Bridge construction progress monitoring method and system based on BIM

Abstract

The invention provides a BIM-based bridge construction progress monitoring method and system, and the method comprises the steps: obtaining an observation matrix based on BIM model data and sensor monitoring data of a target bridge; inputting the observation matrix into a preset Kalman filter to obtain a corresponding fusion matrix; carrying out Granger causal test by taking the overall progress deviation as a dependent variable and taking the stress ratio, the environmental index, the resource delay rate and the process progress deviation as independent variables to obtain a Granger causal test result; and constructing a corresponding DAG, and obtaining the reason causing the overall progress deviation based on the DAG. According to the scheme, BIM model data and sensor monitoring data are accurately fused, the DAG between the overall progress deviation and each piece of quantitative information is constructed, the quantitative information causing the overall progress deviation can be accurately obtained, and an effective basis is provided for subsequent decision making.

Description

Technical Field

[0001] This application relates to the field of bridge construction progress management, and particularly to a BIM-based bridge construction progress monitoring method and system. Background Art

[0002] Bridge construction progress monitoring is a key link in bridge construction. In this process, monitoring personnel collect, analyze, and evaluate data to ensure the quality, safety, and reliability of bridge construction, timely discover potential problems (such as abnormal structural deformation and unqualified construction quality), and take repair and reinforcement measures. Its significance lies in: ensuring the safety and stability of the bridge and preventing construction risks; providing a scientific basis to optimize the construction plan and improve efficiency; and supporting later maintenance to reduce the life-cycle cost. In short, bridge construction progress monitoring is an important means to ensure the smooth, safe, and high-quality completion of bridge projects.

[0003] Currently, BIM (Building Information Modeling) technology is widely used in the construction industry and is also involved in the field of bridge construction progress monitoring. However, in the existing technology, only the bridge BIM model data and the actual construction information are simply compared to obtain the progress deviation, resulting in the inability to determine the accurate bridge construction progress deviation, and unable to give a more detailed reason for the progress deviation, and thus unable to provide an effective basis for subsequent decision-making. Summary of the Invention

[0004] The present invention provides a BIM-based bridge construction progress monitoring method and system to solve the problem in the existing technology that only the bridge BIM model data and the actual construction information are simply compared to obtain the progress deviation, resulting in the inability to determine the accurate bridge construction progress deviation, and unable to give a more detailed reason for the progress deviation, and thus unable to provide an effective basis for subsequent decision-making.

[0005] On the one hand, an embodiment of the present application provides a BIM-based bridge construction progress monitoring method, including: Based on the BIM model data and sensor monitoring data of the target bridge, an observation matrix is obtained; each row of the observation matrix corresponds to the BIM planned progress, measured progress, stress ratio, and environmental index at the corresponding time stamp. The observation matrix is input into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, the process noise covariance matrix is determined based on the construction stage at the prediction moment, and the corresponding prediction matrix is predicted. In the update stage, the Kalman gain is adjusted based on the BIM constraint set, and the prediction matrix is updated to obtain a fusion matrix. Based on the BIM planned schedule and the measured schedule in the fusion matrix, obtain the overall schedule deviation and the corresponding process schedule deviation. Based on the construction log, obtain the resource delay rate corresponding to each timestamp, and use the overall schedule deviation as the dependent variable, and the stress ratio, environmental index, resource delay rate, and process schedule deviation as independent variables respectively to conduct Granger causality tests, and obtain the Granger causality test results between each independent variable and the overall schedule deviation; Taking each independent variable and the dependent variable as nodes respectively, construct edges between each node and the overall schedule deviation based on the Granger causality test results to obtain the corresponding DAG, and obtain the reasons for the overall schedule deviation based on the DAG.

[0006] In an alternative embodiment of the present application, the method further includes: At the prediction moment, based on the BIM model data or sensor monitoring data, obtain the construction time of each process corresponding to the prediction moment, and determine the corresponding construction stage based on the construction time of each process and the total construction period; wherein, the construction stage includes: the foundation construction stage, the superstructure construction stage, and the bridge deck system construction stage; Determine the process noise covariance matrix based on the construction stage where the prediction moment is located, which is achieved through the following formula:

[0007] Wherein, Q k is the process noise covariance matrix, I b is the identity matrix of the BIM planned schedule, I s1 is the identity matrix of the measured schedule, I s2 is the identity matrix of the stress ratio, I e is the identity matrix of the environmental index, p is the construction stage indicator, indicates that the construction stage is the foundation construction stage, indicates that the construction stage is the superstructure construction stage, indicates that the construction stage is the bridge deck system construction stage.

[0008] In an alternative embodiment of the present application, the method further includes: Based on the BIM model data, obtain the time sequence of each process and the minimum time interval between adjacent processes as the BIM time sequence constraint, and obtain the stress interval of each process as the BIM mechanical constraint; Construct a BIM constraint set based on the BIM time sequence constraint and the BIM mechanical constraint; Adjust the Kalman gain based on the BIM constraint set, which is achieved through the following method: The observed values in the observation matrix are respectively tested by using BIM time sequence constraints and BIM mechanical constraints to obtain corresponding test results; The Kalman gain is adjusted based on the test results to obtain the corresponding adjusted Kalman gain.

[0009] In an alternative embodiment of the present application, the observed values in the observation matrix are respectively tested by using BIM time sequence constraints and BIM mechanical constraints to obtain corresponding test results, including: For the BIM time sequence constraint test, it is required that the observed values of the BIM planned progress, the stress ratio, and the environmental index all conform to the BIM time sequence constraints. Based on the BIM model data, the unfinished processes in the time window corresponding to the observed value of the actual progress are obtained, and the BIM time sequence constraint test is performed on each unfinished process to obtain the first test result; For the BIM mechanical constraint test, it is required that the observed values of the BIM planned progress, the actual progress, and the environmental index all conform to the BIM mechanical constraints. The BIM mechanical constraint test is performed on the unfinished processes in the time window corresponding to the observed value of the stress ratio to obtain the second test result; The test result is obtained based on the first test result and the second test result.

[0010] In an alternative embodiment of the present application, the Kalman gain is adjusted based on the test results to obtain the corresponding adjusted Kalman gain, which is achieved through the following formula:

[0011] where represents the weight coefficient of the i th kind of data in the observation matrix; represents the weight coefficient matrix composed of the weight coefficients of various data in the observation matrix; represents that the observed value of the i th kind of data does not conform to the corresponding j th BIM constraint, m represents the number of corresponding BIM constraints; is an indicator function, and when the observed value of the i th kind of data does not conform to the BIM constraint, its value is 1, and when the observed value of the i th kind of data conforms to the constraint, its value is 0; represents the Kalman gain before adjustment, represents the adjusted Kalman gain, represents the Hadamard product, that is, element-by-element multiplication of matrices.

[0012] In an alternative embodiment of the present application, taking each independent variable and dependent variable as nodes, edges between each node and the overall progress deviation are constructed based on the Granger causality test results to obtain the corresponding DAG, including: For each independent variable node, add at least one corresponding attribute; For any independent variable, if the independent variable is the Granger cause of the dependent variable, construct an edge between the independent variable and the dependent variable, and use the direct contribution degree corresponding to the independent variable as the weight of the corresponding edge to obtain the DAG.

[0013] In an alternative embodiment of the present application, the reasons for the overall progress deviation are obtained based on the DAG, including: Traverse the DAG, and select the independent variables corresponding to the edges with weights within the preset interval as the basis for progress deviation; Based on the BIM model data, obtain the process details in the time window corresponding to the progress deviation basis, and determine the reasons for the overall progress deviation.

[0014] In a second aspect, an embodiment of the present application provides a BIM-based bridge construction progress monitoring system, including: An observation matrix acquisition module, configured to obtain an observation matrix based on the BIM model data and sensor monitoring data of the target bridge; where each row of the observation matrix corresponds to the BIM planned progress, measured progress, stress ratio, and environmental index at the corresponding timestamp; A fusion matrix acquisition module, configured to input the observation matrix into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, determine the process noise covariance matrix based on the construction stage at the prediction moment, and predict the corresponding prediction matrix. In the update stage, adjust the Kalman gain based on the BIM constraint set, and update the prediction matrix to obtain the fusion matrix; A causality test result acquisition module, configured to obtain the overall progress deviation and the corresponding process progress deviation based on the BIM planned progress and measured progress in the fusion matrix, obtain the resource delay rate corresponding to each timestamp based on the construction log, and use the overall progress deviation as the dependent variable, and use the stress ratio, environmental index, resource delay rate, and process progress deviation as independent variables respectively to perform Granger causality test to obtain the Granger causality test results between each independent variable and the overall progress deviation; A progress deviation reason acquisition module, configured to take each independent variable and dependent variable as nodes, construct edges between each node and the overall progress deviation based on the Granger causality test results to obtain the corresponding DAG, and obtain the reasons for the overall progress deviation based on the DAG.

[0015] In an alternative embodiment of the present application, the system further includes a construction stage acquisition module, configured to: At the prediction moment, based on the BIM model data or sensor monitoring data, obtain the construction time of each process corresponding to the prediction moment, and determine the corresponding construction stage based on the construction time of each process and the total construction period; wherein, the construction stage includes: the foundation construction stage, the superstructure construction stage, and the bridge deck system construction stage; Determine the process noise covariance matrix based on the construction stage where the prediction moment is located, which is achieved through the following formula:

[0016] Wherein, Q k is the process noise covariance matrix, I b is the identity matrix of the BIM planned progress, I s1 is the identity matrix of the measured progress, I s2 is the identity matrix of the stress ratio, I e is the identity matrix of the environmental index, p is the construction stage indicator, indicates that the construction stage is the foundation construction stage, indicates that the construction stage is the superstructure construction stage, indicates that the construction stage is the bridge deck system construction stage.

[0017] In an alternative embodiment of the present application, the system further includes a BIM constraint set acquisition module, which is used for: Based on the BIM model data, obtain the time sequence of each process and the minimum time interval between adjacent processes as the BIM time sequence constraint, and obtain the stress interval of each process as the BIM mechanical constraint; Construct a BIM constraint set based on the BIM time sequence constraint and the BIM mechanical constraint; Adjust the Kalman gain based on the BIM constraint set, which is achieved through the following method: Respectively use the BIM time sequence constraint and the BIM mechanical constraint to check the observed values in the observation matrix, and obtain the corresponding inspection results; Adjust the Kalman gain based on the inspection results to obtain the corresponding adjusted Kalman gain.

[0018] In an alternative embodiment of the present application, respectively using the BIM time sequence constraint and the BIM mechanical constraint to check the observed values in the observation matrix, and obtaining the corresponding inspection results, includes: For the BIM time-series constraint test, make the observed values of the BIM planned progress, the stress ratio, and the environmental index all comply with the BIM time-series constraints. Based on the BIM model data, obtain the unfinished processes in the time window corresponding to the observed value of the actual progress, and perform the BIM time-series constraint test on each unfinished process to obtain the first test result; For the BIM mechanical constraint test, make the observed values of the BIM planned progress, the actual progress, and the environmental index all comply with the BIM mechanical constraints. Perform the BIM mechanical constraint test on the unfinished processes in the time window corresponding to the observed value of the stress ratio to obtain the second test result; Obtain the test result based on the first test result and the second test result.

[0019] In an alternative embodiment of the present application, adjust the Kalman gain based on the test result to obtain the corresponding adjusted Kalman gain, which is achieved through the following formula:

[0020] Where, represents the weight coefficient of the i th type of data in the observation matrix, represents the weight coefficient matrix composed of the weight coefficients of various types of data in the observation matrix; represents that the observed value of the i th type of data does not comply with the corresponding j th BIM constraint, m represents the quantity of the corresponding BIM constraint; is an indicator function, and when the observed value of the i th type of data does not comply with the BIM constraint, its value is 1, and when the observed value of the i th type of data complies with the constraint, its value is 0; represents the Kalman gain before adjustment, represents the adjusted Kalman gain, represents the Hadamard product, that is, element-wise multiplication of matrices.

[0021] In an alternative embodiment of the present application, take each independent variable and the dependent variable as nodes respectively, and construct edges between each node and the overall progress deviation based on the Granger causality test result to obtain the corresponding DAG, including: For each independent variable node, add the corresponding at least one attribute; For any independent variable, if the independent variable is the Granger cause of the dependent variable, then construct an edge between the independent variable and the dependent variable, and use the direct contribution degree corresponding to the independent variable as the weight of the corresponding edge to obtain the DAG.

[0022] In an alternative embodiment of the present application, the reasons for the overall schedule deviation are obtained based on the DAG, including: Traverse the DAG, and select the independent variables corresponding to the edges with weights within a preset range as the basis for schedule deviation; Obtain the process details in the time window corresponding to the schedule deviation basis based on the BIM model data, and determine the reasons for the overall schedule deviation.

[0023] In a third aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements any one of the above-mentioned BIM-based bridge construction progress monitoring methods.

[0024] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the above-mentioned BIM-based bridge construction progress monitoring methods.

[0025] In a fifth aspect, the present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements any one of the above-mentioned BIM-based bridge construction progress monitoring methods.

[0026] The solution provided by the embodiments of the present application accurately fuses the BIM model data and sensor monitoring data in the bridge construction process, that is, uses Kalman filtering to dynamically fuse the BIM planned progress, measured progress, stress ratio, and environmental index. Different process noise covariances are considered in the prediction stage, and the Kalman gain is adjusted based on the BIM constraint set in the update stage; and taking the overall schedule deviation as the dependent variable, and taking the stress ratio, environmental index, resource delay rate, and process schedule deviation as independent variables respectively, perform Granger causality test to obtain the Granger causality test results between each independent variable and the overall schedule deviation, and then construct the edges between each node and the overall schedule deviation based on the Granger causality test results to obtain the corresponding DAG; finally, obtain the reasons for the overall schedule deviation based on the DAG. This solution accurately fuses the BIM model data and sensor monitoring data, can obtain accurate overall schedule deviation, and constructs a DAG between the overall schedule deviation and each quantitative information, and can accurately obtain the detailed quantitative information causing the overall schedule deviation, so as to provide an effective basis for subsequent construction decisions. Description of the Drawings

[0027] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0028] Figure 1 It is a schematic flow chart of a BIM-based bridge construction progress monitoring method provided by the present invention; Figure 2 It is a structural block diagram of a BIM-based bridge construction progress monitoring system provided by the present invention; Figure 3 It is a schematic structural diagram of an electronic device provided by the present invention. Specific embodiments

[0029] Figure 1 It is a schematic flow chart of a BIM-based bridge construction progress monitoring method provided by an embodiment of the present application. As Figure 1 shown, the method may include: Step S101, based on the BIM model data and sensor monitoring data of the target bridge, obtain an observation matrix; each row of the observation matrix corresponds to the BIM planned progress, measured progress, stress ratio, and environmental index at the corresponding timestamp.

[0030] Among them, the target bridge is the bridge that is under construction and requires construction progress monitoring.

[0031] Among them, BIM (Building Information Modeling) model data is the core carrier of the building information model. It integrates the information of the entire life cycle of the building project in a digital way to form a three-dimensional visual parametric model. During the construction process, the timing information, structural information, and mechanical information of each process and each workpiece can be obtained through the BIM model data.

[0032] Sensor data refers to the data collected by sensors installed on bridge components. These sensors include stress sensors that collect stress data of key bridge nodes, environmental sensors that collect construction environment data (which can include temperature sensors and wind speed sensors, etc.), and RFID (RadioFrequency Identification) tags on components that collect data from the time the component enters the factory to the completion of assembly.

[0033] Specifically, first obtain the original data of the BIM model data and sensor data, and then set a fixed time window (i.e., preset a time period). For example, this time window can be 15 minutes or one hour, and the size of the time window can be selected according to the computing power. Collect and align different types of original data according to the time window, and assign corresponding timestamps to each time window in chronological order, then the observation matrix for subsequent Kalman filtering can be obtained. It can be understood that each timestamp of this observation matrix corresponds to the observed values of four types: BIM planned progress, actual measured progress, stress ratio, and environmental index.

[0034] Specifically, for any BIM planned progress, the planned progress at each moment in its corresponding time window can be obtained, and it is obtained by calculating the average value of the planned progress at each moment. The planned progress at each moment is the ratio of the sum of the construction times of each process at this moment to the total construction period. For any actual measured progress, the actual measured progress at each moment in its corresponding time window can be obtained, and it is obtained by calculating the average value of the actual measured progress at each moment. The actual measured progress at each moment is the ratio of the sum of the construction times recorded by the sensor to the total construction period. For any stress ratio, the stress ratio of the key nodes at each moment in its corresponding time window can be obtained, and it is obtained by calculating the average value of the stress ratios of the key nodes at each moment. The stress ratio at each moment is the ratio of the stress at the key point to the design stress. For any environmental index, the temperature and wind speed at each moment in its corresponding time window can be obtained, and the temperature and wind speed are weighted and summed, and then it is obtained by calculating the average value of the weighted sums at each moment.

[0035] Step S102: Input the observation matrix into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, determine the process noise covariance matrix based on the construction stage at the prediction moment, and predict the corresponding prediction matrix. In the update stage, adjust the Kalman gain based on the BIM constraint set, and update the prediction matrix to obtain the fusion matrix.

[0036] Among them, according to the different construction progress in the entire construction period, the construction stage can be divided into different dimensions. In the embodiment of the present application, the construction stage is divided into: foundation construction stage, superstructure construction stage, and bridge deck system construction stage. In the prediction stage of using Kalman filtering, the influence degrees of different factors on the accuracy of the predicted value are different. For example, in the foundation construction stage, the BIM model data has a higher influence degree on the predicted value. In the superstructure construction stage, the sensor monitoring data (i.e., actual measured progress, stress ratio, and environmental index) has a higher influence degree on the predicted value. And in the bridge deck system construction stage, the environmental index has a higher influence degree on the predicted value. Then, in order to ensure that the process noise covariance matrix is more in line with the actual situation, in the embodiment of the present application, the weights of the influencing factors in different process noise covariance matrices will be adjusted in different construction stages.

[0037] Among them, the BIM constraint set in the embodiments of the present application includes the time sequence constraints or constraint sets of process parts, and also includes the stress intervals of each process, that is, the BIM mechanical constraint set. This BIM constraint set is to split the BIM model data to obtain the process set for construction, obtain the time sequence relationship of each process, and the time sequence relationship between adjacent processes, so as to obtain the BIM time sequence constraints. Further, each process is split into different components, and the stress intervals of the key nodes of each component are obtained, so as to obtain the BIM mechanical constraints. Then, in the update stage of the Kalman filter, through the construction of the BIM constraint set, higher weights are assigned to the observed values that meet the constraints, so that the update process more conforms to the engineering logic under the BIM data model, and provides more accurate output results for subsequent causal analysis.

[0038] Specifically, the Kalman filter algorithm is mainly divided into two steps: prediction and update. In the embodiments of the present application, a preset Kalman filter is used to fuse four types of data: BIM planned progress, measured progress, stress ratio, and environmental index. In the update stage, the state at the current moment (time k, that is, the kth time stamp) is estimated based on the posterior estimate value at the previous moment (time k-1, that is, the (k-1)th time stamp), and the prior estimate value at time k is obtained. In this process, the current construction stage is first obtained, and the process noise covariance matrix required for estimation in the prediction stage is determined based on this construction stage. Q k . In the update stage, the observed value at the current moment is used to correct the estimated value in the prediction stage, the posterior estimate value at the current moment is obtained, and the posterior estimate covariance of the state variable is updated as the input for the next iteration. In this process, it is necessary to adjust the Kalman gain calculation process through the BIM constraint set, that is, through the inspection of the BIM constraint set, the weight of the observed value that meets the constraint is increased, so as to obtain the adjusted Kalman gain.

[0039] Step S103: Based on the BIM planned progress and measured progress in the fusion matrix, obtain the overall progress deviation and the corresponding process progress deviation. Based on the construction log, obtain the resource delay rate corresponding to each time stamp, and use the overall progress deviation as the dependent variable, and the stress ratio, environmental index, resource delay rate, and process progress deviation as independent variables respectively to perform Granger causality test, and obtain the Granger causality test results between each independent variable and the overall progress deviation.

[0040] Among them, the Granger causality test is a statistical hypothesis testing method based on time series, which is used to determine whether the past values of a variable (or time series) have a significant contribution to predicting the future values of another variable. Its core idea is that if the past information of variable X can significantly improve the prediction accuracy of variable Y, then X is considered the "Granger cause" of Y. In the embodiments of this application, the overall progress deviation is used as the dependent variable, and the stress ratio, environmental index, resource delay rate, and process progress deviation are used as independent variables, so as to analyze whether each independent variable is the "Granger cause" of the overall progress deviation respectively.

[0041] Among them, based on the BIM planned progress and the measured progress in the fusion matrix, the overall progress deviation and the corresponding process progress deviation are obtained, including: taking the ratio of the difference between the BIM planned progress and the measured progress corresponding to the same time stamp to the total construction period as the overall progress deviation.

[0042] Among them, based on the BIM planned progress and the measured progress in the fusion matrix, the corresponding process progress deviation is obtained, including: splitting the BIM model data to obtain the data of each process. For any time window corresponding to a time stamp, obtain the BIM planned progress and the measured progress of all started processes in this time window, and take the ratio of the difference between the BIM planned progress and the measured progress of each started process to the designed construction period of this started process as the overall progress deviation. In the embodiments of this application, the designed construction period can be obtained through the design document.

[0043] Among them, based on the construction log, the resource delay rate corresponding to each time stamp is obtained, including: for any time stamp, obtain the construction log of the time window corresponding to this time stamp, and extract the resource delay rate through a preset natural language processing algorithm. For example, mechanical failures result in a 15% time loss, etc.

[0044] Specifically, taking the stress ratio, environmental index, resource delay rate, and process progress deviation as independent variables respectively, a Granger causality test is conducted to determine whether there is a causal relationship between each independent variable and the overall progress deviation. Specifically, calculate the F value between the overall progress deviation and each independent variable respectively, and determine whether each independent variable is the Granger cause of the overall progress deviation based on the F value.

[0045] Specifically, the causal relationship between variables is judged through the following steps: Model construction: establish a regression model of the lag term of the dependent variable Y (overall progress deviation) with respect to the independent variable X (such as stress ratio) (which can be determined by selection through AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion)) and other control variables. Hypothesis testing: test whether the lag term of the independent variable X has a significant incremental contribution to predicting Y. Result output: If the null hypothesis is rejected (i.e., X is the Granger cause of Y), then further calculate the standardized regression coefficient to quantify the direct contribution degree of X to Y.

[0046] Step S104: Respectively take each independent variable and the dependent variable as nodes, and based on the Granger causality test results, construct the edges between each node and the overall progress deviation to obtain the corresponding DAG, and obtain the reasons for the overall progress deviation based on the DAG.

[0047] Specifically, based on the Granger causality test results between each independent variable and the dependent variable, construct the corresponding DAG, and then determine the reasons for the overall progress deviation according to the DAG.

[0048] The solution provided in the embodiment of the present application accurately fuses the BIM model data and sensor monitoring data in the bridge construction process, that is, uses Kalman filtering to dynamically fuse the BIM planned progress, measured progress, stress ratio, and environmental index, considers different process noise covariances in the prediction stage, and adjusts the Kalman gain based on the BIM constraint set in the update stage; and takes the overall progress deviation as the dependent variable, and takes the stress ratio, the environmental index, the resource delay rate, and the process progress deviation as independent variables respectively to conduct Granger causality tests, obtains the Granger causality test results between each independent variable and the overall progress deviation, and then constructs the edges between each node and the overall progress deviation based on the Granger causality test results to obtain the corresponding DAG; finally, obtains the reasons for the overall progress deviation based on the DAG. This solution accurately fuses the BIM model data and sensor monitoring data, can obtain accurate overall progress deviation, and constructs a DAG between the overall progress deviation and each quantitative information, and can accurately obtain the detailed quantitative information causing the overall progress deviation, so as to provide an effective basis for subsequent construction decisions.

[0049] In an alternative embodiment of the present application, the method may further include: At the prediction moment, based on the BIM model data or sensor monitoring data, obtain the construction time of each process corresponding to the prediction moment, and determine the corresponding construction stage based on the construction time of each process and the total construction period; wherein, the construction stage includes: foundation construction stage, superstructure construction stage, and deck system construction stage; Determine the process noise covariance matrix based on the construction stage at the prediction moment, which is achieved through the following formula:

[0050] Wherein, Q k is the process noise covariance matrix, I b is the identity matrix of the BIM planned schedule, I s1 is the identity matrix of the measured progress, I s2 is the identity matrix of the stress ratio, I e is the identity matrix of the environmental index, p is the construction stage indicator, indicating that the construction stage is the foundation construction stage, indicating that the construction stage is the superstructure construction stage, indicating that the construction stage is the bridge deck system construction stage.

[0051] Specifically, the division of the construction stage can have multiple granularities. For example, on the basis of being divided into the foundation construction stage, the superstructure construction stage, and the bridge deck system construction stage, the foundation construction stage can further be divided into multiple construction stages according to the progress. Correspondingly, according to the different granularities of the construction stage division, the weights of different types of data in the corresponding process noise covariance matrix equation are also different, so as to realize the dynamic adjustment of the process noise covariance matrix in the prediction stage. This method can make the result obtained by the Kalman filter more accurate.

[0052] In an alternative embodiment of the present application, the method may further include: based on the BIM model data, obtaining the time sequence of each process and the minimum time interval between adjacent processes as the BIM time sequence constraint, and obtaining the stress range of each process as the BIM mechanical constraint; Constructing a BIM constraint set based on the BIM time sequence constraint and the BIM mechanical constraint; Adjusting the Kalman gain based on the BIM constraint set, which is achieved through the following method: Respectively using the BIM time sequence constraint and the BIM mechanical constraint to check the observed values in the observation matrix, and obtaining the corresponding check results; Adjusting the Kalman gain based on the check results to obtain the corresponding adjusted Kalman gain.

[0053] Among them, the sequence of operations refers to the order in which operations start. For example, operation A must start after operation B is completed, or operation A must start after operation B starts, etc. The minimum time interval between adjacent operations refers to the interval time between operations. For example, operation A must start 24 hours after operation B is completed, or operation A must start 2 hours after operation B starts, etc.

[0054] Furthermore, the observed values in the observation matrix are respectively tested using BIM sequence constraints and BIM mechanical constraints to obtain corresponding test results, including: For the BIM sequence constraint test, let the observed values of the BIM planned progress, stress ratio, and environmental index all conform to the BIM sequence constraints. Based on the BIM model data, the unfinished operations in the time window corresponding to the observed value of the actual progress are obtained, and the BIM sequence constraint test is performed on each unfinished operation to obtain the first test result; For the BIM mechanical constraint test, let the observed values of the BIM planned progress, actual progress, and environmental index all conform to the BIM mechanical constraints. The BIM mechanical constraint test is performed on the unfinished operations in the time window corresponding to the observed value of the stress ratio to obtain the second test result; The test result is obtained based on the first test result and the second test result.

[0055] Specifically, the Kalman gain is adjusted based on the test result to obtain the corresponding adjusted Kalman gain, which is achieved through the following formula:

[0056] Among them, represents the weight coefficient of the i -th type of data in the observation matrix, represents the weight coefficient matrix composed of the weight coefficients of various types of data in the observation matrix; represents that the observed value of the i -th type of data does not conform to the corresponding j -th type of BIM constraint, m represents the number of corresponding BIM constraints; is an indicator function, and its value is 1 when the observed value of the i -th type of data does not conform to the BIM constraint, and its value is 0 when the observed value of the i -th type of data conforms to the constraint; represents the Kalman gain before adjustment, represents the adjusted Kalman gain, represents the Hadamard product, that is, element-by-element multiplication of matrices.

[0057] In an alternative embodiment of the present application, taking each independent variable and dependent variable as nodes, edges between each node and the overall schedule deviation are constructed based on the Granger causality test results to obtain the corresponding DAG, including: For each independent variable node, add at least one corresponding attribute; For any independent variable, if the independent variable is the Granger cause of the dependent variable, then construct an edge between the independent variable and the dependent variable, and use the direct contribution degree corresponding to the independent variable as the weight of the corresponding edge to obtain the DAG.

[0058] Further, based on the DAG, obtain the reasons for the overall schedule deviation, including: Traverse the DAG, and select the independent variables corresponding to the edges with weights within a preset interval as the basis for schedule deviation; Based on the BIM model data, obtain the process details in the time window corresponding to the schedule deviation basis, and determine the reasons for the overall schedule deviation.

[0059] Among them, DAG (Directed Acyclic Graph) is a graph structure composed of vertices and directed edges. Its characteristic is that the directions of all edges are arranged in a specific order, and there is no closed-loop path. It has two characteristics: Directedness, the edges in the graph have directionality, representing a one-way relationship from the starting point to the ending point, usually used to describe dependencies or causal relationships. Acyclicity, there is no closed-loop path in the graph, that is, starting from any vertex and advancing along the directed edge, it is impossible to return to the starting point. This feature enables the DAG to avoid the problem of circular dependencies and ensures the clarity and executability of the dependency relationship.

[0060] In the embodiment of the present application, first, define the nodes in the following way: Construct a dependent variable node, that is, the overall schedule deviation (such as the total project duration deviation rate). Construct independent variable nodes: potential influencing factors (such as stress ratio, resource delay rate, environmental index, etc.). Then, determine the edge construction rules in the following way: Through Granger causality test screening, only retain the edges between the independent variables that pass the significance test (such as p≤0.05) and the overall schedule deviation. And set the direction of the edges in the following way: The edges point from the independent variable nodes to the overall schedule deviation node, indicating that "the independent variable affects the dependent variable".

[0061] After the DAG construction is completed, traverse the DAG and filter the critical edges, that is, find the main reasons for the schedule deviation. Starting from the "overall schedule deviation" node, trace back all the edges pointing to this node in reverse. A weight interval (i.e., the direct contribution interval, for example, the weight is greater than 0.3) can be set first, and then traverse the entire DAG to select the edges whose weights fall within the weight interval, obtaining the independent variables that have a significant impact on the overall schedule deviation. For example, two significant edges, the stress ratio (weight = 0.48) and the resource delay rate (weight = -0.35), are filtered out, indicating that these two variables have significant positive and negative impacts on the overall schedule deviation.

[0062] Furthermore, the BIM model data can be further combined to locate the specific processes that affect the overall schedule deviation. According to the lag order (such as lag 1 period) used in the Granger test, determine the time offset of the influence of the independent variable. For example: If the lag order is 1 month, analyze the influence of the independent variable in the current month on the overall schedule deviation in the next month. At the same time, extract the process parameters associated with the key independent variables from the BIM model (such as the time, quality, and resource allocation records of the "concrete pouring process" corresponding to the stress ratio, which can also be added as attributes of the corresponding nodes). Calculate the deviation threshold of the key process parameters. For example, a stress ratio exceeding the design value by 15% results in a construction schedule lag; a resource delay rate exceeding 20% causes a chain delay. In this way, the specific reasons for the overall schedule deviation are determined, providing a data-driven improvement basis for schedule management.

[0063] Figure 2 The structural block diagram of a BIM-based bridge construction schedule monitoring system provided by an embodiment of the present application is shown as Figure 2 shown. The system may include: an observation matrix acquisition module 201, a fusion matrix acquisition module 202, a causal test result acquisition module 203, and a schedule deviation reason acquisition module 204, where: The observation matrix acquisition module 201 is used to obtain an observation matrix based on the BIM model data and sensor monitoring data of the target bridge; each row of the observation matrix corresponds to the BIM planned schedule, measured schedule, stress ratio, and environmental index at the corresponding timestamp; The fusion matrix acquisition module 202 is used to input the observation matrix into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, determine the process noise covariance matrix based on the construction stage at the prediction moment, and predict the corresponding prediction matrix. In the update stage, adjust the Kalman gain based on the BIM constraint set, and update the prediction matrix to obtain the fusion matrix; The causality test result acquisition module 203 is used to obtain the overall schedule deviation and the corresponding process schedule deviation based on the BIM planned schedule and the actual measured schedule in the fusion matrix, obtain the resource delay rate corresponding to each time stamp based on the construction log, and use the overall schedule deviation as the dependent variable, and the stress ratio, environmental index, resource delay rate, and process schedule deviation as independent variables respectively to perform a Granger causality test to obtain the Granger causality test results between each independent variable and the overall schedule deviation; The schedule deviation cause acquisition module 204 is used to construct an edge between each node and the overall schedule deviation based on the Granger causality test results with each independent variable and the dependent variable as nodes, obtain the corresponding DAG, and obtain the cause of the overall schedule deviation based on the DAG.

[0064] The solution provided by the embodiment of the present application accurately fuses the BIM model data and sensor monitoring data in the bridge construction process, that is, dynamically fuses the BIM planned schedule, actual measured schedule, stress ratio, and environmental index using Kalman filtering, considers different process noise covariance matrices in different construction stages during the prediction stage, and adjusts the Kalman gain based on the BIM constraint set during the update stage; and uses the overall schedule deviation as the dependent variable, and the stress ratio, environmental index, resource delay rate, and process schedule deviation as independent variables respectively to perform a Granger causality test to obtain the Granger causality test results between each independent variable and the overall schedule deviation, and then constructs an edge between each node and the overall schedule deviation based on the Granger causality test results to obtain the corresponding DAG; finally, obtains the cause of the overall schedule deviation based on the DAG. This solution accurately fuses the BIM model data and sensor monitoring data, can obtain accurate overall schedule deviation, and constructs a DAG between the overall schedule deviation and each quantization information, and can accurately obtain the detailed quantization information that causes the overall schedule deviation, so as to provide an effective basis for subsequent construction decisions.

[0065] In an alternative embodiment of the present application, the system further includes a construction stage acquisition module for: At the prediction moment, based on the BIM model data or sensor monitoring data, obtain the construction time of each process corresponding to the prediction moment, and determine the corresponding construction stage based on the construction time of each process and the total construction period; where the construction stage includes: the foundation construction stage, the superstructure construction stage, and the deck system construction stage; Determine the process noise covariance matrix based on the construction stage where the prediction moment is located, which is implemented through the following formula:

[0066] Among them, Q k is the process noise covariance matrix,I b is the identity matrix for the BIM planned progress, I s1 is the identity matrix for the measured progress, I s2 is the identity matrix for the stress ratio, I e is the identity matrix for the environmental index, p is the construction stage indicator, indicating that the construction stage is the foundation construction stage, indicating that the construction stage is the superstructure construction stage, indicating that the construction stage is the bridge deck system construction stage.

[0067] In an alternative embodiment of the present application, the system further includes a BIM constraint set acquisition module for: Based on the BIM model data, obtain the time sequence of each process and the minimum time interval between adjacent processes as the BIM time sequence constraint, and obtain the stress interval of each process as the BIM mechanical constraint; Construct a BIM constraint set based on the BIM time sequence constraint and the BIM mechanical constraint; Adjust the Kalman gain based on the BIM constraint set, achieved by the following means: Respectively use the BIM time sequence constraint and the BIM mechanical constraint to check the observed values in the observation matrix, and obtain the corresponding inspection results; Adjust the Kalman gain based on the inspection results to obtain the corresponding adjusted Kalman gain.

[0068] In an alternative embodiment of the present application, respectively use the BIM time sequence constraint and the BIM mechanical constraint to check the observed values in the observation matrix, and obtain the corresponding inspection results, including: For the BIM time sequence constraint check, make the observed values of the BIM planned progress, the stress ratio, and the environmental index all conform to the BIM time sequence constraint. Based on the BIM model data, obtain the unfinished processes in the time window corresponding to the observed value of the measured progress, and conduct a BIM time sequence constraint check on each unfinished process to obtain the first inspection result; For the BIM mechanical constraint check, make the observed values of the BIM planned progress, the measured progress, and the environmental index all conform to the BIM mechanical constraint, and conduct a BIM mechanical constraint check on the unfinished processes in the time window corresponding to the observed value of the stress ratio to obtain the second inspection result; Obtain the inspection result based on the first inspection result and the second inspection result.

[0069] In an alternative embodiment of the present application, the Kalman gain is adjusted based on the inspection result to obtain the corresponding adjusted Kalman gain, which is achieved through the following formula:

[0070] Wherein, represents the weight coefficient of the i th type of data in the observation matrix, represents the weight coefficient matrix composed of the weight coefficients of various types of data in the observation matrix; represents that the observation value of the i th type of data does not conform to the corresponding j th BIM constraint, m represents the number of corresponding BIM constraints; is an indicator function, and when the observation value of the i th type of data does not conform to the BIM constraint, its value is 1, and when the observation value of the i th type of data conforms to the constraint, its value is 0; represents the Kalman gain before adjustment, represents the adjusted Kalman gain, represents the Hadamard product, that is, element-wise multiplication of matrices.

[0071] In an alternative embodiment of the present application, taking each independent variable and dependent variable as nodes, edges between each node and the overall schedule deviation are constructed based on the Granger causality test result to obtain the corresponding DAG, including: For each independent variable node, at least one corresponding attribute is added; For any independent variable, if the independent variable is the Granger cause of the dependent variable, an edge is constructed between the independent variable and the dependent variable, and the direct contribution degree corresponding to the independent variable is used as the weight of the corresponding edge to obtain the DAG.

[0072] In an alternative embodiment of the present application, the reasons for the overall schedule deviation are obtained based on the DAG, including: Traverse the DAG, and select the independent variables corresponding to the edges with weights within the preset interval as the basis for schedule deviation; Based on the BIM model data, obtain the process details in the time window corresponding to the schedule deviation basis, and determine the reasons for the overall schedule deviation.

[0073] Figure 3 Illustrates a schematic diagram of the physical structure of an electronic device, such as Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logical instructions in the memory 330 to execute the BIM-based bridge construction progress monitoring method, which includes: obtaining an observation matrix based on the BIM model data and sensor monitoring data of the target bridge; where each row of the observation matrix corresponds to the BIM planned progress, the measured progress, the stress ratio, and the environmental index at the corresponding timestamp; inputting the observation matrix into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, determine the process noise covariance matrix based on the construction stage at the prediction moment, and predict the corresponding prediction matrix. In the update stage, adjust the Kalman gain based on the BIM constraint set, and update the prediction matrix to obtain a fusion matrix; based on the BIM planned progress and the measured progress in the fusion matrix, obtain the overall progress deviation and the corresponding process progress deviation, obtain the resource delay rate corresponding to each timestamp based on the construction log, and use the overall progress deviation as the dependent variable, and use the stress ratio, the environmental index, the resource delay rate, and the process progress deviation as independent variables respectively to perform Granger causality tests to obtain the Granger causality test results between each independent variable and the overall progress deviation; respectively use each independent variable and the dependent variable as nodes, and based on the Granger causality test results, construct edges between each node and the overall progress deviation to obtain the corresponding DAG, and obtain the reasons for the overall progress deviation based on the DAG.

[0074] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0075] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the BIM-based bridge construction progress monitoring method provided by the above-mentioned various methods. The method includes: obtaining an observation matrix based on the BIM model data and sensor monitoring data of the target bridge; wherein each row of the observation matrix corresponds to the BIM planned progress, measured progress, stress ratio, and environmental index at the corresponding timestamp; inputting the observation matrix into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, determine the process noise covariance matrix based on the construction stage at the prediction moment, and predict the corresponding prediction matrix. In the update stage, adjust the Kalman gain based on the BIM constraint set, and update the prediction matrix to obtain a fusion matrix; obtain the overall progress deviation and the corresponding process progress deviation based on the BIM planned progress and measured progress in the fusion matrix, obtain the resource delay rate corresponding to each timestamp based on the construction log, and use the overall progress deviation as the dependent variable, and use the stress ratio, the environmental index, the resource delay rate, and the process progress deviation as independent variables respectively to perform a Granger causality test to obtain the Granger causality test results between each independent variable and the overall progress deviation; respectively use each independent variable and the dependent variable as nodes, and construct edges between each node and the overall progress deviation based on the Granger causality test results to obtain the corresponding DAG, and obtain the reasons for the overall progress deviation based on the DAG.

[0076] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a BIM-based bridge construction progress monitoring method provided by the above-mentioned various methods. The method includes: based on the BIM model data and sensor monitoring data of the target bridge, obtaining an observation matrix; wherein each row of the observation matrix corresponds to the BIM planned progress, measured progress, stress ratio, and environmental index at the corresponding timestamp; inputting the observation matrix into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, based on the construction stage at the prediction moment, determining the process noise covariance matrix, and predicting to obtain the corresponding prediction matrix. In the update stage, adjusting the Kalman gain based on the BIM constraint set, and updating the prediction matrix to obtain a fusion matrix; based on the BIM planned progress and measured progress in the fusion matrix, obtaining the overall progress deviation and the corresponding process progress deviation, based on the construction log, obtaining the resource delay rate corresponding to each timestamp, and using the overall progress deviation as the dependent variable, and using the stress ratio, the environmental index, the resource delay rate, and the process progress deviation as independent variables respectively, performing a Granger causality test to obtain the Granger causality test results between each independent variable and the overall progress deviation; respectively using each independent variable and the dependent variable as nodes, based on the Granger causality test results, constructing edges between each node and the overall progress deviation to obtain the corresponding DAG, and based on the DAG, obtaining the reasons for the overall progress deviation.

[0077] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0078] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, also by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A bridge construction progress monitoring method based on BIM, characterized in that: include: Based on the BIM model data and sensor monitoring data of the target bridge, the observation matrix is ​​obtained; Each row of the observation matrix corresponds to the BIM planned progress, measured progress, stress ratio and environmental index at the corresponding timestamp; The observation matrix is ​​input into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, the process noise covariance matrix is ​​determined based on the construction stage at the prediction moment, and the corresponding prediction matrix is ​​predicted. In the update stage, the Kalman gain is adjusted based on the BIM constraint set, and the prediction matrix is ​​updated to obtain a fusion matrix. Based on the BIM planned progress and the measured progress in the fusion matrix, the overall progress deviation and the corresponding process progress deviation are obtained, and based on the construction log, the resource delay rate corresponding to each of the timestamps is obtained, and the overall progress deviation is used as the dependent variable, and the stress ratio, the environmental index, the resource delay rate and the process progress deviation are used as independent variables to perform a Granger causality test to obtain the Granger causality test results between each variable and the overall progress deviation; Each variable and the dependent variable are used as nodes respectively, and the edge between each node and the overall progress deviation is constructed based on the Granger causality test result to obtain the corresponding DAG, and the cause of the overall progress deviation is obtained based on the DAG.

2. The method according to claim 1, characterized in that The method further comprises: At the predicted moment, based on the BIM model data or the sensor monitoring data, the construction time of each process corresponding to the predicted moment is obtained, and the corresponding construction stage is determined based on the construction time of each process and the total construction period; wherein the construction stage includes: foundation construction stage, superstructure construction stage and bridge deck system construction stage; The process noise covariance matrix is ​​determined based on the construction stage at the prediction time, and is implemented by the following formula: in, Q k is the process noise covariance matrix, I b is the unit matrix of BIM planning schedule, I s1 is the identity matrix of the measured progress, I s2 is the identity matrix of the stress ratios, I e is the identity matrix of the environmental index, p is the construction stage indicator, Indicates that the construction stage is the basic construction stage. Indicates that the current construction stage is the superstructure construction stage. It indicates that the current construction phase is the bridge deck construction phase.

3. The method according to claim 1, characterized in that The method further includes: based on the BIM model data, obtaining the timing of each process and the minimum time interval between adjacent processes as BIM timing constraints, and obtaining the stress interval of each process as BIM mechanical constraints; Constructing the BIM constraint set based on the BIM timing constraint and the BIM mechanical constraint; The adjustment of the Kalman gain based on the BIM constraint set is achieved in the following manner: Using the BIM timing constraint and the BIM mechanical constraint to test the observation values ​​in the observation matrix respectively, and obtaining corresponding test results; The Kalman gain is adjusted based on the test result to obtain a corresponding adjusted Kalman gain.

4. The method according to claim 3, characterized in that The respectively using the BIM timing constraint and the BIM mechanical constraint to check the observation values ​​in the observation matrix to obtain corresponding test results includes: For the BIM timing constraint check, the observed value of the BIM planned progress, the observed value of the stress ratio, and the observed value of the environmental index are all made to meet the BIM timing constraint, and the unfinished process in the time window corresponding to the observed value of the measured progress is obtained based on the BIM model data, and the BIM timing constraint check is performed on each unfinished process to obtain a first test result; For the BIM mechanical constraint check, the observed value of the BIM planned progress, the observed value of the measured progress, and the observed value of the environmental index are all made to conform to the BIM mechanical constraint, and the BIM mechanical constraint check is performed on the unfinished process in the time window corresponding to the observed value of the stress ratio to obtain a second test result; The inspection result is obtained based on the first inspection result and the second inspection result.

5. The method according to claim 3, characterized in that: The Kalman gain is adjusted based on the test result to obtain the corresponding adjusted Kalman gain, which is achieved by the following formula: in, represents the first i The weight coefficient of the data, represents a weight coefficient matrix composed of weight coefficients of various data in the observation matrix; Indicates i The observed value of the data does not match the corresponding j BIM constraints, m Indicates the number of corresponding BIM constraints; is the indicator function, and i When the observed value of the data does not meet the BIM constraint, its value is 1. i When the observed value of the data meets the constraints, its value is 0; represents the Kalman gain before adjustment, represents the adjusted Kalman gain, represents the Hadamard product, which is the element-wise multiplication of matrices.

6. The method according to claim 1, characterized in that The respective variables and the dependent variable are used as nodes, and the edges between each node and the overall progress deviation are constructed based on the Granger causality test result to obtain the corresponding DAG, including: For each variable node, add at least one corresponding attribute; For any independent variable, if the independent variable is the Granger cause of the dependent variable, an edge is constructed between the independent variable and the dependent variable, and the direct contribution corresponding to the independent variable is used as the weight of the corresponding edge to obtain the DAG.

7. The method according to claim 1, characterized in that The reasons causing the overall progress deviation are obtained based on the DAG, including: Traversing the DAG, and selecting the independent variables corresponding to the edges whose weights are within a preset interval as the progress deviation basis; The progress deviation is obtained based on the BIM model data according to the process details in the corresponding time window, and the cause of the overall progress deviation is determined.

8. A BIM-based bridge construction progress monitoring system, characterized in that: include: An observation matrix acquisition module is used to acquire an observation matrix based on the BIM model data and sensor monitoring data of the target bridge; each row of the observation matrix corresponds to the BIM planned progress, measured progress, stress ratio and environmental index at a corresponding timestamp; A fusion matrix acquisition module is used to input the observation matrix into a preset Kalman filter. In the prediction stage, for each row of the observation matrix, the process noise covariance matrix is ​​determined based on the construction stage at the prediction moment, and the corresponding prediction matrix is ​​predicted. In the update stage, the Kalman gain is adjusted based on the BIM constraint set, and the prediction matrix is ​​updated to obtain a fusion matrix. A causal test result acquisition module is used to acquire the overall progress deviation and the corresponding process progress deviation based on the BIM planned progress and the measured progress in the fusion matrix, acquire the resource delay rate corresponding to each of the timestamps based on the construction log, and perform a Granger causal test with the overall progress deviation as the dependent variable, the stress ratio, the environmental index, the resource delay rate and the process progress deviation as independent variables, respectively, to acquire the Granger causal test results between the respective variables and the overall progress deviation; The progress deviation cause acquisition module is used to use each variable and the dependent variable as nodes, construct edges between each node and the overall progress deviation based on the Granger causality test result, obtain the corresponding DAG, and obtain the cause of the overall progress deviation based on the DAG.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images