to a construction personnel visualization interface.

[0007] Preferably, the collecting of the first geographic engineering data, the second environmental equipment data and the third personnel data includes: Data imported from the geographic information system and engineering design data are set as geographic engineering data; sensors that monitor the environment and operating equipment parameters are installed at the construction site, and the monitored environment and equipment data are set as environmental equipment data; construction personnel are equipped with smart monitoring bracelets, and the location information, exercise status, heart rate, and blood pressure values ​​monitored by the personnel are recorded as personnel data; all data are recorded in the digital twin model historical database.

[0008] Preferably, the process of obtaining the first feature realization in the step includes: The digital twin model is used to compare and verify the geographic engineering data with the standard value, set the normal range and threshold, compare the actual deviation, and determine whether the deviation exceeds the threshold; if the actual value exceeds the set threshold, it is marked as an anomaly; the geographic engineering data is analyzed through the model, and the volume, size, and position are recorded as feature types; the value of the feature type is the feature value; the deviation of each feature value is weighted and summed according to a certain weight and set as the first feature.

[0009] Preferably, the second feature implementation process of the step includes: The digital twin model is used to compare and verify the environmental equipment data with the standard value, set the normal range and threshold, compare the actual value, and determine whether it exceeds the threshold; if it exceeds the set threshold, it is marked as abnormal; the environmental equipment data is analyzed through the model, and the flow rate and equipment pressure value are recorded as feature types, and the value of the feature type is the feature value; the weighted sum of each feature value and the deviation is set as the second feature.

[0010] Preferably, the process of obtaining the third feature implementation in the step includes: The digital twin model is used to compare and verify the personnel data with the standard value to determine whether the value exceeds the threshold; if the actual value exceeds the set threshold, it is marked as an abnormality; through the model analysis of personnel data, the location information, status, heart rate, and blood pressure of the construction personnel are recorded as feature types, and the value of the feature type is the feature value; the deviation of each feature value is weighted and summed according to a certain weight and set as the third feature.

[0011] Preferably, the step of obtaining the comprehensive characteristic value includes: According to the first feature, the second feature and the third feature, they are multiplied by the eigenvalue variation according to the weight to obtain a comprehensive eigenvalue, which is input into the digital twin model.

[0012] Preferably, the step of obtaining the optimization coefficient includes: According to the comprehensive characteristic value, its values ​​in different time periods are analyzed, and the average value of the comprehensive characteristic value in several time periods is calculated, recorded as the optimization coefficient, and input into the digital twin model.

[0013] Preferably, the visual interface includes: Based on the optimization coefficient obtained through analysis, the digital twin model sends the analysis and optimization prediction results to the smart bracelet. The bracelet vibrates to varying degrees, and the small LCD screen highlights and displays the specific risk content, risk type, and recommended measures.

[0014] Preferably, the water conservancy project construction safety anomaly monitoring system based on digital twins includes: Data extraction module: used to collect construction site geo-engineering data, environmental equipment data, and personnel data; Digital twin model module: This module integrates and optimizes data to build a digital twin model; updates the digital twin model in real time, extracts data for multi-dimensional analysis, determines whether there are any abnormal changes, and predicts future development trends in real time; Feature fusion module: The first feature, the second feature, and the third feature are fused using a weighted summation method to form a comprehensive feature value and obtain the optimization coefficient; Automatic optimization decision support module: optimizes construction plans and resource scheduling based on optimization coefficients and provides real-time notifications; Visual interface module: Send the obtained results to the construction worker's wristband.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The comprehensive eigenvalue proposed in this paper, through the weighted summation of multiple data features, not only encompasses traditional geographic and engineering elements, but also incorporates dynamic environmental factors, equipment operating status, and the real-time status of personnel, providing a richer and more comprehensive data foundation for construction safety monitoring. Compared with traditional monitoring methods based on a single data source, its innovation lies in the deep integration of multi-source heterogeneous data, breaking down data silos and enabling a more accurate reflection of the complex conditions at the construction site.

[0016] The optimization coefficient proposed in this paper enables a quantitative assessment of construction safety risks by analyzing comprehensive characteristic values ​​over different time periods. Unlike previous qualitative or simple quantitative assessment methods, this method dynamically adjusts risk levels based on real-time data, providing an intuitive, accurate, and dynamic risk quantification tool for construction safety management. This reduces safety risks and resource waste caused by irrational decision-making. This innovation shifts construction safety management from empirical judgment to data-driven, scientific decision-making, improving the timeliness and accuracy of risk assessments.

[0017] 3. The visualization interface module proposed in this invention displays assessment reports through a visual interface. Construction workers can determine different risk levels based on the vibration frequency of the wristband, achieving efficient transmission and communication of risk information. Its innovation lies in presenting complex assessment results to construction workers in an easy-to-understand manner, ensuring effective communication of information. This visualization interface also supports interactive functions, allowing users to quickly understand the risk status of specific areas or equipment, providing strong support for on-site decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a method for monitoring abnormal safety of water conservancy project construction based on digital twins proposed in an embodiment of the present invention; Figure 2 A flowchart for obtaining comprehensive characteristic values ​​and optimization coefficients proposed in an embodiment of the present invention; Figure 3 This is a structural diagram of the water conservancy project construction safety anomaly monitoring system based on digital twins proposed in the embodiment of the application of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] During the construction of water conservancy projects, the construction site environment is complex and there are multiple safety risks. If there are problems such as incomplete monitoring data, poor real-time performance and untimely early warning, it will be difficult to meet the safety requirements of modern water conservancy project construction. The development of a method and system that can monitor safety anomalies in water conservancy project construction in real time, comprehensively and intelligently has important practical significance.

[0021] The present invention relates to the field of water conservancy engineering technology, and more specifically to a method and system for monitoring water conservancy construction safety anomalies based on digital twins. The system is applicable to water conservancy construction scenarios such as dam construction and river regulation, improving the safety and monitoring efficiency of water conservancy construction. To illustrate the effectiveness of the method and system of the present invention, a detailed description will be provided in conjunction with the accompanying drawings and the following examples. Example 1

[0022] The embodiment of the present application discloses a method for monitoring safety anomalies of water conservancy project construction based on digital twins, which detects safety anomalies of water conservancy project construction during the construction of a large dam water conservancy project. Figure 1 The flowchart of the water conservancy project construction safety anomaly monitoring method based on digital twins simulates the geographical engineering data, environmental equipment data and personnel data of the construction site, uses the twin difference network to build and optimize the digital twin model, and realizes dynamic tracking and simulation model display; uses the digital twin model to optimize the data perception and processing of the geographical engineering data, environmental equipment data and personnel data respectively to obtain the first feature, second feature and third feature data; optimizes and integrates the first feature, second feature and third feature data through the digital twin model to obtain a comprehensive feature value, and uses a multi-time series method to analyze and optimize to obtain an optimization coefficient; uses the optimization coefficient to determine the level; automatically adjusts the maintenance progress of the construction project according to the level, performs real-time prediction, and sends the results to the construction personnel's visualization interface.

[0023] Furthermore, geographical engineering data, environmental equipment data, and personnel data of the water conservancy project construction site are collected and input into the digital twin model. Corresponding to the above steps, the specific implementation includes: Specifically, at the beginning of construction, data is imported into the geographic information system and combined with satellite remote sensing technology to obtain large-scale and complex geographic information, obtain high-resolution on-site images, and obtain terrain and landform data after processing, which is recorded as geographic engineering data; obtain topographic maps of the construction site and engineering design data; install sensors for monitoring environmental parameters at the construction site and install sensors for monitoring equipment operation on construction equipment, and collect data in real time through the sensor network, which is recorded as environmental equipment data; after processing the collected geographic engineering and environmental equipment data, use the digital twin model to achieve dynamic tracking and simulation model to display complex terrain, and use AR augmented reality technology to build a multi-scene sandbox to assist construction personnel in positioning, intuitively display construction points that are difficult to visually observe, simulate operating procedures and safety procedures in different scenarios, and the execution effects of different emergency plans. The location information, movement status, heart rate and blood pressure values ​​displayed on the wristbands worn by each construction worker are recorded as personnel data; the twin difference network algorithm spatial positioning and data fusion module is used to convert the coordinates of the collected geographic engineering data, unify the data format, fill in missing values ​​and digitize them, and convert the engineering design drawings and documents into a computable format; the time series data of different devices and different monitoring parameters of environmental equipment data are aligned, and the data differences and change trends of adjacent time points are compared. The starting point and sampling frequency parameters of each time series are automatically adjusted to keep the environmental equipment data synchronized in the time dimension, fill in the missing data parts and record the normal operating status and fault status of the equipment; the personnel data is located and recorded to form a complete personnel activity trajectory and status data set.

[0024] The embodiments of this application acquire data through a variety of means, including high-precision measurement equipment, sensors, and monitoring wristbands. These devices can obtain real-time data on geo-engineering, environmental equipment parameters, and personnel status. This real-time data acquisition capability enables the system to promptly reflect the latest conditions at the construction site, providing dynamic and real-time data support for construction safety monitoring, avoiding the errors and omissions that may be caused by a single data source, and providing a rich and comprehensive information foundation for subsequent comprehensive analysis and risk assessment, ensuring the accuracy and reliability of the data.

[0025] Furthermore, the geographic engineering data, environmental equipment data, and personnel data are analyzed respectively to obtain the first feature, the second feature, and the third feature. Corresponding to the above steps, the specific implementation includes: Based on the geo-engineering data, it is compared with standard engineering design data. Based on engineering design specifications and construction requirements, normal ranges and thresholds are set. The deviation between the actual building dimensions and the designed dimensions is compared to determine whether the deviation exceeds the threshold. If the actual value exceeds the set threshold, it is marked as abnormal; if the actual value does not exceed the set threshold, it is marked as normal. By analyzing the geo-engineering data, the volume, size, and location of the building are recorded as feature types; the feature value is the value of the feature type. Through analysis, the volume weight is set to 0.3, the size weight is set to 0.3, and the location weight is set to 0.4. The weighted sum of each feature value is set as the first feature a.

[0026] By comparing geographic engineering data with standard engineering design data, the embodiment of the present application can accurately extract key volume, size, and position parameters during the construction process. This precise feature extraction method helps to promptly detect structural deviations that may occur during the construction process, set normal ranges and thresholds, and compare deviations in real time. Once the actual value exceeds the set threshold, the system can immediately mark the anomaly, thereby achieving real-time monitoring and timely early warning of the construction process. The deviations of each eigenvalue are weighted and summed to obtain the first feature, realizing multi-dimensional feature analysis. This quantitative evaluation method makes the measurement of the degree of anomaly more scientific and accurate, providing a more detailed decision-making basis for construction safety management.

[0027] According to the environmental equipment data, it is compared with the standard value, and the normal range and threshold are set according to the engineering design specifications and construction requirements. The actual water level is compared to determine whether the water level exceeds the threshold water level, or whether the flow rate exceeds the threshold flow rate, or whether the pressure exceeds the threshold pressure; if the actual value exceeds the set threshold, it is marked as an abnormality; due to the rapid change frequency of environmental equipment data, when the actual value of the environmental equipment data exceeds the set threshold, an adaptive data collection strategy is adopted to automatically start an emergency drone inspection, increase the frequency of water level and flow rate monitoring, and store the key monitoring data of the environmental equipment. The environmental data includes timestamp, location size and sensor ID; the equipment data includes timestamp, location, equipment ID and operating status. This adaptive risk handling method facilitates more timely marking of abnormalities and timely acquisition of situations where sudden abnormalities occur. By analyzing the environmental equipment data, the current water level value, flow rate and pressure value are recorded as feature types, and the feature value is the value of the feature type. Through analysis, the weight of the current water level value is set to 0.3, the flow rate weight is set to 0.3, the pressure value weight is set to 0.2, and the state value weight is set to 0.2. The weighted sum of each feature value is set as the second feature b.

[0028] The embodiment of the present application conducts in-depth analysis of environmental equipment data and accurately extracts key environmental parameters such as water level, flow rate and pressure. It can timely capture slight anomalies in environmental changes, compare the monitored environmental equipment data with the standard value in real time, and immediately determine whether the actual water level and other parameters exceed the set threshold. Once the threshold is exceeded, the system will mark the anomaly in real time and issue an early warning, and perform weighted summation on the deviations of each characteristic value to obtain the second feature, achieving multi-dimensional analysis, so that the system can more comprehensively identify anomalies in environmental equipment data, avoid misjudgment or missed judgment caused by focusing on only a single feature, and enhance the ability to identify construction safety risks.

[0029] Based on the personnel data, existing parameters are compared with the normal physical sign values ​​of construction workers. Based on the individual's physical condition, normal ranges and thresholds are set for each body shape value. The values ​​are then compared to the individual's actual condition to determine whether they exceed the threshold. If the actual value exceeds the set threshold, it is marked as abnormal. When analyzing personnel data, UWB precise positioning and posture recognition technology is introduced. An LSTM network is used to analyze abnormal patterns in personnel trajectories to determine whether they have spent extended periods in high-risk areas. Dynamic safety density thresholds are defined. Based on the personnel location clustering results and the equipment movement trajectory, collision probabilities are calculated in real time and spatial partitioning warnings are triggered. This provides a more accurate display of the construction worker's status and effectively monitors the occurrence of safety accidents. By analyzing the third-party personnel data, the construction worker's location information, movement status, heart rate, and blood pressure values ​​are recorded as feature types, with the feature value representing the feature type. The weight of the location information is set to 0.2, the weight of the flow velocity movement status is set to 0.2, the weight of the heart rate is set to 0.3, and the weight of the blood pressure value is set to 0.3. The weighted sum of each feature value is set as the third feature c.

[0030] This embodiment of the application comprehensively understands the real-time status of construction workers by monitoring their location, movement status, heart rate, blood pressure, and other multi-dimensional data. Based on each worker's specific data, personalized risk assessments are performed, making risk assessments more accurate and targeted. The third feature also enables the system to fully monitor the situation of construction workers, ensuring their safety.

[0031] Furthermore, the first feature, the second feature, and the third feature are integrated to obtain a comprehensive feature value, and the comprehensive feature value is analyzed to obtain a risk assessment coefficient; the risk assessment coefficient is used to determine the risk level and generate an assessment report. Corresponding to the above steps, the specific implementation includes: According to the first, second and third features, the product of the eigenvalue variation and the weight is calculated with the weight ratio of 0.3, 0.4 and 0.3 to obtain the comprehensive eigenvalue , the calculation formula is expressed as:

[0032] in, 、 and are the first, second and third features respectively, ω1, ω2 and ω3 are the weights of the first, second and third features respectively, and .

[0033] The embodiment of the present application multiplies the variation of the first feature, the second feature, and the third feature by weight and adds them up to form a comprehensive characteristic value, which comprehensively reflects the overall risk status of the construction site with a unified quantitative standard. This makes subsequent optimization coefficient calculations, risk level determinations, and construction plan adjustments more consistent and comparable, and facilitates analysis and decision-making by management personnel. At different water conservancy project construction sites, the weights of each feature can be flexibly adjusted according to the characteristics and needs of the specific project.

[0034] Furthermore, according to the comprehensive characteristic value , analyze its values ​​in different time periods, take the average value of the comprehensive characteristic values ​​of several time periods, and record it as the optimization coefficient , refer to the acquisition process Figure 2 The flow chart of the comprehensive eigenvalue and optimization coefficient is obtained, and the calculation formula is expressed as: ; in, is the optimization coefficient, is the comprehensive eigenvalue, and n is the number of data points in the time window. Based on the standardized optimization, the risk level classification criteria are set as follows: Low risk: 0≤ <0.3; Medium risk: 0.3 ≤ <0.7; High risk: 0.7 ≤ ≤1; The calculated standardized optimization coefficient is compared with the set threshold to determine the current risk level, and then an assessment report is generated, which includes the risk level, main risk factors and their sources, the location of risk occurrence and optimization coefficient information.

[0035] This embodiment of the application averages the comprehensive characteristic values ​​across multiple time periods, reducing the impact of data anomalies at a single time point on the evaluation results. This comprehensive analysis method for multi-period data improves the reliability of the optimization coefficient, avoids misjudgments caused by short-term data fluctuations, and enhances the foresight of construction safety management.

[0036] Adjust the time window of the monitoring optimization coefficient according to the risk level. If the optimization coefficient is less than the low-risk threshold, adjust the time window to 1.5-2 times the default length; if the optimization coefficient is between the low-risk threshold and the high-risk threshold, keep the time window length unchanged; if the optimization coefficient is greater than the high-risk threshold, adjust the time window to 0.5-0.7 times the default length; each time the time window length is adjusted, it does not jump directly to the target length, but gradually approaches the target length in a certain step size to reduce resource consumption, optimize monitoring efficiency, and avoid excessive process occupation.

[0037] The embodiment of the present application calculates the optimization coefficient, dynamically adjusts the length of the time window according to the risk level of the construction stage, shortens the time window during high-risk periods, and extends the time window during low-risk periods, and predicts the trend of window data through a model; the comprehensive characteristic value dynamically adjusts the weight according to changes in weather and terrain at the construction site, so that the multi-time series analysis method is upgraded from a general algorithm to a technical solution with professional barriers to water conservancy projects.

[0038] Furthermore, the construction project maintenance plan schedule is dynamically adjusted according to the risk level and sent to the visualization interface. Corresponding to the above steps, the specific implementation includes: Construction workers are equipped with smart bracelets, which allow them to check the latest safety status and risk information related to their work areas at any time. When receiving information, it is highlighted and can directly display text, numbers, icons and other information; different degrees of vibration are used to transmit information according to the risk level, long vibration indicates high risk, continuous short vibration indicates medium risk, and short vibration once indicates low risk; according to the risk level results, the construction sequence is adjusted, and construction tasks in high-risk areas are given priority. The twin difference network algorithm is used to extract the difference between the current construction equipment operation data and the normal operation data according to the risk assessment coefficient, and the data is processed in real time to modify the construction method; according to the construction progress requirements, the corresponding workers are arranged to carry out construction in high-risk areas, and safety inspections of the construction site are strengthened; the equipment deployment and material supply plan are optimized, and the supply of waterproof materials is increased to reserve emergency supplies in advance.

[0039] In the embodiment of the present application, the construction personnel's wristband sends timely warnings to the construction personnel through vibration and highlighting, ensuring that the construction personnel can immediately notice abnormal situations and take corresponding response measures, so that they can quickly take correct actions in emergencies, reduce confusion and blind responses, and improve the efficiency of emergency handling.

[0040] The embodiment of the present application realizes the construction safety anomaly monitoring of digital twin water conservancy projects through a water conservancy project construction safety anomaly monitoring method based on digital twins. The specific process mainly includes the following steps: first, simulate the geographical engineering data, environmental equipment data and personnel data of the construction site, use the twin difference network to build and optimize the digital twin model, and realize dynamic tracking and simulation model display; use the digital twin model to optimize the data perception and processing of the geographical engineering data, environmental equipment data and personnel data respectively, and obtain the first feature, second feature and third feature data; optimize and fuse the first feature, second feature and third feature data through the digital twin model to obtain a comprehensive feature value, and use a multi-time series method to analyze and optimize to obtain an optimization coefficient; use the optimization coefficient to determine the level; automatically adjust the maintenance progress of the construction project according to the level, and make real-time predictions, and send the results to the construction personnel visualization interface. The present invention proposes a comprehensive characteristic value, a risk assessment coefficient and a visual interface module for the above process; the comprehensive characteristic value provides a more comprehensive data basis for construction safety monitoring; the risk assessment coefficient provides an intuitive and dynamic risk quantification tool, improving the timeliness and accuracy of risk assessment; the visual interface module presents the assessment results to construction personnel in an easy-to-understand manner, ensuring the effective communication of information.

[0041] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents. Example 2

[0042] In the first embodiment, the method of the present invention realizes the abnormal monitoring of the construction safety of a large-scale dam water conservancy project. In the embodiment of this application, the water conservancy project construction safety system based on digital twin proposed by the present invention is applied to the abnormal monitoring of the construction safety of a B-type dam water conservancy project; Figure 3 Schematic diagram of the structure of the water conservancy project construction safety anomaly monitoring system based on digital twins. The water conservancy project construction safety system based on digital twins includes: a data extraction module, a digital twin model module, a feature fusion module, an automatic optimization decision support module and a visualization interface module.

[0043] Furthermore, the data acquisition module uses lightweight methods, combined with small drone mapping and digital processing of design drawings, to acquire primary geographic engineering data. Low-cost, yet high-precision sensors monitor water levels, flow rates, and small equipment status to acquire environmental equipment data. Construction workers wear wristbands and provide basic personal information and simple activity data, thereby acquiring personnel data.

[0044] Furthermore, the digital twin model module integrates the collected data to construct a digital twin model; updates the digital twin model in real time, extracts data for analysis, and determines whether there are any abnormal changes.

[0045] Furthermore, the feature fusion module fuses the first feature a, the second feature b and the third feature c using a weighted summation method to form a comprehensive feature , analyze the comprehensive characteristics Get the optimization coefficient. The specific implementation process includes: According to the obtained first feature a, second feature b and third feature c, the product of the feature value variation and the weight is calculated with a weight ratio of 0.4, 0.4 and 0.2 to obtain the comprehensive feature , and its calculation formula is expressed as:

[0046] in, is the comprehensive eigenvalue, 、 and are the first, second and third features respectively, ω1, ω2 and ω3 are the weights of the first, second and third features respectively, and .

[0047] Furthermore, according to the comprehensive characteristic value, the values ​​of different time periods are analyzed, and the average value of the comprehensive characteristic value of one minute is taken and recorded as the optimization coefficient. For the specific flowchart of obtaining the optimization coefficient, please refer to Figure 2 , and its calculation formula is expressed as: ; in, is the optimization coefficient, is the comprehensive eigenvalue, and n is the number of data points in the time window.

[0048] Furthermore, based on the calculated optimization coefficient, the risk level classification criteria are set to determine the risk level: Low risk: 0≤ <0.4; Medium risk: 0.4 ≤ <0.8; High risk: 0.8 ≤ ≤1; Furthermore, based on the risk level results, the construction sequence is adjusted, and construction tasks in high-risk areas are given priority. The twin difference network algorithm in deep learning is used to adjust the time window of the monitoring optimization coefficient according to the risk level. If the optimization coefficient is less than the low-risk threshold, the time window is adjusted to 1.5-2 times the default length; if the optimization coefficient is between the low-risk threshold and the high-risk threshold, the time window length is kept unchanged; if the optimization coefficient is greater than the high-risk threshold, the time window is adjusted to 0.5-0.7 times the default length; each time the time window length is adjusted, it does not jump directly to the target length, but gradually approaches the target length with a certain step size, reducing resource consumption, optimizing monitoring efficiency, avoiding excessive process occupation, extracting the difference between the current construction equipment operation data and the data during normal operation, processing the data in real time, and thus modifying the construction method; according to the construction progress requirements, the corresponding workers are arranged to carry out construction in high-risk areas, and safety inspections of the construction site are strengthened; optimize the equipment allocation and material supply plan, increase the supply of waterproof materials, and reserve emergency supplies in advance.

[0049] Furthermore, the visual interface displays information and notifies construction personnel through highlighting and different vibration frequencies, so that they can obtain information in real time.

[0050] The construction worker's wristband vibrates to different degrees according to the risk level to transmit information. Continuous long vibration indicates high risk, continuous short vibration indicates medium risk, and one short vibration indicates low risk, as shown in Table 1.

[0051] Table 1. Calculation of risk assessment coefficients, classification and visualization module display

[0052] The embodiment of the present application uses a water conservancy project construction safety anomaly monitoring system based on digital twins to integrate data management of the data acquisition module, digital twin module, feature fusion module, automatic optimization decision support module and visualization interface module, realizes real-time model updates, conducts accurate risk assessment of construction projects, and provides effective decision support and intuitive visualization display.

[0053] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A water conservancy project construction safety anomaly monitoring method based on digital twins, characterized by: The following steps are involved: Simulating the construction site's geographic engineering data, environmental equipment data, and personnel data, a digital twin model is constructed and optimized using a twin difference network to achieve dynamic tracking and simulation model display. The twin difference network consists of two sub-networks with identical structures and shared weights. Each sub-network receives different input data and independently extracts and transforms its features. The digital twin model is used to optimize the perception and processing of geographic engineering data, environmental equipment data, and personnel data to obtain the first feature, second feature, and third feature data; The first, second, and third feature data are optimized and integrated through the digital twin model to obtain a comprehensive feature value. The optimization coefficient is calculated and a multi-time series method is used to perform dynamic scenario simulation analysis and adjust the time window according to the construction stage. The optimization coefficient is used to determine the grade; the maintenance progress of the construction project is automatically adjusted according to the grade, and real-time prediction is performed, and the results are sent to the visual interface of the construction personnel.

2. The water conservancy project construction safety anomaly monitoring method based on digital twin according to claim 1 is characterized in that: The geographic engineering data, environmental equipment data and personnel data include: Data imported from the geographic information system and engineering design data are set as geographic engineering data; sensors that monitor the environment and operating equipment parameters are installed at the construction site, and the monitored environment and equipment data are set as environmental equipment data; construction personnel are equipped with smart monitoring bracelets, and the location information, exercise status, heart rate, and blood pressure values ​​monitored by the personnel are recorded as personnel data; all data are recorded in the digital twin model historical database.

3. The water conservancy project construction safety anomaly monitoring method based on digital twin according to claim 1 is characterized in that: The process of obtaining the first feature includes: The digital twin model is used to compare and verify the geographic engineering data with the standard value, set the normal range and threshold, compare the actual deviation, and determine whether the deviation exceeds the threshold; if the actual value exceeds the set threshold, it is marked as an anomaly; the geographic engineering data is analyzed through the model, and the volume, size, and position are recorded as feature types; the value of the feature type is the feature value; the deviation of each feature value is weighted and summed according to the weight and set as the first feature.

4. The water conservancy project construction safety anomaly monitoring method based on digital twin according to claim 1 is characterized in that: The process of obtaining the second feature includes: The digital twin model is used to compare and verify the environmental equipment data with the standard value, set the normal range and threshold, compare the actual value, and determine whether it exceeds the threshold; if it exceeds the set threshold, it is marked as abnormal; the environmental equipment data is analyzed through the model, and the flow rate and equipment pressure value are recorded as feature types, and the value of the feature type is the feature value; the weighted sum of each feature value and the deviation is set as the second feature.

5. The water conservancy project construction safety anomaly monitoring method based on digital twin according to claim 1 is characterized in that: The process of obtaining the third feature includes: The digital twin model is used to compare and verify the personnel data with the standard value to determine whether the value exceeds the threshold; if the actual value exceeds the set threshold, it is marked as an abnormality; through the model analysis of personnel data, the location information, status, heart rate, and blood pressure of the construction personnel are recorded as feature types, and the value of the feature type is the feature value; the deviation of each feature value is weighted and summed according to the weight and set as the third feature.

6. The method according to claim 1, the water conservancy project construction safety anomaly monitoring method based on digital twin, is characterized in that: The process of obtaining the comprehensive eigenvalue includes: According to the first feature, the second feature and the third feature, they are multiplied by the eigenvalue variation according to the weight to obtain a comprehensive eigenvalue, which is input into the digital twin model.

7. The method according to claim 1, the water conservancy project construction safety anomaly monitoring method based on digital twin, is characterized in that: The process of obtaining the optimization coefficient includes: According to the comprehensive characteristic value, its values ​​in different time periods are simulated and analyzed, and the average value of the comprehensive characteristic value in each time period is calculated, recorded as the optimization coefficient, and input into the digital twin model.

8. The method according to claim 1, the water conservancy project construction safety anomaly monitoring method based on digital twin, is characterized in that: The implementation process of dynamic scenario simulation analysis using a multi-time sequence method according to the construction stage includes: The time window length of the optimization coefficient is dynamically adjusted according to the environmental and equipment load parameters during the construction phase. The time window is shortened during high-risk periods and extended during low-risk periods. The window data trend is predicted through the model.

9. The water conservancy project construction safety anomaly monitoring method based on digital twin according to claim 1 is characterized in that: The visual interface includes: Based on the optimization coefficient obtained through analysis, the digital twin model sends the analysis and optimization prediction results to the smart bracelet. The bracelet vibrates to varying degrees, and the small LCD screen it is equipped with highlights and displays the specific simulation optimization results.

10. The water conservancy project construction safety anomaly monitoring system based on digital twin is characterized by: include: Data extraction module: used to extract geographic engineering data, environmental equipment data and personnel data of the construction site, and perform parameter processing; Digital twin model module: Uses a twin difference network to fuse and optimize data to build a digital twin model; updates and optimizes the digital twin model in real time, extracts data for multi-dimensional simulation analysis, determines changes in data parameters, and predicts future development trends in real time; Feature data fusion module: The first feature, the second feature, and the third feature are fused using a weighted summation method to form a comprehensive feature value, and then the optimization coefficient is obtained through weighted summation of the algorithm; Automatic optimization decision support module: optimizes construction plans and simulates resource scheduling parameters based on optimization coefficients, and provides real-time notifications; Visual interface module: Send the obtained results to the construction worker's wristband.

Images