Construction management optimization method and system based on digital twinborn technology

Through digital twin technology, the twin model and coupling feedback mechanism are built, which solves the problem of difficult prediction of highway construction quality, real-time simulation and optimization of construction strategies are realized, and the accuracy and efficiency of construction management are improved.

CN119026993AInactive Publication Date: 2024-11-26QINGHAI TRAFFIC CONTROL INFORMATION TECH CO LTD
View PDF 0 Cites 8 Cited by

Patent Information

Application Number
CN202411183282.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, the quality of highway construction is difficult to accurately predict and the management is inaccurate, which leads to difficult control of construction quality and low efficiency.

Method used

A twin model is built based on digital twin technology, combining geographical distribution and IoT sensing data, a scene simulation module and construction prediction module are built, a coupled feedback mechanism is established, construction scenarios are simulated in real time, construction quality is predicted, and construction strategies are optimized through quality deviation.

Benefits of technology

Real-time simulation of highway construction scenarios is achieved, construction quality and efficiency are improved, and construction management is enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026993A_ABST
    Figure CN119026993A_ABST
Patent Text Reader

Abstract

The invention provides a construction management optimization method and system based on a digital twinning technology, and relates to the technical field of data engineering construction management.The method comprises the steps that a twinning model is built through the digital twinning technology, a scene simulation module and a construction prediction module are built in the twinning model, and a coupling feedback mechanism of the scene simulation module and the construction prediction module is built; based on a coupling feedback mechanism, obtaining a construction quality prediction result in a simulation scene, determining a quality deviation value according to the construction quality prediction result and a construction quality target, taking the quality deviation value as an optimization target to carry out time sequence accumulation optimization adjustment on a construction strategy, and utilizing the construction optimization strategy to carry out construction management. The technical problems that in the prior art, the quality of highway construction cannot be accurately predicted, management is inaccurate, the construction quality is difficult to control, and the efficiency is low are solved. The technical effects of improving the accuracy and reliability of highway construction management and improving the construction quality and efficiency are achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of engineering construction management processing, and in particular to a construction management optimization method and system based on digital twin technology. Background Art

[0002] In highway construction, the control and management of construction quality is always a key issue. However, existing construction management methods often rely on prior planning and manual experience, and lack the ability to accurately predict and adjust dynamic changes in the construction process in real time. Especially in the face of emergencies or rapid changes in environmental conditions, traditional management methods cannot provide timely and accurate response plans, resulting in difficulty in controlling construction quality. The lack of accurate prediction of construction quality in the management process further affects construction efficiency and quality control.

[0003] The existing technology cannot accurately predict the quality of highway construction and is not managed precisely, resulting in technical problems such as difficulty in controlling construction quality and low efficiency. Summary of the invention

[0004] This application provides a construction management optimization method and system based on digital twin technology, which is used to solve the technical problems in the prior art that the quality of highway construction cannot be accurately predicted and the management is imprecise, resulting in difficulty in controlling construction quality and low efficiency.

[0005] In view of the above problems, the present application provides a construction management optimization method and system based on digital twin technology.

[0006] The first aspect of the present application provides a construction management optimization method based on digital twin technology, the method comprising: constructing a twin model through digital twin technology based on the geographical distribution of the construction project and Internet of Things sensor data, the twin model being used to simulate the on-site data of the construction project; constructing a scene simulation module and a construction prediction module, the scene simulation module simulates the construction environment according to environmental parameters and geographical data, and the construction prediction module predicts the construction quality according to the construction strategy; embedding the scene simulation module and the construction prediction module into the twin model, and establishing a coupling feedback mechanism of the scene simulation module and the construction prediction module; based on the coupling feedback mechanism, obtaining the construction quality prediction result of the construction prediction module under the simulation scenario of the scene simulation module; determining the quality deviation amount according to the construction quality prediction result and the construction quality target, performing time-series cumulative optimization adjustment on the construction strategy with the quality deviation amount as the optimization target, obtaining a construction optimization strategy, and using the construction optimization strategy to perform construction management.

[0007] The second aspect of the present application provides a construction management optimization system based on digital twin technology, the system comprising: a twin model building component, the twin model building component is used to build a twin model through digital twin technology based on the geographical distribution of the construction project and the Internet of Things sensor data, the twin model is used to simulate the on-site data of the construction project; a module building component, the module building component is used to build a scene simulation module and a construction prediction module, the scene simulation module simulates the construction environment according to environmental parameters and geographical data, and the construction prediction module predicts the construction quality according to the construction strategy; a feedback mechanism establishment component, the feedback mechanism establishment component is used to send the scene The scene simulation module and the construction prediction module are built into the twin model, and a coupling feedback mechanism of the scene simulation module and the construction prediction module is established; a prediction result acquisition component is used to obtain the construction quality prediction result of the construction prediction module under the simulation scenario of the scene simulation module based on the coupling feedback mechanism; an optimization strategy acquisition component is used to determine the quality deviation amount according to the construction quality prediction result and the construction quality target, and perform time-series cumulative optimization adjustment on the construction strategy with the quality deviation amount as the optimization target to obtain the construction optimization strategy, and use the construction optimization strategy to manage construction.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The method provided in the embodiment of the present application is based on the geographical distribution of the construction project and the sensor data of the Internet of Things, and a twin model is constructed through the digital twin technology. The twin model is used to simulate the on-site data of the construction project; a scene simulation module and a construction prediction module are constructed, and the scene simulation module simulates the construction environment according to the environmental parameters and geographical data, and the construction prediction module predicts the construction quality according to the construction strategy; the scene simulation module and the construction prediction module are built into the twin model, and a coupling feedback mechanism of the scene simulation module and the construction prediction module is established; based on the coupling feedback mechanism, the construction quality prediction result of the construction prediction module under the simulation scenario of the scene simulation module is obtained; the quality deviation amount is determined according to the construction quality prediction result and the construction quality target, and the construction strategy is optimized and adjusted in time series accumulation with the quality deviation amount as the optimization target, and the construction optimization strategy is obtained, and the construction optimization strategy is used for construction management. The technical effect of simulating the highway construction scene in real time, predicting the construction quality, and adjusting the highway construction strategy through feedback and optimization, improving the accuracy and reliability of highway construction management, and improving the construction quality and efficiency is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flowchart of the construction management optimization method based on digital twin technology provided for this application;

[0012] Figure 2 A structural diagram of the construction management optimization system based on digital twin technology provided for this application.

[0013] Explanation of the accompanying drawings: twin model building component 11, module building component 12, feedback mechanism establishment component 13, prediction result acquisition component 14, optimization strategy acquisition component 15. DETAILED DESCRIPTION

[0014] This application provides a construction management optimization method and system based on digital twin technology, which is used to solve the technical problems in the prior art that the quality of highway construction cannot be accurately predicted and the management is imprecise, resulting in difficult to control construction quality and low efficiency. It achieves the technical effect of real-time simulation of highway construction scenes, prediction of construction quality, and adjustment of highway construction strategies through feedback and optimization, improving the accuracy and reliability of highway construction management, and improving construction quality and efficiency.

[0015] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a construction management optimization method based on digital twin technology, the method comprising:

[0017] Based on the geographical distribution of construction projects and IoT sensor data, a twin model is constructed through digital twin technology, and the twin model is used to simulate the on-site data of the construction projects.

[0018] Specifically, first, the geographical distribution of the construction project is obtained, which refers to the geographical location, topography and surrounding environment of the construction project in the physical space. For example, the precise geographical location of the highway construction project is obtained by using geographic information system technology, and the topography and surrounding environment of the highway construction project area are collected through topographic maps, satellite images, drone aerial photography and other means, which can help analyze the construction difficulty, environmental impact and potential natural disaster risks of the project. At the same time, the IoT sensor data of the construction project is obtained. The IoT sensor data is data information collected by the sensor network deployed at the highway construction site, including various real-time data collected at the highway construction project site, such as temperature, humidity, vibration, pressure, displacement data, etc. Then, the geographical distribution data such as the geographical location and environmental characteristics of the construction project are integrated, and the real-time data from the IoT sensors, such as temperature, humidity, vibration, pressure, displacement data, etc., are synchronously accessed, and the twin model is constructed using the digital twin technology. The twin model is used to simulate the construction site data of the current highway construction project through real-time data analysis. Digital twin technology is an innovative means based on digital technology. It creates a corresponding virtual image, namely a digital twin, by comprehensively digitally modeling the physical entity or system in the real world. The digital twin not only contains the basic properties of the physical entity such as geometry, structure, and material, but also can synchronize the dynamic information of the physical entity such as the operating status and environmental parameters in real time, thus realizing comprehensive monitoring, simulation, prediction and optimization of the physical entity.

[0019] A scene simulation module and a construction prediction module are constructed. The scene simulation module simulates the construction environment according to environmental parameters and geographic data, and the construction prediction module predicts the construction quality according to the construction strategy.

[0020] Specifically, a scenario simulation module is constructed based on the environmental parameters and geographic data information of the highway construction scenario. Through the scenario simulation module, a comprehensive simulation of the construction environment can be achieved, thereby predicting the construction situation under different environmental conditions. The construction prediction module can predict the construction quality according to different construction strategies, such as the selection of highway construction materials, the application of construction methods, and the arrangement of construction time. By combining the scenario simulation module and the construction prediction module, dynamic adjustments to construction management can be made, and the information feedback from simulation and prediction can be responded to in a timely manner to optimize the construction plan.

[0021] Furthermore, the construction of the scene simulation module includes: setting an environmental parameter acquisition module, a geographic data acquisition module, and a scene parameter fusion module. The environmental parameter acquisition module is used to connect to the weather acquisition channel to obtain real-time weather data and weather forecast data. The geographic data acquisition module is used to connect to the geological model and the hydrological model to obtain geological data and hydrological change data. The scene parameter fusion module is used to fuse the environmental parameters of the environmental parameter acquisition module and the geographic data acquisition module with the geographic data to generate scene simulation parameters; and use the scene simulation parameters to simulate multiple construction scenarios.

[0022] Specifically, to construct a scenario simulation module, first set up an environmental parameter acquisition module and a geographic data acquisition module. The environmental parameter acquisition module obtains weather data and weather forecast information of the construction environment of the highway construction project by connecting to the weather acquisition channel. The weather acquisition channel refers to a system for collecting, processing and transmitting weather data. It relies on a variety of sensors, radars, satellites and other observation equipment to monitor and record various parameters in the atmosphere in real time, such as temperature, humidity, air pressure, wind speed, wind direction, precipitation, etc., and can provide accurate and timely weather data. The geographic data acquisition module is connected with the geological model and the hydrological model to obtain the geological structure and hydrological change data of the construction site respectively. The geological model is a three-dimensional quantitative random model, which is based on geological, well logging, geophysical data and various interpretation results or conceptual models for comprehensive analysis. It is mainly used to describe the geometric shape of underground rock formations, stratum contact relationships, lithology distribution, structural characteristics and reservoir properties (such as porosity, permeability, etc.). The hydrological model is an approximate simulation technology for natural hydrological phenomena. It uses mathematical physics methods or conceptual models to describe the relationship between various physical quantities in the hydrological system, and can describe the occurrence and development process of hydrological phenomena (such as floods, droughts, water resources distribution, etc.). The scene parameter fusion module fuses the environmental parameters obtained by the environmental parameter acquisition module and the geographic data acquisition module with the geographic data to generate scene simulation parameters. Then, using these scene simulation parameters, multiple possible highway construction scenes can be simulated to achieve a comprehensive simulation of the construction environment, thereby predicting the construction situation under different environmental conditions.

[0023] Furthermore, the construction prediction module comprises: collecting historical project data with the construction conditions and construction quality objectives of the construction project as search conditions; screening key environmental parameters according to the requirements of the construction project, the key environmental parameters being environmental parameters whose influence on construction quality exceeds a preset threshold; setting screening coverage constraints with the key environmental parameters and their influence; screening the historical project data using the screening coverage constraints to obtain a project sample set; configuring positive and negative sample setting conditions and setting the positive and negative sample ratios, extracting the project sample set, and constructing a model training data set; performing neural model training convergence through the model training data set to obtain a construction quality prediction model, and constructing the construction prediction module based on the construction quality prediction model.

[0024] Specifically, in the process of building the construction prediction module, the construction conditions and construction quality goals of the highway construction project are first used as search guides, and relevant historical project data are widely searched and collected. The historical project data provides empirical information on the impact of various factors on quality during highway construction, including environmental parameter data, construction process data, material data, project management data, etc. Then, according to the specific requirements of the construction project, the key environmental parameters that affect the construction quality exceeding the preset threshold are screened out. The key environmental parameters are important factors that directly determine the construction results. The preset threshold means that the environmental parameters will only be considered as key factors when the degree of influence reaches or exceeds the preset value. For example, when the humidity exceeds a certain range, it may significantly affect the strength of concrete, setting time, quality of asphalt paving, etc., and is therefore regarded as a key environmental parameter. The preset threshold can be set according to actual needs and expert experience. In order to make better use of key environmental parameter data, historical project data is further screened by setting screening coverage constraints to obtain a representative project sample set. The screening coverage constraints refer to a series of rules or conditions set when screening historical project data to ensure that the selected data samples can fully cover and represent the different value ranges and impact levels of key environmental parameters, such as the value range of key environmental parameters, coverage requirements, sample balance, etc.

[0025] Next, the evaluation criteria for construction quality are clarified. The quality criteria include specific technical indicators, acceptance criteria, qualified rate, etc. According to the quality criteria, the project sample set is divided into positive and negative examples. The positive sample refers to the highway construction sample with qualified quality, and the negative sample refers to the highway construction sample with unqualified quality or defects. For samples close to the boundary between qualified and unqualified, certain boundary conditions or thresholds can be set. For example, a sample within an allowable error range can be regarded as a positive or negative sample. The positive and negative sample setting conditions can be set according to the qualified rate of the actual project. For example, the qualified rate of 80% is used as a positive sample, and the qualified rate of less than 50% is used as a negative sample. For the positive and negative sample ratio, the positive sample: negative sample ratio can be set to 3:2 or 1:1 according to actual needs. When setting the ratio, it is necessary to ensure that the positive and negative sample ratios are balanced to ensure that the model can fully learn the factors affecting construction quality under different circumstances during training. Random sampling or stratified sampling methods are used to extract samples from the screened project sample set to construct a model training data set. Finally, the neural model is trained through the model training data set until the model converges, thereby obtaining a model that can accurately predict the construction quality. Based on the construction quality prediction model, the construction prediction module is constructed. The construction prediction module can accurately predict the quality of highway construction through the screening of historical data and environmental parameters and model training, thereby guiding the subsequent highway construction management and strategy optimization.

[0026] The scenario simulation module and the construction prediction module are built into the twin model, and a coupling feedback mechanism of the scenario simulation module and the construction prediction module is established.

[0027] Specifically, the scenario simulation module and the construction prediction module are built into the twin model, and a coupled feedback mechanism that interacts in time and space dimensions is established through data sharing and parameter interaction. The scenario simulation module generates various possible construction conditions and environmental changes by simulating dynamic highway construction scenes, and the construction prediction module uses these dynamic scene data to make real-time highway construction quality predictions and analyze possible construction quality problems in the current scene. Under the coupled feedback mechanism, a close interactive relationship is established between the simulation and prediction modules. Specifically, the coupled feedback mechanism ensures that the construction prediction module can use the construction environment simulation parameters output by the scenario simulation module in real time to make accurate construction quality predictions. This prediction result not only provides guidance for the current construction strategy, but also is fed back to the scenario simulation module for adjusting and optimizing the simulation parameters. For example, if the prediction result shows that there is a potential risk in the construction quality under a certain environmental condition, the scenario simulation module will adjust the simulation parameters based on this feedback information to make it closer to the real construction environment, thereby simulating the actual construction conditions more accurately. Moreover, as time goes by, simulation and prediction are continuously iterated; it is also reflected in the spatial dimension, and fine adjustments can be made for different construction areas and different environmental conditions. Through continuous feedback of coupled simulation results, dynamic optimization of simulation and prediction is achieved, so that the entire twin model can more accurately reflect and predict the actual situation during the construction process. Through the coupled feedback mechanism, construction strategies can be quickly adjusted and optimized in complex and changing construction environments, thereby effectively reducing quality risks, improving the accuracy and real-time nature of construction management, and providing accurate and reliable data support and decision-making basis for construction management.

[0028] Based on the coupling feedback mechanism, the construction quality prediction result of the construction prediction module in the simulation scenario of the scenario simulation module is obtained.

[0029] Furthermore, based on the coupling feedback mechanism, the construction quality prediction result of the construction prediction module under the simulation scenario of the scene simulation module is obtained, including: establishing a coupling feedback mechanism between the scene simulation module and the construction prediction module, wherein the output of the scene simulation module is used as the input of the construction prediction module, and the output of the construction prediction module is used as cumulative feedback to the scene simulation module, and the scene simulation module continuously performs simulation output and couples with the cumulative feedback as the input of the construction prediction module; establishing a timing feedback loop, which is a mechanism for recording and tracking prediction results at time nodes, utilizing the cumulative feedback to correspond to the timing feedback loop in time sequence, and outputting the construction quality prediction result of the prediction timing node through the timing feedback loop according to the prediction timing node of the construction prediction module.

[0030] Specifically, first, a coupling feedback mechanism is constructed between the scene simulation module and the construction prediction module, that is, the simulation scene data generated by the scene simulation module is used as the input of the construction prediction module, and the construction prediction module predicts the construction quality according to the input and outputs the prediction result. The prediction result is not only used for the current construction decision, but also returned to the scene simulation module as cumulative feedback to adjust the simulation parameters to more accurately simulate the actual construction conditions. The cumulative feedback is to compare and analyze the construction prediction results of the previous time series node with the actual situation, identify deviations or potential risks, and accumulate adjustment information. The analysis results are fed back to the scene simulation module, and the scene simulation module adjusts the simulation output based on these feedback information to make it closer to the actual highway construction situation, thereby optimizing the construction prediction for the next stage.

[0031] A timing feedback loop is established, which is used to record and track the construction quality prediction results of each time node. At each timing node (such as a key time point of construction), a construction quality prediction result will be generated, and the prediction result will be recorded in detail and compared with the actual construction situation to generate cumulative feedback information. The cumulative feedback information is combined with the prediction result of the current time node to adjust and optimize the prediction input of the next timing node. The timing feedback loop integrates these cumulative feedback information into the prediction process of the next timing node, so that each prediction can learn and improve from previous experience and gradually improve the prediction accuracy. In this way, the prediction output of each time node is not only used for immediate construction decision-making, but also accumulated and integrated into the feedback mechanism, and the construction quality prediction result of the predicted timing node is output through the timing feedback loop. Through this cyclic feedback mechanism, the construction quality prediction result accuracy and construction quality management level of the construction prediction module can be continuously improved under the simulation scenario of the scenario simulation module.

[0032] The quality deviation is determined according to the construction quality prediction result and the construction quality target, and the construction strategy is adjusted for time-series cumulative optimization with the quality deviation as the optimization target to obtain the construction optimization strategy, which is used for construction management.

[0033] Specifically, the construction quality prediction result of the construction prediction module under the simulation scenario is obtained, and then the construction quality prediction result is compared with the construction quality target to obtain the quality deviation between the construction quality prediction result and the construction quality target. The quality deviation refers to the gap between the predicted construction quality and the predetermined construction target, which is used to measure the effectiveness of the current construction strategy in achieving the target quality. After determining the quality deviation, the quality deviation is used as the optimization target, and the existing construction strategy is gradually adjusted and optimized by time series accumulation. The time series accumulation optimization adjustment not only considers the quality deviation of the current node, but also integrates the deviation information of the previous nodes to gradually reduce the cumulative deviation in the entire construction process. Through the optimization process, a construction optimization strategy is generated. After repeated adjustment and optimization, the optimization strategy can minimize the quality deviation in the construction process. Then, the construction optimization strategy is used to carry out actual highway construction management, which can not only effectively reduce the quality problems in highway construction, but also improve the efficiency and management level of the construction process, ensure that the highway construction project can achieve the established quality goals as planned, and improve the accuracy and reliability of highway construction management.

[0034] Furthermore, the screening coverage constraint condition is set based on the key environmental parameter and its influence, including: obtaining the value range of the key environmental parameter; segmenting the value range, wherein the number of segment segments corresponds to the influence fluctuation range of the key environmental parameter; and setting the coverage constraint condition of each key environmental parameter based on the segment segmentation: Where n is the number of segment divisions, X i,min is the key environmental parameter X i The minimum value of the range, X i,max is the key environmental parameter X i The maximum value of the value range, k is the interval index, the value range of k is 1 to n, and k is adjusted to select the coverage constraints of different intervals; according to the influence of the key environmental parameters, the sample coverage rate of the key environmental parameters is determined; according to the sample coverage rate of each key environmental parameter, the coverage constraints of each key environmental parameter are combined to set the screening coverage constraints.

[0035] Specifically, first, the value range of each key environmental parameter is obtained. The key environmental parameter refers to the environmental variables that have a significant impact on the quality of highway construction and have been preset as screening targets, such as temperature, humidity, wind speed, etc. The value range of the key parameter includes the lowest value to the highest value. Then, according to the impact fluctuation range of the key environmental parameter, the value range of the key parameter is segmented, that is, the number of value range segmentations corresponds to the impact fluctuation range of the key environmental parameter. The impact fluctuation range refers to the sensitivity and response degree of highway construction quality to the changes in these parameters within different parameter value ranges. Segment segmentation can ensure that samples are evenly extracted within each impact interval.

[0036] For each segment, set its coverage constraint, that is, for each key environmental parameter X i , the coverage of the segment is expressed as: Where ΔX i Represents the length of each segment, and the calculation formula is n is the number of segment divisions, m is the number of predefined segments, X i,min is the key environmental parameter X i The minimum value of the range, X i,max is the key environmental parameter X i The maximum value of the value range, k is the interval index, the value range of k is 1 to n, and k is adjusted to select the coverage constraints of different intervals.

[0037] According to the influence of each key environmental parameter, the influence is the degree of influence of each key environmental parameter on the quality of highway construction, and the coverage rate of the parameter in the sample set is determined. The sample coverage rate refers to the proportion of each key parameter section in the sample set that should be represented by the sample to ensure that the change of the parameter can be fully considered under different environmental conditions. For example, in a highway construction project, one of the key environmental parameters is temperature, and the temperature range is between 10℃ and 40℃. By analyzing historical data, it is found that the influence of temperature on construction quality presents the following characteristics: 10℃ to 20℃: the construction quality is good, because the material performance within this temperature range is relatively stable; 20℃ to 30℃: the construction quality is relatively stable, but may be affected by material expansion; 30℃ to 40℃: the construction quality is poor, because high temperature may cause softening of asphalt mixture and evaporation of water, affecting the construction effect. In order to ensure the representativeness of temperature in the sample set, the coverage rate can be set as follows: 10℃ to 20℃: the sample coverage rate is 30%, because the construction quality within this range is good, but it is necessary to ensure sufficient samples for verification. 20℃ to 30℃: The sample coverage rate is 40%. This range is the most common construction temperature, so more samples are needed to reflect normal construction conditions. 30℃ to 40℃: The sample coverage rate is 30%. There are many construction quality problems under high temperature, which need to be focused on and ensure sufficient samples for analysis. Finally, according to the sample coverage rate of each key environmental parameter, the coverage constraints of each key environmental parameter are integrated to form the final screening coverage constraint. The coverage constraint is the requirement for the minimum number of samples that each parameter in the sample set should have in each section, ensuring that the value sections of each key parameter are fully represented in the sample set. The screening coverage constraint ensures that the sample set selected from the historical project data not only covers all important sections of each single parameter, but also comprehensively considers the coverage requirements under the interaction of multiple parameters. Through the combination, it is ensured that the selected project samples can comprehensively and evenly cover the value ranges of all key parameters, so that the sample set has good representativeness and balance, providing comprehensive data support for subsequent model training and construction quality prediction, thereby improving the accuracy and reliability of prediction.

[0038] Furthermore, the construction strategy is subjected to time-series cumulative optimization adjustment with the quality deviation as the optimization target to obtain the construction optimization strategy, including: constructing a time-series prediction model, the time-series prediction model is used to perform time-series prediction on the construction strategy; taking the minimum quality deviation as the optimization target, constructing an objective function, fitting the cumulative time-series prediction results of the time-series prediction model into the objective function as the evaluation value, and constructing a strategy optimization space; taking the construction strategy as the search center, determining the search direction with the quality deviation, performing time-series optimization through the strategy optimization space according to the corresponding time-series relationship of the quality deviation, outputting the construction strategy with the minimum time-series cumulative deviation, and obtaining the construction optimization strategy.

[0039] Specifically, an appropriate time series prediction algorithm is selected, such as ARIMA, LSTM, etc., and the historical construction strategy data is used as input variables to train the time series prediction model so that it can learn the patterns and trends in the time series. After the training is completed, the final time series prediction model is obtained. The time series prediction model can predict the construction effects at various time nodes in the future based on the construction strategy of highway construction.

[0040] Then, since the quality deviation needs to be reduced as much as possible during the entire construction process, the minimum quality deviation is taken as the optimization goal, and the objective function is constructed. The objective function integrates the cumulative time series prediction results of the time series prediction model as the evaluation value, so as to accurately reflect the quality performance under different construction strategies and provide the optimization direction. A strategy optimization space is constructed, which contains all possible combinations of highway construction strategies and provides a basis for subsequent optimization search. The construction strategy is used as the search starting center, and the search direction is determined by analyzing the size and direction of the quality deviation. That is, the search direction is determined by the deviation of the current construction strategy and points to the direction of reducing the deviation, ensuring that the search process can be carried out in a targeted manner in the direction of reducing the quality deviation. According to the time series relationship of the quality deviation, time series optimization is performed in the strategy optimization space, considering the construction strategy adjustments at different time points and their cumulative effects, and constantly adjusting the strategy to find a strategy combination that can minimize the cumulative quality deviation of the entire construction process. Finally, through careful search and optimization, the construction strategy with the smallest cumulative deviation in time series is output, namely the construction optimization strategy. The construction optimization strategy is optimized and adjusted at multiple time nodes, and can maintain the minimum value of quality deviation in the entire construction process, thereby improving the accuracy of the construction strategy, ensuring that the construction quality is close to or reaches the expected goal, reducing the quality risk in actual highway construction, and thus improving the accuracy and reliability of the entire construction management.

[0041] Furthermore, the objective function expression is: Among them, J(θ) is the objective function, which represents the target value of the policy parameter θ, w k is the weight factor for each time point t+k, Q pred (t+k) is the cumulative time series prediction result, Q target (t+k) is the target quality value at time t+k, k is the time step index, K is the total time step and the time length corresponding to the corresponding time series relationship; Q pred (t+k)=f(X(t),X(t-1),……,X(tn)), where X(t) is the input data, t is the current time series node, k is the prediction step, and f(·) is the time series prediction model.

[0042] Specifically, the minimum mass deviation is taken as the optimization goal, and an objective function is constructed. The expression of the objective function is: Among them, J(θ) is the objective function, which represents the target value of the strategy parameter θ. By minimizing the value of this function, the optimal strategy parameter can be found to minimize the deviation between the construction quality prediction result and the target quality value. k The weight factor is the weight factor of each time point t+k. By adjusting the weight factor, the influence of certain time nodes can be highlighted or weakened. The setting of the weight factor can be based on the importance of each time node in the actual construction process. pred (t+k) is the cumulative time series prediction result, Q target (t+k) is the target quality value at time t+k, representing the quality standard or target expected to be achieved at that time point, k is the time step index, K is the total time step and the time length of the corresponding time series relationship, which determines the future time range that the model needs to predict. pred (t+k)=f(X(t),X(t-1),……,X(tn)), where X(t) is the input data, t is the current time series node, k is the prediction step, and f(·) is the time series prediction model, which can capture the time series dependencies in the data and make future quality predictions based on them.

[0043] Through the guidance of the objective function, the quality performance of different construction strategies can be evaluated. At the same time, the introduction of the time series prediction model enables the optimization process to take into account the quality impact at multiple time points in the future. Ultimately, the optimal construction strategy obtained through strategy optimization can significantly reduce the quality deviation during the construction process and improve the overall construction quality and efficiency.

[0044] Embodiment 2 is based on the same inventive concept as the construction management optimization method based on digital twin technology in the previous embodiment. Figure 2 As shown, the present application provides a construction management optimization system based on digital twin technology, wherein the system includes:

[0045] A twin model building component 11, wherein the twin model building component 11 is used to build a twin model through digital twin technology based on the geographical distribution of the construction project and IoT sensor data, and the twin model is used to simulate the on-site data of the construction project;

[0046] A module construction component 12, wherein the module construction component 12 is used to construct a scene simulation module and a construction prediction module. The scene simulation module simulates the construction environment according to environmental parameters and geographic data, and the construction prediction module predicts the construction quality according to the construction strategy;

[0047] A feedback mechanism establishment component 13, wherein the feedback mechanism establishment component 13 is used to embed the scenario simulation module and the construction prediction module into the twin model, and establish a coupling feedback mechanism of the scenario simulation module and the construction prediction module;

[0048] A prediction result obtaining component 14, wherein the prediction result obtaining component 14 is used to obtain the construction quality prediction result of the construction prediction module under the simulation scenario of the scenario simulation module based on the coupling feedback mechanism;

[0049] The optimization strategy acquisition component 15 is used to determine the quality deviation amount according to the construction quality prediction result and the construction quality target, perform time-series cumulative optimization adjustment on the construction strategy with the quality deviation amount as the optimization target, obtain the construction optimization strategy, and use the construction optimization strategy to perform construction management.

[0050] Furthermore, the module construction component 12 is used to perform the following steps: setting an environmental parameter acquisition module, a geographic data acquisition module, and a scene parameter fusion module, the environmental parameter acquisition module is used to connect to the weather acquisition channel to obtain real-time weather data and weather forecast data, the geographic data acquisition module is used to connect to the geological model and the hydrological model to obtain geological data and hydrological change data, the scene parameter fusion module is used to fuse the environmental parameters of the environmental parameter acquisition module and the geographic data acquisition module with the geographic data to generate scene simulation parameters; and use the scene simulation parameters to simulate multiple construction scenes.

[0051] Furthermore, the module construction component 12 is also used to perform the following steps: collecting historical project data based on the construction conditions and construction quality goals of the construction project as search conditions; screening key environmental parameters according to the requirements of the construction project, the key environmental parameters being environmental parameters whose impact on construction quality exceeds a preset threshold; setting screening coverage constraints based on the key environmental parameters and their impact; using the screening coverage constraints to screen the historical project data to obtain a project sample set; configuring positive and negative sample setting conditions and setting the positive and negative sample ratios, extracting the project sample set, and constructing a model training data set; performing neural model training convergence through the model training data set to obtain a construction quality prediction model, and constructing the construction prediction module based on the construction quality prediction model.

[0052] Furthermore, the module construction component 12 is also used to perform the following steps: obtaining the value range of the key environmental parameter; segmenting the value range, wherein the number of segment segments corresponds to the impact fluctuation range of the key environmental parameter; and setting the coverage constraint condition of each key environmental parameter based on the segment segmentation: Where n is the number of segment divisions, X i,min is the key environmental parameter X i The minimum value of the range, X i,max is the key environmental parameter X i The maximum value of the value range, k is the interval index, the value range of k is 1 to n, and k is adjusted to select the coverage constraints of different intervals; according to the influence of the key environmental parameters, the sample coverage rate of the key environmental parameters is determined; according to the sample coverage rate of each key environmental parameter, the coverage constraints of each key environmental parameter are combined to set the screening coverage constraints.

[0053] Furthermore, the prediction result acquisition component 14 is used to perform the following steps: establishing a coupling feedback mechanism between the scenario simulation module and the construction prediction module, wherein the output of the scenario simulation module is used as the input of the construction prediction module, and the output of the construction prediction module is used as cumulative feedback to the scenario simulation module, and the scenario simulation module continuously performs simulation output and is coupled with the cumulative feedback as the input of the construction prediction module; establishing a timing feedback loop, which is a mechanism for recording and tracking prediction results at time nodes, using the cumulative feedback to correspond to the timing feedback loop in time, and outputting the construction quality prediction result of the prediction timing node through the timing feedback loop according to the prediction timing node of the construction prediction module.

[0054] Furthermore, the optimization strategy acquisition component 15 is used to perform the following steps: construct a timing prediction model, which is used to perform timing prediction on the construction strategy; take the minimum quality deviation as the optimization goal, construct an objective function, fit the cumulative timing prediction results of the timing prediction model into the objective function as the evaluation value, and construct a strategy optimization space; take the construction strategy as the search center, determine the search direction based on the quality deviation, perform timing optimization through the strategy optimization space according to the corresponding timing relationship of the quality deviation, output the construction strategy with the minimum cumulative timing deviation, and obtain the construction optimization strategy.

[0055] Furthermore, the optimization strategy obtaining component 15 is also used to perform the following steps: The objective function expression is: Among them, J(θ) is the objective function, which represents the target value of the policy parameter θ, w k is the weight factor for each time point t+k, Q pred (t+k) is the cumulative time series prediction result, Q target (t+k) is the target quality value at time t+k, k is the time step index, K is the total time step and the time length corresponding to the corresponding time series relationship; Q pred (t+k)=f(X(t),X(t-1),……,X(tn)), where X(t) is the input data, t is the current time series node, k is the prediction step, and f(·) is the time series prediction model.

[0056] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0057] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Construction management optimization method based on digital twin technology, characterized in that: The construction management optimization method based on digital twin technology includes: Based on the geographical distribution of construction projects and IoT sensor data, a twin model is constructed through digital twin technology, and the twin model is used to simulate the on-site data of the construction project; Constructing a scene simulation module and a construction prediction module. The scene simulation module simulates the construction environment according to environmental parameters and geographic data, and the construction prediction module predicts the construction quality according to the construction strategy; The scenario simulation module and the construction prediction module are built into the twin model, and a coupling feedback mechanism of the scenario simulation module and the construction prediction module is established; Based on the coupling feedback mechanism, obtaining the construction quality prediction result of the construction prediction module under the simulation scenario of the scenario simulation module; The quality deviation is determined according to the construction quality prediction result and the construction quality target, and the construction strategy is adjusted for time-series cumulative optimization with the quality deviation as the optimization target to obtain the construction optimization strategy, which is used for construction management.

2. The construction management optimization method based on digital twin technology according to claim 1, characterized in that: The construction scene simulation module comprises: An environmental parameter acquisition module, a geographic data acquisition module, and a scene parameter fusion module are set. The environmental parameter acquisition module is used to connect to the weather acquisition channel to obtain real-time weather data and weather forecast data. The geographic data acquisition module is used to connect to the geological model and the hydrological model to obtain geological data and hydrological change data. The scene parameter fusion module is used to fuse the environmental parameters of the environmental parameter acquisition module and the geographic data acquisition module with the geographic data to generate scene simulation parameters. The scenario simulation parameters are used to perform multiple construction scenario simulations.

3. The construction management optimization method based on digital twin technology according to claim 1, characterized in that: The construction prediction module is constructed, including: Collect historical project data using the construction conditions and construction quality objectives of the construction project as search conditions; Screening key environmental parameters according to the requirements of the construction project, wherein the key environmental parameters are environmental parameters whose impact on construction quality exceeds a preset threshold; Setting screening coverage constraints based on the key environmental parameters and their influence; Filtering the historical project data using the screening coverage constraint condition to obtain a project sample set; Configure the positive and negative sample setting conditions and set the positive and negative sample ratios, extract the project sample set, and build a model training data set; The neural model training is converged through the model training data set to obtain a construction quality prediction model, and the construction prediction module is constructed based on the construction quality prediction model.

4. The construction management optimization method based on digital twin technology as claimed in claim 3 is characterized in that: Based on the key environmental parameters and their influence, set the screening coverage constraints, including: Obtaining the value range of the key environmental parameter; The value range is segmented, wherein the number of segment divisions corresponds to the impact fluctuation range of the key environmental parameters; The coverage constraints of each key environmental parameter are set based on the segment segmentation: X i ∈ Where n is the number of segment divisions, X i,min is the key environmental parameter X i The minimum value of the range, X i,max is the key environmental parameter X i The maximum value of the range, k is the interval index, k ranges from 1 to n, and k is adjusted to select the coverage constraints of different intervals; Determine the sample coverage of the key environmental parameters according to the influence of the key environmental parameters; The coverage constraint condition of each key environmental parameter is combined according to the sample coverage rate of each key environmental parameter to set the screening coverage constraint condition.

5. The construction management optimization method based on digital twin technology according to claim 1, characterized in that: Based on the coupling feedback mechanism, the construction quality prediction result of the construction prediction module in the simulation scenario of the scenario simulation module is obtained, including: A coupling feedback mechanism is established between the scenario simulation module and the construction prediction module, wherein the output of the scenario simulation module is used as the input of the construction prediction module, and the output of the construction prediction module is used as cumulative feedback to the scenario simulation module, and the scenario simulation module continuously performs simulation output and is coupled with the cumulative feedback as the input of the construction prediction module; A timing feedback loop is established, which is a mechanism for recording and tracking prediction results at time nodes. The cumulative feedback is used to correspond to the timing feedback loop in time, and the construction quality prediction results of the predicted timing nodes are output through the timing feedback loop according to the predicted timing nodes of the construction prediction module.

6. The construction management optimization method based on digital twin technology according to claim 1, characterized in that: Taking the quality deviation as the optimization target, the construction strategy is adjusted by time-series cumulative optimization to obtain a construction optimization strategy, including: Constructing a time series prediction model, wherein the time series prediction model is used to perform time series prediction on the construction strategy; Taking the minimum quality deviation as the optimization goal, constructing an objective function, taking the cumulative time series prediction results of the time series prediction model as the evaluation value to fit into the objective function, and constructing a strategy optimization space; The construction strategy is used as the search center, the quality deviation is used to determine the search direction, and according to the corresponding time series relationship of the quality deviation, time series optimization is performed through the strategy optimization space, and the construction strategy with the smallest time series cumulative deviation is output to obtain the construction optimization strategy.

7. The construction management optimization method based on digital twin technology according to claim 6, characterized in that: The objective function expression is: Among them, J(θ) is the objective function, which represents the target value of the policy parameter θ, w k is the weight factor for each time point t+k, Q pred (t+k) is the cumulative time series prediction result, Q target (t+k) is the target quality value at time t+k, k is the time step index, K is the total time step and the time length corresponding to the corresponding time series relationship; Q pred (t+k)=f(X(t),X(t-1),……,X(tn)), where X(t) is the input data, t is the current time series node, k is the prediction step, and f(·) is the time series prediction model.

8. Construction management optimization system based on digital twin technology, characterized by: The steps for implementing the method according to any one of claims 1 to 7 include: A twin model building component, wherein the twin model building component is used to build a twin model through digital twin technology based on the geographical distribution of the construction project and IoT sensor data, and the twin model is used to simulate the on-site data of the construction project; A module construction component, wherein the module construction component is used to construct a scene simulation module and a construction prediction module. The scene simulation module simulates the construction environment according to environmental parameters and geographic data, and the construction prediction module predicts the construction quality according to the construction strategy; A feedback mechanism establishment component, wherein the feedback mechanism establishment component is used to embed the scenario simulation module and the construction prediction module into the twin model and establish a coupling feedback mechanism between the scenario simulation module and the construction prediction module; A prediction result obtaining component, the prediction result obtaining component is used to obtain the construction quality prediction result of the construction prediction module under the simulation scenario of the scenario simulation module based on the coupling feedback mechanism; An optimization strategy acquisition component is used to determine the quality deviation amount according to the construction quality prediction result and the construction quality target, perform time-series cumulative optimization adjustment on the construction strategy with the quality deviation amount as the optimization target, obtain the construction optimization strategy, and use the construction optimization strategy to perform construction management.

Citation Information

Cited By

  • Traceable road construction management and control system based on digital twinning

    CN120029119A

  • Self-compacting concrete construction quality control method, device and equipment based on machine learning

    CN120048406A

  • A machine learning-based method, apparatus, and equipment for quality control of self-compacting concrete construction.

    CN120048406B

  • Road traffic protection facility durability optimization method based on digital twinning

    CN120387313A

  • Power grid construction management and control method based on three-dimensional digital twinning

    CN120672294A