Municipal road construction method and system based on BIM

Abstract

The invention discloses a BIM-based municipal road construction method and system, and the method comprises the steps: collecting traffic flow data, accident information and weather conditions, and generating original traffic data and traffic state data; collecting construction data; cleaning and processing the collected original traffic data and traffic state data to obtain traffic data and traffic information characteristics; generating traffic flow prediction data and an initial model framework based on the traffic data and the traffic information features; generating a construction scheme and a stage schedule by using an optimization algorithm in combination with the predicted traffic flow data and construction data; and filling the construction scheme and the stage schedule into the initial model framework to generate an initial BIM model, and generating the BIM model according to the construction data through dynamic traffic simulation. Through collection, processing and analysis of comprehensive traffic data and construction data, a construction scheme is optimized, and dynamic traffic simulation is carried out, so that the construction efficiency is remarkably improved, traffic congestion is reduced, and the construction safety is improved.

Description

Technical Field

[0001] The present application relates to the technical field of road construction, and in particular to a municipal road construction system based on BIM. Background Art

[0002] With the acceleration of urbanization, the demand for municipal infrastructure construction and maintenance is increasing. However, traditional construction management methods often ignore the impact of construction on surrounding traffic, resulting in frequent traffic congestion and traffic accidents, which increases social costs. At the same time, low construction efficiency and information asymmetry also lead to waste of resources and affect construction progress. Therefore, an intelligent system that can monitor traffic conditions in real time, analyze construction impacts and perform dynamic optimization is needed to improve the scientificity and rationality of road construction, and the BIM three-dimensional model came into being.

[0003] In the relevant technical scheme, a BIM-based municipal road construction method is provided by the Chinese patent with publication number CN118607072A. First, the municipal road construction data collected from multiple departments such as the design department, survey and mapping department, municipal facilities management department, traffic management department and environmental monitoring agency are stored in the database. By collecting and classifying the data of multiple departments such as design, survey and mapping, municipal facilities management, traffic management and environmental monitoring, standard data and auxiliary data are established. First, a standard municipal road construction BIM model based on the data of the design department is constructed, and then an auxiliary BIM model group is constructed based on the data of other departments. The invention can fully display the details of municipal road construction, assist in comprehensive evaluation and planning before construction, reduce potential data errors and conflicts, and improve construction efficiency and quality. The BIM model provides an intuitive communication platform for all parties in the project, promotes the smooth progress of the project, and realizes the digital management and optimization of municipal road construction.

[0004] However, in the process of implementing relevant technical solutions, it was found that there were at least the following technical problems: Municipal road construction is generally carried out within the city, and even needs to be carried out in the city center. Therefore, construction will lead to restricted traffic flow on some construction roads, resulting in frequent traffic congestion and traffic accidents, increasing social costs. At the same time, on the timeline, there are seasonal (a certain period of time) changes in traffic flow near the construction site. If this seasonal change is not presented in the BIM model, the construction efficiency will decrease when the construction department uses the BIM model. Summary of the invention

[0005] In order to solve the above problems, an embodiment of the present invention provides a municipal road construction system based on BIM, the system comprising: Traffic data collection module, which collects traffic flow data, accident information and weather conditions, and generates raw traffic data and traffic status data; A construction data collection module collects construction data; Traffic data processing module cleans and processes the collected raw traffic data and traffic status data to obtain traffic data and traffic information features; Traffic flow prediction module, which generates traffic flow prediction data and initial model framework based on traffic data and traffic information characteristics; The construction plan optimization module combines the predicted traffic flow data and construction data and uses optimization algorithms to generate construction plans and phase schedules; The dynamic traffic simulation module fills the construction plan and phase schedule into the initial model framework to generate the initial BIM model. Through dynamic traffic simulation, the BIM model is generated according to the construction data.

[0006] Furthermore, the method for generating the original traffic data and the traffic status data includes: Categorize traffic flow data, accident information, and weather conditions by time and location IP; Use spreadsheets to record classified traffic flow data, accident information, and weather conditions to obtain raw traffic data; The original traffic data is cleaned and formatted, and traffic density, average vehicle speed and accident rate are calculated. The traffic status score is calculated using the weighted average method with traffic density, average vehicle speed and accident rate as data items. Traffic density, average vehicle speed, accident rate and traffic status score are summarized to generate traffic status data.

[0007] Furthermore, the method for acquiring the traffic information characteristics includes: The traffic status data is cleaned and sorted, missing data and outliers are processed, traffic data is obtained, and the unit root test is used to determine whether the time series of traffic data is stationary. If not, differential processing is used to make the time series stationary. If it is stationary, time period identifiers are created for the traffic data, and statistical analysis is performed on traffic density, average vehicle speed and accident rate to obtain statistical identifiers. The time period identifiers and statistical identifiers are summarized to obtain traffic information characteristics.

[0008] Furthermore, the method for obtaining traffic flow prediction data includes: Traffic data and traffic information features are input into the pre-built traffic flow prediction model, and traffic flow prediction data is output.

[0009] Furthermore, the method for constructing the traffic flow prediction model includes: Set construction parameters, including the order of autoregressive terms, the number of differences, the seasonal cycle and the order of moving average terms; use statistical software to draw partial autocorrelation diagrams and use autocorrelation diagrams; Preset seasonal cycle, use partial autocorrelation plot to determine the order of autoregressive term, and use autocorrelation plot to determine the order of moving average term; Construct the SARIMA basic expression equation, which includes: ; In the formula, For the moment Traffic flow forecast data; is a constant term; is the autoregression coefficient; is the order of the autoregressive term; is the moving average coefficient; For the front The error term at each moment; is the order of the moving average term; and is the number of the moment; is the seasonal autoregressive coefficient; is the seasonal moving average coefficient; For the front seasonal error term; is the order of the seasonal moving average term; is the white noise error term; The SARIMA basic expression equation is fitted to complete the construction of the traffic flow prediction model.

[0010] Furthermore, the training method of the traffic flow prediction model includes: All traffic data and traffic information features are used as inputs of the traffic flow prediction model. The traffic flow prediction model takes the traffic flow prediction data corresponding to each set of traffic data and traffic information features as output, takes the actual traffic flow prediction data corresponding to each set of traffic data and traffic information features as the prediction target, and takes minimizing the sum of the prediction accuracies of all predicted traffic flow prediction data as the training target; the traffic flow prediction model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped; the traffic flow prediction model is a seasonal difference autoregressive sliding average model.

[0011] Furthermore, the method for generating the construction plan and the phase schedule includes: Preset the objective function; preset the state space of the construction plan; randomly set a construction plan from the state space as the search starting point; preset the initial temperature; Start looping to update the current status and temperature: Calculate the objective function and obtain the target value of the current state; Generate neighborhood solutions from the current state; Calculate the target value of the neighborhood solution; if the target value of the neighborhood solution is greater than the target value of the current state, update the current state to the neighborhood solution; if the target value of the neighborhood solution is less than the target value of the current state, randomly generate a random number and compare it with the update probability. If the random number is less than the update probability, update the current state to the neighborhood solution. If the random number is greater than or equal to the update probability, keep the current state unchanged. Update the temperature using a linear cooling strategy; Check whether the loop termination condition is reached. When the loop termination condition is reached, stop the optimization algorithm and generate a construction plan and phase schedule at the end of the algorithm.

[0012] A municipal road construction method based on BIM, the method comprising: Collect traffic flow data, accident information and weather conditions to generate raw traffic data and traffic status data; Collect construction data; Clean and process the collected raw traffic data and traffic status data to obtain traffic data and traffic information characteristics; Generate traffic flow prediction data and initial model framework based on traffic data and traffic information characteristics; Combine predicted traffic flow data with construction data and use optimization algorithms to generate construction plans and phase schedules; Fill the construction plan and phase schedule into the initial model framework to generate the initial BIM model, and generate the BIM model based on the construction data through dynamic traffic simulation.

[0013] The technical effects and advantages of a BIM-based municipal road construction system provided by the present invention are as follows: The present invention optimizes the construction plan and performs dynamic traffic simulation by collecting, processing and analyzing comprehensive traffic data and construction data, thereby significantly improving construction efficiency, reducing traffic congestion and improving construction safety. Through the traffic data collection module and the data processing module, the system of the present invention can reflect the traffic status in real time and accurately, provide data-driven decision support, and effectively improve the monitoring and early warning capabilities of the traffic management department on traffic conditions during construction; combined with historical traffic data and real-time data, the system uses advanced traffic flow prediction models to generate highly accurate traffic flow prediction data, helping construction planners to reasonably arrange construction time, optimize construction sequence, and reduce interference with traffic flow; using optimization algorithms, based on real-time traffic prediction and construction data, the optimal construction plan is generated to ensure efficient construction and minimize the impact on traffic and construction costs; through accurate traffic flow prediction and traffic management measures, traffic safety during construction is improved, and road traffic efficiency is effectively improved, reducing the negative impact of construction on the public and urban traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a connection diagram of a BIM-based municipal road construction system in Example 1; Figure 2 A flow chart of a method for generating a construction plan and a phase schedule in Example 1; Figure 3 This is a flow chart of a BIM-based municipal road construction method in Example 2. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Example 1: Please refer to Figure 1 As shown, the municipal road construction system based on BIM described in this embodiment includes: Traffic data collection module, which collects traffic flow data, accident information and weather conditions, and generates raw traffic data and traffic status data; A construction data collection module collects construction data; Traffic data processing module cleans and processes the collected raw traffic data and traffic status data to obtain traffic data and traffic information characteristics; Traffic flow prediction module, which generates traffic flow prediction data and initial model framework based on traffic data and traffic information characteristics; The construction plan optimization module combines the predicted traffic flow data and construction data and uses optimization algorithms to generate construction plans and phase schedules; The dynamic traffic simulation module fills the construction plan and phase schedule into the initial model framework to generate the initial BIM model. Through dynamic traffic simulation, the BIM model is generated according to the construction data.

[0017] The use of electronic sensors (such as ground induction coils, radar speed guns and cameras) can automatically record the number of vehicles passing through the corresponding location; anonymous location data collected from mobile devices or vehicle navigation systems can help analyze traffic flow and average speed; traffic flow data is the number and average speed of vehicles passing through a specific location (such as roads, intersections) within a specific time period or per unit time, which can be used to analyze traffic congestion and traffic efficiency.

[0018] Accident information includes the time and location of the accident, the number of vehicles involved, casualties, causes of the accident, etc., which can be obtained from the Traffic Management Bureau and the Public News Office. When an accident occurs, the transportation department will generally block roads, or partially block roads, which will increase congestion and reduce traffic efficiency.

[0019] Weather conditions involve meteorological factors that affect road traffic safety and flow, including temperature, rainfall, snowfall, visibility, wind speed, etc., which can be obtained from national or local meteorological bureaus.

[0020] Collecting traffic flow data, accident information and weather conditions can provide support for a series of decisions such as traffic management, construction plan formulation, traffic flow forecasting, etc., ensuring that the construction plan can fully consider the actual conditions and possible impacts of traffic flow.

[0021] The method for generating the original traffic data and the traffic status data includes: Categorize traffic flow data, accident information, and weather conditions by time and location IP; for example, organize traffic flow data by hour or minute and associate it with corresponding accident and weather data.

[0022] Use a spreadsheet to record classified traffic flow data, accident information, and weather conditions to obtain raw traffic data; the raw traffic data includes timestamps, locations, number of vehicles, accident events, weather parameters, etc.; The original traffic data is cleaned to remove erroneous or incomplete data (such as duplicate values, outliers, etc.), and the format problems are corrected. The original traffic data corresponding to a specific time period (such as every hour or every day) is selected to calculate indicators such as traffic density, average vehicle speed and accident rate. The traffic status score is calculated using the weighted average method with indicators such as traffic density, average vehicle speed and accident rate as data items; indicators such as traffic density, average vehicle speed and accident rate, as well as traffic status scores are summarized to generate traffic status data.

[0023] Traffic density: the number of vehicles per unit area.

[0024] Average speed: The average speed of vehicles in a specific area.

[0025] Accident rate: the frequency of traffic accidents occurring within a certain period of time.

[0026] The method for obtaining traffic data and generating traffic information features includes: Use the Pandas library in Python to clean and organize traffic status data, process missing data and outliers, obtain traffic data, and use unit root tests (such as Dickey-Fuller test) to determine whether the time series of traffic data is stationary. If not, use differential processing (such as simple differential) to make the time series stationary. If it is stationary, create time period identifiers for traffic data including peak and non-peak periods, perform statistical analysis on indicators such as traffic density, average speed and accident rate, obtain statistical identifiers such as standard deviation, maximum and minimum values, summarize time period identifiers and statistical identifiers, and obtain traffic information characteristics.

[0027] Exemplarily, the Dickey-Fuller test is used to determine whether the time series of traffic data is stationary; The p-value is the probability of the observed statistic (or a more extreme statistic) occurring when the null hypothesis is true (nonstationary) in the Dickey-Fuller test; If the p-value is less than the preset significance level (such as 0.05), the unit root hypothesis is rejected and the series is stable; If the p-value is greater than or equal to the preset significance level, the null hypothesis cannot be rejected, the data does not provide sufficient evidence to negate the null hypothesis, and the time series is not stationary.

[0028] Construction data includes construction progress data, construction technology (for example, asphalt laying, concrete pouring, pipeline laying, etc.), construction materials, construction site conditions (topography and geological conditions of the construction location, nearby traffic conditions, etc., and implemented traffic control measures, including temporary traffic signs, signal light adjustments and road closure information) and construction costs.

[0029] The methods for obtaining traffic flow prediction data include: Traffic data and traffic information features are input into the pre-built traffic flow prediction model, and traffic flow prediction data is output.

[0030] The construction method of traffic flow prediction model includes: Set construction parameters, including the order of autoregressive terms, number of differences, seasonal cycles, and order of moving average terms; use statistical software (such as the Statsmodels library in Python, R language, etc.) to draw partial autocorrelation graphs and use autocorrelation graphs; Preset seasonal cycle, use partial autocorrelation plot to determine the order of autoregressive term, and use autocorrelation plot to determine the order of moving average term; Construct the SARIMA basic expression equation, which includes: ; In the formula, For the moment Traffic flow forecast data; is a constant term; is the autoregressive coefficient, which can be calculated using the Yule-Walker equation and represents the current value Before The value of the moment relationship; is the order of the autoregressive term; is the moving average coefficient, which can be calculated using the least squares method and represents the current value With the previous The error term (residual) at time relationship; is the order of the moving average term; is the seasonal autoregressive coefficient, which is calculated using the Yule-Walker equation according to the seasonal cycle and is used to describe the current value With the previous seasonal moments (e.g., 8am and 6pm every day) relationship; is the seasonal moving average coefficient, indicating the current value With the previous Seasonal error term relationship; is the order of the seasonal moving average term, indicating the number of moving average components used in the seasonal part; is a white noise error term, which represents the random error between the actual observation value and the model prediction value. It is usually assumed that these error terms are independent and identically distributed and follow a normal distribution.

[0031] The traffic flow prediction model is constructed by fitting the basic expression equation; the fitting methods include the least squares method and the maximum likelihood method, which are usually completed with the help of statistical software or libraries (such as Python's statsmodels).

[0032] The SARIMA model can effectively capture trends, seasonality and randomness in time series data, better simulate the dynamic characteristics of traffic flow, and improve the accuracy and reliability of traffic flow prediction; through the analysis of historical traffic data, the model can adapt to changes in traffic flow in different time periods (such as peak and non-peak periods) and provide more accurate prediction data for traffic management; combined with traffic flow prediction data, it can monitor traffic flow conditions in real time during the construction process, adjust the construction plan in time, and ensure a smooth construction process.

[0033] The training methods of the traffic flow prediction model include: All traffic data and traffic information features are used as inputs of the traffic flow prediction model. The traffic flow prediction model takes the traffic flow prediction data corresponding to each set of traffic data and traffic information features as output, takes the actual traffic flow prediction data corresponding to each set of traffic data and traffic information features as the prediction target, and takes minimizing the sum of the prediction accuracies of all predicted traffic flow prediction data as the training target.

[0034] The calculation formula for prediction accuracy is: ,in, is the number of each set of traffic data and traffic information features, For prediction accuracy, For the Traffic data and traffic information features corresponding to the predicted traffic flow prediction data, For the The actual traffic flow prediction data corresponding to the group traffic data and traffic information characteristics are obtained; the traffic flow prediction model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped; the traffic flow prediction model is a seasonal difference autoregressive sliding average model.

[0035] like Figure 2 As shown, the method for generating the construction plan and phase schedule includes: Preset objective function, for example, the objective function is caused by the construction plan , construction time and construction cost, then the objective function include: ×Construction time+ × Construction cost; In the formula, , and is the corresponding weight.

[0036] The state space of the preset construction plan is the set of all possible construction plans; each state in the state space is represented as a schedule of a specific construction plan, such as road closures or construction activities within a specific time period.

[0037] Randomly set a construction plan from the state space as the search starting point; Preset the initial temperature; the higher the temperature, the greater the probability of accepting a suboptimal solution, thus allowing a wider range of exploration; start a loop to update the current state and temperature; Calculate the objective function and obtain the target value of the current state to evaluate the pros and cons of the construction plan; Generate a neighborhood solution from the current state. The neighborhood solution is obtained by making small adjustments to the current construction plan. The method of generating a neighborhood solution includes adjusting the construction time, changing the construction sequence, and modifying the construction period. For example: Adjust the construction time: Assuming that a construction section in the current state is from 8:00 to 12:00, you can try to advance the start time of this section to 7:30, or delay it to 8:30, thus generating a new neighborhood solution.

[0038] Change the construction order: If the current construction status is to carry out construction B after construction A on a certain road, you can try to adjust the order and carry out construction B first and then construction A, thus generating a new neighborhood solution.

[0039] Modify the construction cycle: Change the time of a short-term construction step from 2 hours to 1.5 hours to observe its impact on the overall effect, and a new neighborhood solution can be generated.

[0040] Calculate the target value of the neighborhood solution; if the target value of the neighborhood solution is greater than the target value of the current state, update the current state to the neighborhood solution; if the target value of the neighborhood solution is less than the target value of the current state, randomly generate a random number and compare it with the update probability. If the random number is less than the update probability, update the current state to the neighborhood solution. If the random number is greater than or equal to the update probability, keep the current state unchanged.

[0041] Update probability The calculation methods include: ; In the formula, is the target value of the neighborhood solution; is the target value of the current state; is a natural constant; is the current temperature, and is the initial temperature at the beginning, which determines the degree of acceptance of worse solutions. The higher the temperature, the greater the probability of acceptance.

[0042] Update the temperature and use a linear cooling strategy; Exemplary: ; In the formula, is the updated temperature, is the current temperature, is the temperature reduction coefficient, 0< <1, which is the default value.

[0043] Check whether the loop termination conditions are met. When the loop termination conditions are met, stop the optimization algorithm. The construction plan corresponding to the current state is the final output of the algorithm. The loop termination conditions include reaching the preset minimum temperature and the preset number of cycles.

[0044] Combining the construction plan and the corresponding schedule into a table is the phase schedule.

[0045] It is particularly noted that the present invention assumes that all design drawings of the construction plan exist. Therefore, in the subsequent filling, when using BIM software (such as Revit, Navisworks, Tekla, etc.) for modeling, it is sufficient to gradually fill in the elements combined with the corresponding construction methods and required time according to the specific architectural design drawings and infrastructure design drawings in the construction plan. The phase schedule is used to add a timeline of construction activities in the BIM software.

[0046] By systematically evaluating and optimizing the arrangement of each construction activity, the overall construction time can be effectively shortened, thereby reducing the project duration; using the objective function to evaluate the construction cost and taking corresponding strategies to correct the construction arrangement can help to achieve reasonable control of funds and reduce cost waste; through model calculation and random generation of neighborhood solutions, the advantages and disadvantages of various construction plans can be scientifically evaluated, providing data-driven support for decision makers, making the decision-making process more transparent and reasonable; by optimizing the time, sequence and cycle of construction operations, the conflict between traffic flow and construction can be reduced, the risk of accidents can be reduced, and the safety of construction workers can be guaranteed.

[0047] The methods for generating BIM models include: Input traffic control measures into the initial BIM model, such as traffic guidance signs and temporary traffic signals, add traffic network symbols, including roads, intersections, signal lights and traffic signs, etc., import dynamic traffic simulation software (such as VISSIM, Synchro and AIMSUN, etc.) to create a simulation environment, set simulation parameters according to construction data, and use dynamic visualization technology to establish a BIM model.

[0048] Embodiment 2: Figure 3 As shown, based on the same inventive concept as the BIM-based municipal road construction system in the aforementioned embodiment, the present application provides a BIM-based municipal road construction method, and the method in the embodiment of the present application is based on the same inventive concept as the system embodiment. The method includes: Collect traffic flow data, accident information and weather conditions to generate raw traffic data and traffic status data; Collect construction data; Clean and process the collected raw traffic data and traffic status data to obtain traffic data and traffic information characteristics; Generate traffic flow prediction data and initial model framework based on traffic data and traffic information characteristics; Combine predicted traffic flow data with construction data and use optimization algorithms to generate construction plans and phase schedules; Fill the construction plan and phase schedule into the initial model framework to generate the initial BIM model, and generate the BIM model based on the construction data through dynamic traffic simulation.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0050] What has been described above is only a preferred specific implementation manner of the embodiments of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can make equivalent substitutions or changes according to the technical scheme and concept of the present application within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A municipal road construction system based on BIM, characterized in that: The system includes: Traffic data collection module, which collects traffic flow data, accident information and weather conditions, and generates raw traffic data and traffic status data; A construction data collection module collects construction data; Traffic data processing module cleans and processes the collected raw traffic data and traffic status data to obtain traffic data and traffic information features; Traffic flow prediction module, which generates traffic flow prediction data and initial model framework based on traffic data and traffic information characteristics; The construction plan optimization module combines the predicted traffic flow data and construction data and uses optimization algorithms to generate construction plans and phase schedules; The dynamic traffic simulation module fills the construction plan and phase schedule into the initial model framework to generate the initial BIM model. Through dynamic traffic simulation, the BIM model is generated according to the construction data.

2. A BIM-based municipal road construction system as claimed in claim 1, characterized in that: The method for generating the original traffic data and the traffic status data comprises: Categorize traffic flow data, accident information, and weather conditions by time and location IP; Use spreadsheets to record classified traffic flow data, accident information, and weather conditions to obtain raw traffic data; The original traffic data is cleaned and formatted, and traffic density, average vehicle speed and accident rate are calculated. The traffic status score is calculated using the weighted average method with traffic density, average vehicle speed and accident rate as data items. Traffic density, average vehicle speed, accident rate and traffic status score are summarized to generate traffic status data.

3. A BIM-based municipal road construction system as claimed in claim 1, characterized in that: The method for acquiring the traffic information feature includes: The traffic status data is cleaned and sorted, missing data and outliers are processed, traffic data is obtained, and the unit root test is used to determine whether the time series of traffic data is stationary. If not, differential processing is used to make the time series stationary. If it is stationary, time period identifiers are created for the traffic data, and statistical analysis is performed on traffic density, average vehicle speed and accident rate to obtain statistical identifiers. The time period identifiers and statistical identifiers are summarized to obtain traffic information characteristics.

4. A BIM-based municipal road construction system as claimed in claim 1, characterized in that: The method for acquiring traffic flow prediction data comprises: Traffic data and traffic information features are input into the pre-built traffic flow prediction model, and traffic flow prediction data is output.

5. A BIM-based municipal road construction system as claimed in claim 4, characterized in that: The method for constructing the traffic flow prediction model includes: Set construction parameters, including the order of autoregressive terms, the number of differences, the seasonal cycle and the order of moving average terms; use statistical software to draw partial autocorrelation diagrams and use autocorrelation diagrams; Preset seasonal cycle, use partial autocorrelation plot to determine the order of autoregressive term, and use autocorrelation plot to determine the order of moving average term; Construct the SARIMA basic expression equation, which includes: ； In the formula, For the moment Traffic flow forecast data; is a constant term; is the autoregression coefficient; is the order of the autoregressive term; is the moving average coefficient; For the front The error term at each moment; is the order of the moving average term; and is the number of the moment; is the seasonal autoregressive coefficient; is the seasonal moving average coefficient; For the front seasonal error term; is the order of the seasonal moving average term; is the white noise error term; The SARIMA basic expression equation is fitted to complete the construction of the traffic flow prediction model.

6. A BIM-based municipal road construction system as claimed in claim 5, characterized in that: The training method of the traffic flow prediction model includes: All traffic data and traffic information features are used as inputs of the traffic flow prediction model. The traffic flow prediction model takes the traffic flow prediction data corresponding to each set of traffic data and traffic information features as output, takes the actual traffic flow prediction data corresponding to each set of traffic data and traffic information features as the prediction target, and takes minimizing the sum of the prediction accuracies of all predicted traffic flow prediction data as the training target; the traffic flow prediction model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped; the traffic flow prediction model is a seasonal difference autoregressive sliding average model.

7. A BIM-based municipal road construction system as claimed in claim 1, characterized in that: The method for generating the construction plan and the phase schedule includes: Preset the objective function; preset the state space of the construction plan; randomly set a construction plan from the state space as the search starting point; preset the initial temperature; Start looping to update the current status and temperature: Calculate the objective function and obtain the target value of the current state; Generate neighborhood solutions from the current state; Calculate the target value of the neighborhood solution; if the target value of the neighborhood solution is greater than the target value of the current state, update the current state to the neighborhood solution; if the target value of the neighborhood solution is less than the target value of the current state, randomly generate a random number and compare it with the update probability. If the random number is less than the update probability, update the current state to the neighborhood solution. If the random number is greater than or equal to the update probability, keep the current state unchanged. Update the temperature using a linear cooling strategy; Check whether the loop termination condition is reached. When the loop termination condition is reached, stop the optimization algorithm and generate a construction plan and phase schedule at the end of the algorithm.

8. A municipal road construction method based on BIM, characterized in that: Methods include: Collect traffic flow data, accident information and weather conditions to generate raw traffic data and traffic status data; Collect construction data; Clean and process the collected raw traffic data and traffic status data to obtain traffic data and traffic information characteristics; Generate traffic flow prediction data and initial model framework based on traffic data and traffic information characteristics; Combine predicted traffic flow data with construction data and use optimization algorithms to generate construction plans and phase schedules; Fill the construction plan and phase schedule into the initial model framework to generate the initial BIM model, and generate the BIM model based on the construction data through dynamic traffic simulation.

Images