Steel structure construction duration prediction method and system based on digital twinning

Abstract

A steel structure construction period prediction method and system based on digital twinning, comprising the following steps: step 1, by real-time monitoring of the construction site and collecting data, comparing the actual construction situation with the digital model by using the digital twinning model, identifying the existing progress of the project, and real-time monitoring and analyzing the personnel and equipment distribution and work efficiency of the construction site through the sensor network and computer vision; step 2, based on the data of the existing progress and work efficiency of step 1, the optimal period scheme is found by iterative optimization of the period through optimization algorithm; step 3, based on the optimized period scheme, the steel structure construction period is predicted combined with digital twinning according to historical data and current construction conditions. The combination of digital twinning technology and construction period calculation can reflect the real-time state of the physical model of the project and its digital simulation in real time, realize the all-round monitoring and management of the construction process, and accurately predict the construction period of the project.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of building engineering management, and more specifically relates to a steel structure construction duration prediction method and system based on digital twinning. BACKGROUND

[0002] Traditional construction duration calculation methods have limitations to some extent, one of the most important problems is the accurate grasp of construction boundary conditions. Construction duration calculation usually relies on project plans and experience estimates, but these estimates are often affected by many factors, such as human error, unconsidered risk factors, etc., resulting in possible deviations in duration calculation results. In addition, traditional duration calculation formulas lack accuracy in actual construction conditions and cannot fully consider various changes and complexities in the construction process.

[0003] Traditional methods cannot reflect the actual situation of the construction site in real time, and lack precise monitoring of personnel and equipment distribution. Work efficiency evaluation is often based on manual observation and subjective judgment, making it difficult to objectively and accurately identify inefficient or abnormal behavior. Duration optimization and adjustment mainly rely on experience and static data, making it difficult to find the optimal solution in a complex and changing construction environment. In addition, traditional methods have deficiencies in combining historical data and current construction conditions, making it difficult to accurately predict the duration. Lack of effective risk warning mechanism, unable to timely discover and deal with potential problems and risks in the construction process.

[0004] These limitations are particularly prominent in the substation original site reconstruction project carried out by the power supply company. Accurate calculation of construction duration is crucial for the smooth progress of the project, and traditional methods are difficult to meet this demand.

[0005] The prior art document 1 (CN115809856A) discloses an engineering progress deduction method based on digital twinning and knowledge graph, which relates to a method of applying digital twinning technology to construction engineering construction progress management deduction, and specifically relates to an engineering progress deduction method based on digital twinning and knowledge graph. It realizes the following technical scheme: according to the actual engineering progress plan, the knowledge graph of engineering consumables, equipment, tasks, people, environment, weather logical data is established; the engineering total progress twinning digital model is established; the engineering total progress twinning digital model is set as each time node knowledge graph parameter input; the engineering total progress twinning digital model is mapped with the actual engineering construction progress, the time progress of the actual construction process is input into the time node input of the corresponding engineering total progress twinning digital model, and the engineering progress supervision is set; the lag time period of the construction period is input, and the abnormal factor A in the engineering progress is input; the engineering total progress twinning digital model calculates the actual construction progress according to the construction progress, when the actual engineering appears progress deviation, the engineering total progress twinning digital model adjusts the digital model according to the current lag time algorithm, adjusts the overall engineering progress, adjusts the construction progress again, and calculates a new construction schedule.

[0006] The prior art document 1 has the defects that it mainly depends on the static knowledge graph to establish the logical relationship of engineering parameters, and cannot fully realize the real-time response and adaptation to the dynamic changes of the construction site. In addition, when dealing with actual construction progress deviation, the adjustment mechanism is too simple, and lacks intelligent processing ability of comprehensive consideration of various construction factors; in terms of resource optimization allocation, the most efficient allocation strategy is not realized, resulting in that the resource utilization rate is not optimal. SUMMARY

[0007] In order to solve the problems in the prior art, the present application provides a steel structure construction period prediction method and system based on digital twinning.

[0008] In view of the limitations and problems of the traditional construction period calculation method, a more accurate and intelligent construction period calculation method is proposed by using digital twinning technology. Through this method, the problems of the traditional method in the accuracy of construction boundary conditions and the accuracy of construction period calculation formula are solved, so as to improve the safety management level and construction efficiency of the original site reconstruction project.

[0009] The present application adopts the following technical scheme.

[0010] The first aspect of the present application provides a steel structure construction period prediction method based on digital twinning, comprising the following steps:

[0011] Step 1, by monitoring the construction site and collecting data, using the digital twinning model to compare the actual construction situation with the digital model, and identifying the existing progress of the project;

[0012] Step 2, based on the existing progress obtained, monitor and analyze the personnel and equipment distribution and work efficiency of the construction site through sensor networks and computer vision;

[0013] Step 3, based on the existing progress of step 1 and the work efficiency data of step 2, iterative optimization of the construction period is carried out through algorithm to find the optimal construction period scheme;

[0014] Step 4, based on the optimized construction period scheme, predict the steel structure construction period combined with digital twin according to historical data and current construction conditions.

[0015] Preferably, step 1 specifically includes the following steps:

[0016] Step 1.1, configure sensors and monitoring devices, install cameras and RFID tags in all areas of the construction site; cameras are used for video monitoring, and RFID tags are used for tracking personnel and equipment;

[0017] Step 1.2, based on the sensors and monitoring devices configured in step 1.1, collect multi-dimensional data of the construction site, including personnel location, equipment status, and material usage;

[0018] Step 1.3, input the collected data into the digital twin model, compare the actual construction progress with the planned progress, and generate a progress comparison result.

[0019] Preferably, in step 1.3, the comparison of actual construction progress and planned progress includes:

[0020] Step 1.3.1, pre-process the collected data and transmit it to the central processing through the communication protocol; pre-processing includes data cleaning and data formatting; data formatting includes uniformly converting the data format to a standard format for processing data in the digital twin model;

[0021] Step 1.3.2, input the pre-processed real-time construction data into the digital twin model, and load and initialize the planned progress data in the digital twin model, ready for comparison;

[0022] Step 1.3.3, identify and record the location and status of each construction personnel and equipment, and match them with the location and status in the planned progress; compare the start and end times of actual and planned tasks to calculate the time deviation; calculate the task completion ratio by comparing the actual completed work with the planned work, and obtain the actual progress; according to the comparison result, update the planned progress data in the digital twin model in real time, synchronize the digital twin model with the actual construction situation.

[0023] Preferably, step 2 specifically includes the following steps:

[0024] Step 2.1, image processing of the construction site video through computer vision and RFID to identify the location of personnel and equipment on the construction site, detect their actions and operating status;

[0025] Step 2.2, analyze the actions and postures of personnel through pose estimation algorithms to determine their working status, including operating equipment, carrying materials, and resting; identify the working efficiency of personnel and equipment through behavior analysis to determine whether there are low-efficiency or abnormal behaviors;

[0026] Step 2.3, quantify the analysis results and display the analysis results through three-dimensional visualization to calculate the working efficiency of each type of work and equipment and identify factors affecting working efficiency;

[0027] Step 2.4, generate a working efficiency analysis report including the working status, efficiency data, and identification results of low-efficiency or abnormal behaviors of personnel and equipment.

[0028] Preferably, step 3 specifically includes the following steps:

[0029] Step 3.1, use the identified existing progress data and working conditions as the initial solution, represent the initial duration plan as individuals or particles, and each individual or particle represents a duration arrangement scheme, including the start and end times of each task and resource allocation;

[0030] Step 3.2, simulate natural selection, crossover, and mutation operations through genetic algorithms to gradually optimize the duration arrangement scheme;

[0031] Step 3.3, simulate group behavior through particle swarm optimization algorithms to optimize the duration arrangement and find the optimal or near-optimal solution;

[0032] Step 3.4, evaluate the pros and cons of each new solution based on duration, cost, and resource utilization rate comprehensive indicators;

[0033] Step 3.5, in each iteration, select the optimal solution based on the evaluation results and perform crossover and mutation operations to generate new candidate solutions;

[0034] Step 3.6, continue iteration until the preset stopping condition is met, and output the current optimal solution as the final duration arrangement scheme when the stopping condition is met.

[0035] Preferably, in step 3.2, the selection operation includes selecting individuals with better performance from the initial solution set, and preferentially retaining duration schemes with high fitness;

[0036] The crossover operation includes swapping part of the duration arrangement of the selected individuals to generate new duration schemes;

[0037] The mutation operation includes randomly mutating part of the individuals to change the start time of the task or resource allocation.

[0038] Preferably, step 4 specifically comprises the following steps:

[0039] Step 4.1, input the construction boundary conditions including the number of construction personnel, the number of mechanical equipment shifts, and weather factors;

[0040] Step 4.2, based on historical data and experience, establish a construction period calculation model;

[0041] Step 4.3, according to the input boundary conditions, automatically calculate the duration of the sub-item engineering construction period, arrange the daily construction volume, the location distribution and work content of the mechanical equipment and the operating personnel;

[0042] Step 4.4, apply the construction period calculation formula to calculate the expected construction period.

[0043] Preferably, step 4.2 specifically comprises:

[0044] According to historical data, under the condition of a certain number of cranes and construction personnel, estimate the construction period including hoisting and riveting and welding floor support plate laying;

[0045] Set the number of cranes in proportion to the hoisting efficiency, compared with 1 crane, for every additional 1 crane, estimate the hoisting efficiency improvement rate according to the set proportion;

[0046] Set the number of construction personnel in proportion to the riveting and welding floor support plate laying efficiency, estimate the efficiency improvement rate according to the number of personnel increase.

[0047] Preferably, in step 4.4, the construction period calculation formula is as follows:

[0048]

[0049] In the formula:

[0050] X represents the number of cranes;

[0051] Y represents the number of construction personnel;

[0052] Z represents the number of stoppage days;

[0053] D represents the construction period.

[0054] The second aspect of the present application provides a steel structure construction period prediction system based on digital twinning, comprising: a data acquisition and monitoring module, a digital twinning and progress identification module, a work efficiency analysis and evaluation module, and a construction period optimization and prediction module;

[0055] The data acquisition and monitoring module collects multi-dimensional data, including personnel location, equipment status, and material usage, by installing high-resolution cameras, RFID tags, and sensor networks on the construction site, providing basic data support for subsequent analysis and model comparison.

[0056] The digital twin and progress identification module compares actual construction data with planned progress using a digital twin model, adjusts model parameters through a real-time updating mechanism, generates progress comparison results, and identifies the existing progress of the project.

[0057] The work efficiency analysis and evaluation module monitors and analyzes the distribution and working status of personnel and equipment on the construction site in real time through computer vision and sensor networks, evaluates work efficiency, and identifies inefficient and abnormal behaviors.

[0058] The duration optimization and prediction module iteratively optimizes the duration based on existing progress and work efficiency data using genetic algorithms and particle swarm optimization algorithms, generates an optimal duration plan by evaluating duration, cost, and resource utilization indicators, and predicts the steel structure construction duration based on historical data and current construction conditions.

[0059] Compared with the prior art, the beneficial effects of the present application at least include:

[0060] (1) By using a digital twin model, actual construction data is compared with planned progress, effectively identifying the existing progress of the project, improving the accuracy and reliability of progress identification.

[0061] (2) By using pose estimation algorithms and behavior analysis, the work efficiency of construction personnel and equipment is identified, and inefficient or abnormal behaviors are discovered in a timely manner, improving overall work efficiency.

[0062] (3) Based on real-time monitoring data and optimization results, construction plans are dynamically adjusted, improving the flexibility and adaptability of construction management.

[0063] (4) By real-time monitoring and predictive analysis, potential problems and risks in construction are discovered in a timely manner, providing early warning information, saving construction costs, and ensuring the smooth progress of the project. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 is a construction duration prediction flowchart provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. The embodiments described in the present application are only a part of the embodiments of the present application, not all the embodiments. Based on the spirit of the present application, other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0066] In view of the limitations and problems of the traditional construction duration calculation method, a more accurate and intelligent construction duration calculation method is proposed using digital twinning technology. Through this method, the problems of traditional methods in terms of accuracy of construction boundary conditions and accuracy of duration calculation formula are solved, thereby improving the safety management level and construction efficiency of the original station reconstruction project.

[0067] Specifically, the system will use advanced sensor networks to collect real-time data on the construction site, including but not limited to soil conditions, weather conditions, equipment operating conditions, worker activities, etc. These data will be transmitted to the digital twinning system center through the network, and will be digitally modeled and synchronized with the actual site to realize real-time monitoring and simulation of the construction process.

[0068] The digital twinning system center will be equipped with high-performance computers and intelligent algorithms, using advanced machine learning and data mining techniques to analyze and process the large amount of data collected. By reviewing and comparing historical data, the system can identify regular changes and potential risk factors in the construction process, providing an accurate basis for duration calculation.

[0069] In terms of duration calculation, the system will use advanced mathematical modeling methods such as multiple regression analysis and neural network models to consider various factors in the construction process, thereby establishing a more accurate and detailed duration calculation model. These models will be able to fully consider various changes and uncertainties in the construction process, enabling intelligent prediction and optimization of the duration.

[0070] In addition, the digital twinning system will also be equipped with an intelligent decision support system that can automatically propose adjustments to the construction plan based on real-time monitoring data and duration calculation models, and assist project managers in making decisions. This set of digital twinning systems that integrates real-time monitoring, data analysis, duration calculation and decision support will provide a comprehensive intelligent construction management solution for the original station reconstruction project, improving the safety management level and construction efficiency of the project.

[0071] As Figure 1 shown, Example 1 of the present application provides a steel structure construction duration prediction method based on digital twinning, comprising the following steps:

[0072] Step 1, by monitoring the construction site and collecting data, comparing the actual construction situation with the digital model using the digital twin model, identifying the existing progress of the project;

[0073] First, through real-time monitoring and data collection of the construction site, the progress of the current construction project is identified. By using digital twin technology, more real-time data and monitoring indicators are introduced, and the actual construction situation is compared with the digital model, so as to accurately determine the current engineering progress state, and improve the accuracy and reliability of the construction period calculation model.

[0074] Preferably, step 1 specifically includes the following steps:

[0075] Step 1.1, configure sensors and monitoring devices, install high-resolution cameras and RFID tags in all areas on the construction site; cameras are used for video monitoring, and RFID tags are used for tracking personnel and equipment;

[0076] Step 1.2, based on the configured devices, collect multi-dimensional data of the construction site, including personnel location, equipment status, and material usage;

[0077] Step 1.3, input the collected data into the digital twin model, compare the actual construction progress with the planned progress, and generate a progress comparison result.

[0078] Preferably, in step 1.3, the comparison of actual construction progress and planned progress includes:

[0079] Step 1.3.1, pre-process the collected data and transmit it to the central processing through the communication protocol; the pre-processing includes data cleaning and data formatting; the data formatting includes uniformly converting the data format to a standard format for processing data in the digital twin model;

[0080] Step 1.3.2, input the pre-processed real-time construction data into the digital twin model, and load and initialize the planned progress data in the digital twin model, ready for comparison;

[0081] Step 1.3.3, identify and record the location and status of each construction personnel and equipment through sensor and RFID tag data, and match them with the location and status in the planned progress; compare the start and end times of actual and planned tasks to calculate the time deviation; calculate the task completion ratio by comparing the actual completed work with the planned work, and obtain the actual progress; according to the comparison result, real-time update the planned progress data in the digital twin model, synchronize the digital twin model with the actual construction situation.

[0082] Step 2, based on the obtained existing progress, monitor and analyze the personnel and equipment distribution and work efficiency of the construction site through sensor network and computer vision;

[0083] Preferably, step 2 specifically includes the following steps:

[0084] Step 2.1, through computer vision and RFID, image processing of the construction site video, identifying the location of construction site personnel and equipment, detecting their actions and operating status;

[0085] Step 2.2, through pose estimation algorithm to analyze the action and posture of personnel, judge their working state, including operating equipment, carrying materials and resting; through behavior analysis to identify the work efficiency of personnel and equipment, to judge whether there is low efficiency or abnormal behavior;

[0086] Step 2.3, quantifying the analysis results and displaying the analysis results through three-dimensional visualization, calculating the work efficiency of each type of work and equipment, and identifying the factors affecting work efficiency;

[0087] Step 2.4, generating work efficiency analysis report, including personnel and equipment working state, efficiency data and identification results of low efficiency or abnormal behavior.

[0088] Through the deployment of sensor network to monitor the distribution of personnel and equipment in construction site in real time, including camera, RFID tag, etc., to obtain accurate real-time data. Then, use computer vision technology to analyze the monitored video, identify the location, quantity and working state of personnel and equipment. At the same time, the system can also combine intelligent recognition algorithm to classify different types of work and equipment, further improve the accuracy of identification.

[0089] In terms of work efficiency identification, the system uses data analysis and machine learning technology to process and analyze real-time monitoring data to quantify work efficiency and identify influencing factors. By establishing a model, the system can dynamically adjust the relevant parameters in the construction period calculation model according to the actual situation, such as personnel allocation ratio, equipment utilization rate, etc., to reflect the actual situation of construction site.

[0090] Step 3, based on the existing progress of step 1 and the work efficiency data of step 2, through algorithm to iterate and optimize the construction period, to find the optimal construction period scheme;

[0091] Preferably, step 3 specifically includes the following steps:

[0092] Step 3.1, taking the identified existing progress data and working conditions as the initial solution, representing the initial construction period scheme as an individual or particle, each individual or particle representing a construction period arrangement scheme, including the start and end time of each task, resource allocation;

[0093] Step 3.2, through genetic algorithm to simulate natural selection, crossover and mutation operations, gradually optimize the construction period arrangement scheme;

[0094] In step 3.2, the selection operation is performed: select the individual with better performance from the initial solution set, and prefer to keep the high fitness schedule;

[0095] The crossover operation: exchange part of the schedule of the selected individual, generate a new schedule;

[0096] Mutation operation: randomly mutate part of the individual, change the start time of the task or resource allocation.

[0097] Step 3.3, through the particle swarm optimization algorithm, simulate the behavior of the group, optimize the schedule, find the optimal or near-optimal solution;

[0098] Step 3.4, according to the schedule, cost, resource utilization comprehensive index to evaluate the pros and cons of each new solution;

[0099] Step 3.5, in each iteration, according to the evaluation results to select the optimal solution, and carry out the cross and mutation operation, generate new candidate solution;

[0100] Step 3.6, continue iteration, until the preset stop condition is met, meet the stop condition, output the current optimal solution as the final schedule scheme.

[0101] Evolutionary computation-based iterative optimization algorithm:

[0102] This algorithm simulates the process of biological evolution in nature, through the simulation of selection, crossover and mutation operations, gradually optimize the solution of the problem. The system uses genetic algorithm (Genetic Algorithm, GA) and particle swarm optimization algorithm (Particle Swarm Optimization, PSO) and other evolutionary computation algorithms to realize the iterative optimization of the schedule.

[0103] In the schedule calculation and adjustment process, the system first identifies the existing schedule and working conditions as the initial solution input to the optimization algorithm. Then, use evolutionary computation algorithm to iteratively adjust the schedule, generate new solutions, and evaluate the new solutions through the evaluation function to determine their pros and cons. The evaluation function usually includes comprehensive indicators considering schedule, cost, resource utilization and other factors.

[0104] In each iteration, the optimization algorithm selects the better solution according to the evaluation results, and carries out the cross and mutation operations, generates new candidate solution. This process will continue for several iterations, until the preset stop condition is met, such as reaching the maximum number of iterations or finding the optimal solution that meets the requirements.

[0105] Through continuous iteration and optimization, the system can find the optimal schedule to meet project requirements and maximize construction efficiency. The advantage of evolutionary computation algorithms is that they can find global optimal solutions or solutions close to optimal solutions in complex search spaces, while having good adaptability to different types of engineering projects and construction environments.

[0106] Step 4, based on the optimized schedule, predict the steel structure construction period combined with digital twinning according to historical data and current construction conditions.

[0107] By inputting the number of construction personnel, the number of mechanical equipment shifts, weather factors and other common construction boundary conditions, the duration of each sub-item engineering is automatically calculated, and the daily construction volume, mechanical equipment and worker position distribution and work content are arranged in a lean manner.

[0108] The determining factors of construction boundary conditions include the number of mechanical equipment shifts (cranes) and the number of construction personnel. The uncertain factors of construction boundary conditions include weather (such as heavy rain, typhoon, high temperature, etc.) and holidays.

[0109] Preferably, step 4.1, input construction boundary conditions including the number of construction personnel, the number of mechanical equipment shifts, weather factors;

[0110] Step 4.2, based on historical data and experience, establish a construction period calculation model;

[0111] Preferably, step 4.2 specifically includes:

[0112] According to historical data, estimate the construction period including lifting and riveting and welding floor slab laying under the condition of a certain number of cranes and construction personnel;

[0113] Set the number of cranes to be proportional to the lifting efficiency. Compared with 1 crane, for every additional 1 crane, estimate the lifting efficiency improvement rate according to the set proportion;

[0114] Set the number of construction personnel to be proportional to the riveting and welding floor slab laying efficiency. Estimate the efficiency improvement rate according to the number of personnel increase.

[0115] For example:

[0116] According to historical data, when the number of cranes is 2 and the number of construction personnel is 25, the complete construction period is estimated to be 60 days, with lifting accounting for 40% for 24 days and riveting and welding floor slab laying accounting for 60% for 36 days;

[0117] The number of cranes is proportional to the lifting efficiency. Compared with 1 crane, for every additional 1 crane, the lifting efficiency is improved by 30% to 40%, and the lifting efficiency improvement rate is estimated at 35%;

[0118] The number of construction personnel is directly proportional to the efficiency of the riveting and welding floor support plate laying efficiency. Setting the number of construction personnel to 40 is twice the efficiency of 20 people.

[0119] Uncertain factors cause downtime, and the more days of construction period input, the more days of downtime.

[0120] Step 4.3, according to the input boundary conditions, automatically calculate the part item engineering construction period length, arrange the daily construction volume, mechanized equipment and the position distribution and work content of the operation personnel;

[0121] Step 4.4, apply the construction period calculation formula to calculate the expected construction period.

[0122] Preferably, in step 4.4, the construction period calculation formula is as follows:

[0123]

[0124] In the formula:

[0125] X represents the number of cranes;

[0126] Y represents the number of construction personnel;

[0127] Z represents the number of downtime days;

[0128] D represents the number of construction period days.

[0129] The significant difference between the present application and the prior art is that a digital twin model combining real-time monitoring data and dynamic adjustment algorithm is provided, which can not only update in real time to reflect the immediate state of the construction site, but also accurately predict and optimize the construction progress through advanced algorithms; The present application uses computer vision and sensor network technology to monitor personnel and equipment on the construction site, improves the understanding accuracy of construction activities through behavior analysis and pose estimation algorithm; At the same time, the present application uses genetic algorithm and particle swarm optimization algorithm to realize the automation and optimization of construction period arrangement;

[0130] The beneficial effects of the present application over the prior art are that through the integration and analysis of real-time data, the accuracy and reliability of construction period prediction are significantly improved; Dynamic parameter adjustment and intelligent progress adjustment mechanism enable the present application to quickly adapt to any changes in the construction process, effectively reducing construction delays; The intelligentization of resource optimization and scheduling further improves construction efficiency and resource utilization; The present application also provides a user-friendly interface and three-dimensional visualization technology, so that construction managers can more intuitively and conveniently monitor construction progress and manage the construction site.

[0131] The second aspect of the application provides a steel structure construction duration prediction system based on digital twinning, comprising: a data acquisition and monitoring module, a digital twinning and progress identification module, a work efficiency analysis and evaluation module, and a duration optimization and prediction module.

[0132] The data acquisition and monitoring module collects multi-dimensional data, including personnel location, equipment status, and material usage, by installing high-resolution cameras, RFID tags, and sensor networks on the construction site, providing basic data support for subsequent analysis and model comparison.

[0133] The digital twinning and progress identification module compares actual construction data with planned progress using a digital twinning model, adjusts model parameters through a real-time updating mechanism, generates progress comparison results, and identifies the existing progress of the project.

[0134] The work efficiency analysis and evaluation module uses computer vision and sensor networks to monitor and analyze the distribution and working status of personnel and equipment in real time, evaluates work efficiency, and identifies inefficient and abnormal behavior.

[0135] The duration optimization and prediction module uses genetic algorithms and particle swarm optimization algorithms to iteratively optimize the duration based on existing progress and work efficiency data, evaluates comprehensive indicators such as duration, cost, and resource utilization, generates an optimal duration plan, and predicts the steel structure construction duration based on historical data and current construction conditions.

[0136] The application has the beneficial effect of combining digital twinning technology with construction duration calculation, innovatively developing a highly intelligent and accurate construction management system, bringing new management concepts and technical means to the engineering construction field. Through digital twinning technology, the system can reflect the real-time state of the physical model and its digital simulation of the project, achieving comprehensive monitoring and management of the construction process. At the same time, combined with construction duration calculation technology, the system can accurately predict the construction period of the project, providing an important basis for reasonable arrangement of project progress.

[0137] Through the digital twinning model, the actual construction data is compared with the planned progress, effectively identifying the existing progress of the project, improving the accuracy and reliability of progress identification; through pose estimation algorithms and behavior analysis, the work efficiency of construction personnel and equipment is identified, and inefficient or abnormal behavior is discovered in time, improving overall work efficiency; based on real-time monitoring data and optimization results, dynamically adjusting the construction plan improves the flexibility and adaptability of construction management; through real-time monitoring and prediction analysis, potential problems and risks in construction are discovered in time, providing early warning information, saving construction cost, and ensuring the smooth progress of the project.

[0138] The present disclosure can be a system, a method, and / or a computer program product. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0139] It should be noted that the above-mentioned embodiments are only used to illustrate the technical solutions of the present application, not to limit it. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application. Any modification or equivalent replacement should be covered within the protection scope of the claims of the present application.

Claims

1. A steel structure construction period prediction method based on digital twinning, characterized by, The method comprises the following steps: Step 1, by monitoring the construction site and collecting data, comparing the actual construction situation with the digital model by using the digital twin model, identifying the existing progress of the project; Step 2, based on the obtained existing progress, monitoring and analyzing the personnel and equipment distribution and work efficiency of the construction site through sensor network and computer vision; wherein, the action and posture of the personnel are analyzed by using the posture estimation algorithm to judge the working state, including operating equipment, carrying materials and resting; the work efficiency of the personnel and equipment is identified by behavior analysis to determine whether there is low efficiency or abnormal behavior; Step 3, based on the data of the existing progress of step 1 and the work efficiency of step 2, the optimal duration scheme is found by using the optimization algorithm to iteratively optimize the duration; Step 4, based on the optimized duration scheme, the steel structure construction duration is predicted combined with the digital twin according to the historical data and the current construction conditions; wherein, a duration calculation model is established; according to the historical data, the duration of hoisting and riveting and welding floor slab laying is estimated under the condition of the set number of cranes and the number of construction personnel; the number of cranes is set to be proportional to the hoisting efficiency, compared with 1 crane, for every additional 1 crane, the hoisting efficiency is estimated to increase by a certain percentage; the number of construction personnel is set to be proportional to the riveting and welding floor slab laying efficiency, and the efficiency improvement rate is estimated according to the number of personnel.

2. The steel structure construction duration prediction method based on digital twin according to claim 1, characterized in that: Step 1 specifically comprises the following steps: Step 1.1, configure sensors and monitoring devices, install cameras and RFID tags in the construction site to cover all areas; the camera is used for video monitoring, and the RFID tag is used for tracking personnel and equipment; Step 1.2, based on the sensors and monitoring devices configured in step 1.1, collect multi-dimensional data of the construction site, including personnel position, equipment state and material usage; Step 1.3, input the collected data into the digital twin model, compare the actual construction progress with the planned progress, and generate the progress comparison result.

3. The steel structure construction duration prediction method based on digital twin according to claim 2, characterized in that: In step 1.3, the comparison of actual construction progress and planned progress comprises: Step 1.3.1, pre-process the collected data and transmit it to the central processing through the communication protocol; the pre-processing includes data cleaning and data formatting; the data formatting includes uniformly converting the data format to the standard format for processing data in the digital twin model; Step 1.3.2, input the pre-processed real-time construction data into the digital twin model, and load and initialize the planned progress data in the digital twin model, ready for comparison. Step 1.3.3, identify and record the location and status of each worker and equipment, match with the planned schedule, compare the actual and planned task start and end time to calculate the time deviation, compare the actual and planned task completion rate to calculate the task completion rate, and obtain the actual progress; according to the comparison result, real-time update the planned schedule data in the digital twin model, synchronize the digital twin model with the actual construction situation.

4. The steel structure construction schedule prediction method based on digital twin according to claim 1, characterized in that: Step 2 specifically includes the following steps: Step 2.1, through computer vision and RFID, image processing is performed on the video of the construction site to identify the location of the personnel and equipment on the construction site, and the action and running state is detected; Step 2.2, analyze the action and posture of the personnel through pose estimation algorithm to judge the working state, including operating equipment, carrying materials and resting; identify the working efficiency of personnel and equipment through behavior analysis to determine whether there is low efficiency or abnormal behavior; Step 2.3, quantize the analysis results and display the analysis results through three-dimensional visualization to calculate the working efficiency of each type of work and equipment and identify the factors affecting the working efficiency; Step 2.4, generate a working efficiency analysis report including the working state, efficiency data and identification results of low efficiency or abnormal behavior of personnel and equipment.

5. The steel structure construction schedule prediction method based on digital twin according to claim 1, characterized in that: Step 3 specifically includes the following steps: Step 3.1, the existing schedule data and working conditions identified are taken as the initial solution, and the initial construction period scheme is represented as an individual or particle, each individual or particle representing a construction period arrangement scheme, including the start and end time of each task and resource allocation; Step 3.2, simulate natural selection, crossover and mutation operations through genetic algorithm to gradually optimize the construction period arrangement scheme; Step 3.3, simulate group behavior through particle swarm optimization algorithm to optimize the construction period and find the optimal or near-optimal solution; Step 3.4, evaluate the pros and cons of each new solution according to the construction period, cost and resource utilization rate comprehensive index; Step 3.5, in each iteration, select the optimal solution according to the evaluation results and perform crossover and mutation operations to generate new candidate solutions; Step 3.6, continue iteration until the preset stopping condition is met, and output the current optimal solution as the final construction period arrangement scheme when the stopping condition is met.

6. The steel structure construction schedule prediction method based on digital twin according to claim 5, characterized in that: In step 3.2, the selection operation includes selecting individuals with better performance from the initial solution set, and preferentially retaining construction period schemes with high fitness; The crossover operation includes exchanging part of the construction period arrangement of the selected individuals to generate new construction period schemes; The mutation operation includes randomly mutating part of the individuals to change the start time of the task or resource allocation.

7. The steel structure construction schedule prediction method based on digital twin according to claim 1, characterized in that: Step 4 specifically includes the following steps: Step 4.1, inputting construction boundary conditions including the number of construction personnel, the number of mechanical equipment shifts, and weather factors; Step 4.2, establishing a construction period calculation model based on historical data and experience; Step 4.3, automatically calculating the duration of sub-construction projects, arranging daily construction volume, mechanical equipment and worker position distribution, and work content according to the input boundary conditions; Step 4.4, applying the construction period calculation formula to calculate the estimated construction period.

8. The steel structure construction period prediction method based on digital twinning according to claim 7, characterized in that: In step 4.4, the construction period calculation formula is as follows: Wherein: denotes the number of cranes; represents the number of construction workers; represents the number of days of downtime; Indicates the number of days of the duration.

9. A digital-twin-based steel structure construction duration prediction system using the method of any one of claims 1-8, comprising: The data acquisition and monitoring module, the digital twinning and progress identification module, the work efficiency analysis and evaluation module, and the construction period optimization and prediction module; characterized in that: The data acquisition and monitoring module collects multi-dimensional data including personnel location, equipment status and material usage by installing high-resolution cameras, RFID tags and sensor networks on the construction site; The digital twinning and progress identification module compares the actual construction data with the planned progress using the digital twinning model, adjusts the model parameters through a real-time updating mechanism, generates a progress comparison result, and identifies the existing progress of the project; The work efficiency analysis and evaluation module monitors and analyzes the distribution and working status of personnel and equipment on the construction site in real time through computer vision and sensor networks, evaluates work efficiency, and identifies inefficient and abnormal behaviors; The construction period optimization and prediction module iteratively optimizes the construction period based on the existing progress and work efficiency data using genetic algorithms and particle swarm optimization algorithms, evaluates the construction period, cost and resource utilization rate comprehensive index to generate an optimal construction period scheme, and predicts the steel structure construction period based on historical data and current construction conditions.

Images