Building construction risk early warning method and system based on BIM

Abstract

The invention relates to the technical field of construction risk early warning, in particular to a BIM-based building construction risk early warning method and system, and the method comprises the following steps: constructing an incidence matrix between risk nodes based on time and space dimensions for the risk factor of each node in a construction process, calculating the risk propagation intensity value between the nodes, and calculating the risk propagation intensity value between the nodes; and judging the risk association relationship between the nodes, performing grading processing on the risk coupling degree according to the propagation rate, and outputting a risk coupling matrix value. According to the method, a high-risk area is extracted by combining spatial distribution data, dynamic partition management is achieved, dynamic influences of environmental variables such as temperature, humidity and vibration are quantified, the complex relation between environmental conditions and risk states is revealed, the accuracy and real-time performance of risk assessment are optimized, and the risk assessment accuracy is improved by analyzing the risk transfer trend and propagation path changes. And dynamically adjusting node priorities and resource allocation, updating the influence of newly added risk signals in real time, and realizing full-process dynamic optimization of construction risk early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of construction risk early warning, and in particular to a BIM-based construction risk early warning method and system. Background Art

[0002] The field of construction risk early warning technology encompasses various safety risks that may occur during construction, as well as their early warning management methods. The core of this technical field is the use of information technology to identify, analyze, and manage risks at construction sites. Construction risk early warning technology primarily involves the collection of construction environment data, risk factor analysis models, risk level assessment criteria, and the generation and delivery of early warning plans. This overall technical field also includes the research and application of dynamic risk monitoring technologies and emergency response strategies, which are closely related to construction progress, quality, and safety.

[0003] The BIM-based construction risk early warning method and system refers to a method and system for identifying and warning construction risks through building information modeling technology. This patent covers the collection of risk data during the construction phase, BIM-based risk factor modeling and assessment, and analysis of the correlation between construction processes and dynamic changes in risks. Specifically, by integrating construction data, environmental data, and risk indicators into the BIM model, and combining construction information with early warning rules, risk identification and early warning signal generation are achieved. Furthermore, risk grading standards are used to quantitatively assess the risk level of the construction process, ensuring the timely discovery and handling of potential risks at the construction site.

[0004] Existing technologies typically use static analysis to address the patterns of risk propagation in construction processes. These methods lack dynamic assessments of the intensity and rate of risk propagation between nodes, making it difficult to accurately capture changing trends in risk within complex construction environments. During the risk grading process, most technologies fail to incorporate spatial distribution data from nodes and rely solely on a single indicator to assess risk levels, ignoring the regional characteristics of the construction environment. This results in low applicability of risk grading. Regarding the introduction of environmental variables, existing methods fail to dynamically capture the real-time impact of environmental parameters such as temperature, humidity, and vibration on risk. Most analyses rely on fixed parameter weight models, making it difficult to reflect the complex dynamic relationship between environmental conditions and risk status. When responding to new risk signals, existing technologies lack a rapid response mechanism, making it impossible to achieve real-time updates of risk priorities and status levels at construction nodes, which can easily lead to delayed risk management during the construction process. These issues increase the difficulty of addressing potential risks in actual construction scenarios and reduce the safety and efficiency of construction sites. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a BIM-based construction risk warning method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a BIM-based construction risk early warning method, comprising the following steps: S1: Based on the risk factors of each node in the construction process, a correlation matrix between risk nodes is constructed based on the time and space dimensions. The risk propagation intensity value between nodes is calculated, the risk correlation relationship between nodes is determined, the risk coupling degree is graded according to the propagation rate, and the risk coupling matrix value is output; S2: Based on the risk coupling matrix value, a risk propagation threshold is set, and nodes with higher intensity in the risk propagation path are extracted. Combined with the spatial distribution data, the risk level of the area surrounding the node is calculated. The construction area is divided according to the risk level, and the regional risk level boundaries are demarcated, and the risk level partition data is output; S3: Extracting environmental variables in the construction area based on the risk level zoning data, quantifying the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level in the area, analyzing the correlation between environmental variables and risk status, and generating dynamic impact values of environmental variables; S4: Analyze the node risk status change trend using the dynamic impact value of the environmental variable, calculate the node risk transfer probability and evaluate the dynamic change of the risk intensity in the propagation path, adjust the node priority and resource allocation ratio according to the change results, and generate a risk status dynamic change value; S5: Analyze the propagation impact of the new risk signal on the original node based on the dynamic change value of the risk status, recalculate the risk priority and status level of the construction node, update the global risk status based on the propagation path, and output the risk priority and status update value of the construction node.

[0007] As a further solution of the present invention, the risk coupling matrix value includes the risk propagation intensity value between nodes, the node risk correlation degree value, and the risk propagation rate level value; the risk level partition data includes the regional risk level identification, regional boundary information, and key node regional distribution; the dynamic impact value of the environmental variable includes the temperature impact weight, the humidity impact weight, and the vibration impact weight; the dynamic change value of the risk status includes the node risk change trend value, the node risk transfer probability value, and the resource allocation adjustment ratio; the construction node risk priority and status update value includes the node priority adjustment value, the node status level change value, and the global risk update data.

[0008] As a further solution of the present invention, for the risk factors of each node in the construction process, a correlation matrix between risk nodes is constructed based on the time and space dimensions, the risk propagation intensity value between the nodes is calculated, the risk correlation relationship between the nodes is determined, and the risk coupling degree is graded according to the propagation rate. The specific steps of outputting the risk coupling matrix value are as follows: S101: Based on the risk factors of nodes in the construction process, extract the time attributes and spatial location data of each node, calculate the time series difference value, analyze the spatial distance, cross-compare the difference value and distance parameters, analyze the risk association relationship between nodes, calibrate the association parameters to construct the association matrix between nodes, and generate node association relationship data; S102: Based on the node association relationship data, the risk propagation intensity between nodes is calculated, and node pairs with propagation intensity values greater than a set threshold are screened. The strong and weak relationships are calculated by the calibration values of the associated nodes and the difference in propagation intensity. The risk propagation characteristics between the nodes are classified and recorded to generate node risk propagation intensity data. S103: Based on the node risk propagation intensity data and combined with the propagation rate, the cumulative risk value on the path is calculated, the risk gradient is defined according to the cumulative risk value, the coupling degree is graded and marked, and the propagation path information of the graded corresponding nodes is recorded at the same time, and the risk coupling matrix value is output.

[0009] As a further solution of the present invention, based on the risk coupling matrix value, a risk propagation threshold is set, and nodes with higher intensity in the risk propagation path are extracted. Combined with the spatial distribution data, the risk level of the area surrounding the node is calculated. The construction area is divided according to the risk level and the regional risk level boundary is calibrated. The specific steps of outputting the risk level partition data are as follows: S201: Based on the risk coupling matrix value, a reference threshold value of the propagation strength is set, the strength value of each node in the matrix is calculated one by one, and node pairs with strength values greater than the threshold are screened out. The associated parameters of the risk propagation path in the node pairs are analyzed, the screening results are marked and node group data is established to generate high-intensity node group data; S202: Based on the high-intensity node group data, extract the spatial location parameters and distribution relationship of the nodes, calculate the distance weights and distribution densities between the nodes one by one, analyze the impact of the spatial distribution on the risk value in combination with the influence radius around the nodes, delineate the node spatial distribution association information within the area, and generate node spatial distribution impact data; S203: Based on the node spatial distribution impact data, combined with the node risk propagation intensity and regional distribution relationship, calculate the comprehensive risk value of the region, set the gradient level according to the risk value, grade the gradient level information and calibrate the regional boundary range to generate risk level zoning data.

[0010] As a further solution of the present invention, based on the risk level zoning data, environmental variables of the construction area are extracted, the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level in the area are quantified, and the correlation between environmental variables and risk status is analyzed. The specific steps for generating dynamic impact values of environmental variables are as follows: S301: Based on the risk level partition data, extract the spatial range and distribution information of the nodes in the area, match the environmental variable data such as temperature, humidity, and vibration, classify the risk level of the area and the environmental variable values one by one, establish an initial association between the environmental variables and the partition data, and generate initial distribution data of the environmental variables; S302: Based on the initial distribution data of the environmental variables, calculate the degree of influence of the change amplitude of the environmental variables on the regional risk level, analyze the matching relationship between the variables and the risk level, extract the values with larger change amplitudes in the variables and assign dynamic weights, calibrate the influence range and weight information of different variables, and generate dynamic weight data of environmental variables; S303: Based on the dynamic weight data of the environmental variables, calculate the dynamic correlation relationship between the environmental variables and the regional risk status, extract the parameter trend of the variables and the risk level changes, calibrate the risk impact value of the dynamic change of the variables, and integrate the variable association results in the region to generate the dynamic impact value of the environmental variables.

[0011] As a further solution of the present invention, the dynamic impact value of the environmental variable is used to analyze the node risk status change trend, calculate the node risk transfer probability and evaluate the dynamic change of the risk intensity in the propagation path, and adjust the node priority and resource allocation ratio according to the change results. The specific steps of generating the dynamic change value of the risk status are as follows: S401: Based on the dynamic impact value of the environmental variable, extract the time series risk status data of the node, calculate the change range of the risk status in segments, analyze the risk rate in each time period, calibrate the change trend of the node in the time dimension, and record the trend data to generate node risk status trend data; S402: Based on the node risk status trend data, calculate the risk status transition probability between nodes, extract the transition path data of adjacent nodes, perform cumulative calculations on the transition intensity, and perform comparative analysis based on the risk intensity change parameters within the path to generate node risk transition probability data; S403: Based on the node risk transfer probability data, calculate the node priority adjustment factor and the resource allocation ratio parameter, proportionally match the node risk change parameter with the resource utilization data, calibrate the resource allocation adjustment value and the node priority dynamic change parameter, and generate a risk status dynamic change value.

[0012] As a further solution of the present invention, the risk state transition probability calculation formula is specifically: ; in, Representative Node and nodes The risk state transition probability between and Represents nodes and nodes In the The risk status value of each time period, Indicates time period The weight value of Indicates the total number of time periods between nodes, Indicates the sum of all time periods. Represents the sum of squared weights.

[0013] As a further solution of the present invention, the specific steps of analyzing the propagation impact of the new risk signal on the original node based on the dynamic change value of the risk status, recalculating the risk priority and status level of the construction node, updating the global risk status based on the propagation path, and outputting the risk priority and status update value of the construction node are as follows: S501: Based on the risk status dynamic change value, extract the propagation path and impact range of the new risk signal, calculate the risk association strength value of the new signal on the existing node, analyze the impact of the signal on the node risk status change, record the node change parameters and generate analysis results, and generate the new risk signal impact parameter; S502: Based on the newly added risk signal impact parameters, recalculate the risk priority values of the affected nodes, analyze the difference between the priority adjustment value and the original status level, calibrate the new status level parameters of the nodes, dynamically update the priority and level of the node data, and generate node priority and status level data; S503: Based on the node priority and status level data, combined with the risk propagation path, the global risk status change parameters are calculated, the status relationship and priority distribution between nodes are updated, the dynamic adjustment information of the nodes in the global network is recorded, and the construction node risk priority and status update value are generated.

[0014] As a further solution of the present invention, the risk association strength value calculation formula is specifically: ; in, Represents a newly added signal pair node and nodes The risk correlation strength value between and Represents the newly added signal in the time period For Node and nodes The impact strength, Indicates time period The weight value of Indicates the total number of time periods, Indicates the cumulative sum of all time periods. Represents the cumulative sum of weighted squares.

[0015] The BIM-based construction risk early warning system includes: The risk association module targets the risk factors of each node in the construction process, constructs an association matrix between risk nodes based on time and space dimensions, calculates the risk propagation intensity value between nodes, grades the risk coupling degree according to the propagation rate, and outputs the risk coupling matrix value; The regional division module sets the risk propagation threshold based on the risk coupling matrix value, extracts nodes with higher intensity in the risk propagation path, calculates the risk level of the area around the node, divides the construction area according to the risk level, demarcates the regional risk level boundary, and outputs the risk level partition data; The environmental weight module extracts environmental variables of the construction area based on the risk level zoning data, and generates dynamic impact values of environmental variables by quantifying the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level in the area; The state analysis module uses the dynamic impact value of the environmental variable to analyze the node risk state change trend, calculate the node risk transfer probability and evaluate the dynamic change of the risk intensity in the propagation path, and generate a risk state dynamic change value; The priority update module analyzes the propagation impact of the new risk signal on the original node according to the dynamic change value of the risk status, recalculates the risk priority and status level of the construction node, and outputs the risk priority and status update value of the construction node.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, high-risk areas are extracted by combining spatial distribution data to realize dynamic zoning management, quantify the dynamic impact of environmental variables such as temperature, humidity, and vibration, reveal the complex relationship between environmental conditions and risk status, optimize the accuracy and real-time performance of risk assessment, and dynamically adjust node priorities and resource allocation by analyzing risk transfer trends and changes in transmission paths. The impact of new risk signals is updated in real time, thus realizing dynamic optimization of the entire process of construction risk warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 Schematic diagram of the steps of the present invention; Figure 2 is a flow chart of the steps of S1 of the present invention; Figure 3 This is a flow chart of the steps of S2 of the present invention; Figure 4This is a flow chart of the steps of S3 of the present invention; Figure 5 This is a flow chart of the steps of S4 of the present invention; Figure 6 This is a flow chart of the steps of S5 of the present invention; Figure 7 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0020] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0021] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0022] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0023] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0024] See also Figure 1 ,The BIM-based building construction risk early warning method includes the following steps: S1: Based on the risk factors of each node in the construction process, a correlation matrix between risk nodes is constructed based on the time and space dimensions. The risk propagation intensity value between nodes is calculated, the risk correlation relationship between nodes is determined, the risk coupling degree is graded according to the propagation rate, and the risk coupling matrix value is output; S2: Based on the risk coupling matrix value, a risk propagation threshold is set, and nodes with higher intensity in the risk propagation path are extracted. Combined with the spatial distribution data, the risk level of the area surrounding the node is calculated. The construction area is divided according to the risk level, and the regional risk level boundaries are demarcated, and the risk level zoning data is output; S3: Extract environmental variables from the construction area based on risk level zoning data. By quantifying the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level within the area, analyze the correlation between environmental variables and risk status, and generate dynamic impact values of environmental variables. S4: Use the dynamic impact value of environmental variables to analyze the trend of node risk status changes, calculate the node risk transfer probability and evaluate the dynamic changes in risk intensity in the propagation path. Adjust the node priority and resource allocation ratio based on the change results to generate a dynamic change value of the risk status; S5: Analyze the impact of the new risk signal on the original node according to the dynamic change value of the risk status, recalculate the risk priority and status level of the construction node, update the global risk status based on the propagation path, and output the risk priority and status update value of the construction node.

[0025] The risk coupling matrix values include the risk transmission intensity value between nodes, the node risk correlation degree value, and the risk transmission rate level value. The risk level zoning data includes the regional risk level identification, regional boundary information, and key node regional distribution. The dynamic impact value of environmental variables includes the temperature impact weight, humidity impact weight, and vibration impact weight. The dynamic change value of risk status includes the node risk change trend value, the node risk transfer probability value, and the resource allocation adjustment ratio. The construction node risk priority and status update value includes the node priority adjustment value, the node status level change value, and the global risk update data.

[0026] See also Figure 2 , the specific steps of S1 are: S101: Based on the risk factors of nodes in the construction process, extract the time attributes and spatial location data of each node, calculate the time series difference value, analyze the spatial distance, cross-compare the difference value and distance parameters, analyze the risk association relationship between nodes, calibrate the association parameters to construct the association matrix between nodes, and generate node association relationship data; The time attributes are quantified as continuous variables in the form of timestamps. The precise coordinate values of the spatial position are obtained through a total station or a three-dimensional positioning system. When calculating the time series difference value, the time attributes of adjacent nodes are interpolated to obtain the time interval. At the same time, when calculating the spatial distance, the spatial position difference between nodes is measured using the three-dimensional Euclidean distance formula. The difference values and distance parameters are statistically summarized and standardized respectively. The risk correlation between nodes is analyzed through cross-comparison operations on the standardized difference value matrix and distance matrix, and the correlation feature quantities between nodes are extracted. The correlation feature quantities are used as weight parameters to calibrate the strength of the correlation, construct a risk correlation matrix, and generate node correlation relationship data.

[0027] S102: Based on the node association data, the risk propagation intensity between nodes is calculated, and node pairs with a propagation intensity value greater than a set threshold are screened. The strength relationship is calculated by the calibration value of the associated nodes and the difference in propagation intensity. The risk propagation characteristics between each node are classified and recorded to generate node risk propagation intensity data; Calculate the risk propagation intensity between nodes according to the formula ; Calculate the risk propagation intensity between nodes.

[0028] Where, Representation node and nodes The intensity of risk transmission between Representation node and The time propagation coefficient between Representation node and The spatial propagation coefficient between .

[0029] The time propagation coefficient is calculated by measuring the inverse of the time difference between two nodes, for example, and The time is sky, Day, time propagation coefficient The spatial propagation coefficient is calculated by the spatial distance of the three-dimensional coordinate difference and then the inverse is taken, such as the node The coordinates are ,node The coordinates are , spatial distance , spatial propagation coefficient . Risk transmission intensity This result indicates that the inter-node transmission intensity is low and the direct risk transmission effect between nodes is weak.

[0030] S103: Based on the node risk propagation intensity data and the propagation rate, the cumulative risk value on the path is calculated. The risk gradient is delineated based on the cumulative risk value, and the coupling degree is graded and marked. At the same time, the propagation path information of the nodes corresponding to the grade is recorded, and the risk coupling matrix value is output; First, the transmission rate is calculated in segments, and the risk transmission rate is multiplied by the transmission intensity between nodes as the incremental factor of the cumulative risk value. The cumulative risk value of each path node pair is accumulated in sequence, and the cumulative risk value on the path is divided into intervals. The high-risk area is marked in combination with the key nodes on the path, and the corresponding risk gradient is marked according to the interval size of the graded risk value. The graded mark relies on the calculated inter-node transmission path, analyzes the risk distribution characteristics on the path, records the cumulative risk value of the path and uses it as the input parameter of the risk coupling matrix, and finally outputs the risk coupling matrix value.

[0031] See also Figure 3 , the specific steps of S2 are: S201: Based on the risk coupling matrix value, a reference threshold for propagation intensity is set, the intensity value of each node in the matrix is calculated one by one, and node pairs with intensity values greater than the threshold are screened out. The associated parameters of the risk propagation path in the node pairs are analyzed, the screening results are marked, and node group data is established to generate high-intensity node group data; The transmission strength values of all node pairs in the matrix are obtained and compared with a threshold one by one. Node pairs with strength values greater than the threshold are screened out and their information is recorded. The risk-related parameters associated with the transmission paths within these node pairs are analyzed, including temporal differences, spatial distances, and transmission path sequences. These parameters are classified and statistically analyzed to determine the distribution of characteristic values for each parameter, identifying typical transmission characteristics and patterns. High-strength node pairs are then labeled to distinguish their role in the transmission network (e.g., key transmission nodes, secondary transmission nodes, etc.). Based on the screening results, high-strength node group data is aggregated according to the node pair's relevance, path characteristics, or strength level.

[0032] S202: Based on the high-intensity node group data, the spatial location parameters and distribution relationship of the nodes are extracted, the distance weights and distribution densities between the nodes are calculated item by item, and the impact of the spatial distribution on the risk value is analyzed in combination with the influence radius around the nodes. The spatial distribution association information of the nodes within the area is delineated to generate the node spatial distribution impact data; Extract the spatial position parameters and distribution relationship of the nodes, according to the formula ; Calculate the distance weight and distribution density between nodes.

[0033] Where, Represents the overall spatial distribution characteristic value, Representation node and nodes The weight between Representation node and nodes The spatial distance between Indicates the total number of nodes.

[0034] Node weight Calculated by standardizing risk association strength data, such as node and The correlation strength is 0.8, and the standardized weight The spatial distance between nodes Calculated by the three-dimensional Euclidean distance formula, such as node The coordinates are ,node The coordinates are ,distance .

[0035] Overall spatial distribution characteristic value The calculation is based on the total number of nodes For example, select several pairs of node weights and distance , enter the formula to calculate: ; The calculation results are used to analyze the impact of the spatial distribution of nodes on the risk value.

[0036] S203: Based on the node spatial distribution impact data, combined with the node risk propagation intensity and regional distribution relationship, the comprehensive risk value of the region is calculated, the gradient level is set according to the risk value, the gradient level information is graded and the regional boundary range is demarcated to generate risk level zoning data; Based on the risk propagation intensity data and the node density information in the regional distribution, the risk value of each node is superimposed according to its influence range. The node influence range is set by the radius value. The risk values within the node coverage range are accumulated to obtain the comprehensive risk value of each sub-area. At the same time, the accumulated risk value is divided according to the set gradient level. The number of covered nodes and risk value changes at the regional boundary are combined in the graded annotation to delineate the regional boundary range and calibrate the grading results to generate risk level zoning data.

[0037] See also Figure 4 , the specific steps of S3 are: S301: Based on the risk level partition data, the spatial range and distribution information of the nodes in the area are extracted, and the environmental variable data such as temperature, humidity, and vibration are matched. The risk level of the area and the environmental variable values are classified one by one, and the initial association between the environmental variables and the partition data is established to generate the initial distribution data of the environmental variables. The spatial range of the node is determined by the minimum and maximum coordinate values of the nodes in the area. The distribution information includes the node quantity density and position relationship, matching environmental variable data such as temperature, humidity, and vibration. The environmental variable data is obtained through real-time sensors or monitoring equipment. When classifying the risk level and environmental variable values of the area, the average environmental variable value corresponding to the risk level is counted one by one, and the correlation between the environmental variables and the partition risk is analyzed. The initial correlation between the risk level and the environmental variables is established, and finally the initial distribution data of the environmental variables are generated.

[0038] S302: Based on the initial distribution data of environmental variables, the influence of the change range of environmental variables on the regional risk level is calculated, the matching relationship between the variables and the risk level is analyzed, the values with the largest change range among the variables are extracted and assigned dynamic weights, the influence range and weight information of different variables are calibrated, and the dynamic weight data of environmental variables is generated; Calculate the impact of the change in environmental variables on the regional risk level according to the formula ; Calculate the matching relationship between variables and risk levels.

[0039] Where, Indicates the The degree of influence of environmental variables on risk level Indicates the The magnitude of the change in a variable, Indicates the change in regional risk level, Indicates the Dynamic weights of variables.

[0040] The magnitude of changes in environmental variables Calculated by maximum and minimum values, for example, the maximum value of the temperature variable is The minimum value is Degree, then The extent of change in regional risk levels Determined by the range of risk level values, for example, the highest risk level is , the lowest risk level is ,but Dynamic Weight Calculated by variable influence factors, for example, the influence factor of temperature variable is . Substitute each term into the formula: ; The results show that the influence of temperature variables on regional risk level is , and can be used for further variable weight calibration and range division.

[0041] S303: Based on the dynamic weight data of environmental variables, the dynamic correlation relationship between environmental variables and regional risk status is calculated, the parameter trend of the variables and risk level changes is extracted, the risk impact value of the dynamic change of the variables is calibrated, and the variable correlation results in the region are integrated to generate the dynamic impact value of the environmental variables; The dynamic weight is combined with the variable association trend to analyze the risk impact value of the dynamic change of the variable. The dynamic change is calculated through time series analysis to calculate the change rate of the variable in different time periods, and the rate is fitted with the time period change value of the risk level. At the same time, the variable association results in the region are integrated, and the comprehensive dynamic impact value of the environmental variables is generated by summarizing the risk impact range of different variables.

[0042] See also Figure 5 , the specific steps of S4 are: S401: Based on the dynamic impact value of the environmental variable, extract the time series risk status data of the node, calculate the change range of the risk status in segments, analyze the risk rate in each time period, calibrate the change trend of the node in the time dimension, and record the trend data to generate node risk status trend data; The time series risk status is obtained through dynamic monitoring and recording of nodes, and the risk status data is segmented. The change amplitude of the risk status is calculated according to the time node interval of each segment. The change amplitude is calculated by the difference between the maximum and minimum risk values. At the same time, the change trend of the risk status in each period is analyzed, the change law of the node in the time dimension is calibrated, the change trend data is recorded, and the node risk status trend data is generated.

[0043] S402: Based on the node risk status trend data, calculate the risk status transition probability between nodes, extract the transition path data of adjacent nodes, perform cumulative calculations on the transition intensity, and perform comparative analysis based on the risk intensity change parameters within the path to generate node risk transition probability data; The specific calculation formula for the risk state transition probability is: ; in, Representative Node and nodes The risk state transition probability between and Represents nodes and nodes In the The risk status value of each time period, Indicates time period The weight value of Indicates the total number of time periods between nodes, Indicates the sum of all time periods. Represents the cumulative sum of weighted squares.

[0044] Representation node and nodes The probability of risk state transition between

[0045] Risk status value and :Through the node and nodes In the time period Risk status data monitoring and acquisition within the period. Taking time period 2 as an example, node and The risk status values are: Time period 1: ,

[0046] Time period 2: , .

[0047] Time period weight : Reflects the time period The importance of risk is determined based on the fluctuation of risk data within a certain period of time. The greater the fluctuation, the higher the weight. The weight value is calculated by normalization: Weights for time period 1:

[0048] Weights for time period 2: .

[0049] Total number of time periods : Determine from time series data, the current .

[0050] Calculation of risk state transition probability: Calculate the numerator: ; Calculate the denominator: ; Transfer Intensity: ; This result shows that the node and nodes The risk state transition probability between nodes is 0.282, which is used to analyze the risk transfer relationship between nodes and serves as the basis for probability calculation in subsequent steps.

[0051] S403: Based on the node risk transfer probability data, the node priority adjustment factor and the resource allocation ratio parameter are calculated, the node risk change parameter and the resource utilization data are proportionally matched, the resource allocation adjustment value and the node priority dynamic change parameter are calibrated, and the risk status dynamic change value is generated; The node priority is determined by the combined weighting of the transfer probability and the risk change value. The resource allocation ratio parameter is calculated by the ratio of the resource demand and priority of each node. At the same time, the risk change parameters and resource utilization data of the node are proportionally analyzed. Combined with time series monitoring and changes in the risk intensity of the transfer path, the resource allocation adjustment value and the dynamic change parameter of the node priority are calibrated to finally generate the dynamic change value of the risk status.

[0052] See also Figure 6 , the specific steps of S5 are: S501: Based on the dynamic change value of the risk status, the propagation path and impact range of the new risk signal are extracted, the risk correlation strength value of the new signal on the existing nodes is calculated, the impact of the signal on the change of the node risk status is analyzed, the change parameters of the node are recorded and the analysis results are generated, and the impact parameters of the new risk signal are generated; The specific formula for calculating the risk association intensity value is: ; in, Represents a newly added signal pair node and nodes The risk correlation strength value between and Represents the newly added signal in the time period For Node and nodes The impact strength, Indicates time period The weight value of Indicates the total number of time periods, Indicates the cumulative sum of all time periods. Represents the sum of squared weights.

[0053] node and nodes The risk correlation strength between It is calculated based on the difference in impact strength and weight value of new signals added within a time period.

[0054] Added signal impact strength and :According to the time series monitoring data, record the newly added signal to the node and In the time period For example: Time period 1: ,

[0055] Time period 2: ,

[0056] Time period 3: .

[0057] Time period weight : Calculate the weight based on the fluctuation value of the impact of the new signal. The larger the fluctuation value, the higher the weight. The weight is calculated by normalization: Time period 1:

[0058] Time period 2:

[0059] Time period 3: .

[0060] Total number of time periods .

[0061] Calculation process: Calculate the numerator: ; ; Calculate the denominator: ; Calculate the risk association strength: ; This result shows that the node and nodes The risk correlation strength between nodes is 0.27, which is used to analyze the impact of new signals on the risk status between nodes and provide a calculation basis for the subsequent generation of new risk signal impact parameters.

[0062] S502: Based on the newly added risk signal impact parameters, recalculate the risk priority values of the affected nodes, analyze the difference between the priority adjustment value and the original status level, calibrate the new status level parameters of the nodes, dynamically update the priority and level of the node data, and generate node priority and status level data; Recalculate the risk priority value of the affected nodes according to the formula ; Calculate the priority value of the node.

[0063] Where, Representation node The priority value of Representation node The risk weight of Representation node The risk level value, is the total number of nodes.

[0064] Node risk weight By adding new signal influence parameters standardization calculation, such as node The influence parameter is 0.6, and the standardized weight The risk level value of the node Extracted from the dynamically changing value of risk status, such as node The risk level is 4. Substituting these values into the formula, as an example: ; This result shows that the node The priority value is 57%, which is used to dynamically adjust the status level and priority distribution of the node.

[0065] S503: Based on the node priority and status level data, combined with the risk propagation path, the global risk status change parameters are calculated, the status relationship and priority distribution between nodes are updated, the dynamic adjustment information of the nodes in the global network is recorded, and the risk priority and status update value of the construction node are generated; The risk propagation path is calculated through the dynamic relationship matrix between nodes. The status relationship update between nodes is correlated and analyzed through the changes in node priority. The priority distribution is recalculated by normalizing the priority value of each node, recording the dynamic adjustment information of nodes in the global network, and dynamically adjusting the distribution of node priorities in combination with the changes in risk status in the time dimension, ultimately generating the risk priority and status update value of the construction node.

[0066] See also Figure 7 , a BIM-based construction risk early warning system, including: The risk association module targets the risk factors of each node in the construction process, constructs an association matrix between risk nodes based on time and space dimensions, calculates the risk propagation intensity value between nodes, grades the risk coupling degree according to the propagation rate, and outputs the risk coupling matrix value; The regional division module sets the risk propagation threshold based on the risk coupling matrix value, extracts nodes with higher intensity in the risk propagation path, calculates the risk level of the area around the node, divides the construction area according to the risk level, demarcates the regional risk level boundaries, and outputs the risk level partition data; The environmental weight module extracts environmental variables in the construction area based on risk level zoning data, and generates dynamic impact values of environmental variables by quantifying the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level in the area; The state analysis module uses the dynamic impact value of environmental variables to analyze the trend of node risk state changes, calculates the node risk transfer probability, and evaluates the dynamic changes in risk intensity in the propagation path to generate a dynamic change value of risk state; The priority update module analyzes the impact of the new risk signal on the propagation of the original node according to the dynamic change value of the risk status, recalculates the risk priority and status level of the construction node, and outputs the risk priority and status update value of the construction node.

[0067] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. The BIM-based construction risk early warning method is characterized by: The following steps are involved: S1: Based on the risk factors of each node in the construction process, a correlation matrix between risk nodes is constructed based on the time and space dimensions. The risk propagation intensity value between nodes is calculated, the risk correlation relationship between nodes is determined, the risk coupling degree is graded according to the propagation rate, and the risk coupling matrix value is output; S2: Based on the risk coupling matrix value, a risk propagation threshold is set, and nodes with higher intensity in the risk propagation path are extracted. Combined with the spatial distribution data, the risk level of the area surrounding the node is calculated. The construction area is divided according to the risk level, and the regional risk level boundaries are demarcated, and the risk level partition data is output; S3: Extracting environmental variables in the construction area based on the risk level zoning data, quantifying the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level in the area, analyzing the correlation between environmental variables and risk status, and generating dynamic impact values of environmental variables; S4: Analyze the node risk status change trend using the dynamic impact value of the environmental variable, calculate the node risk transfer probability and evaluate the dynamic change of the risk intensity in the propagation path, adjust the node priority and resource allocation ratio according to the change results, and generate a risk status dynamic change value; S5: Analyze the propagation impact of the new risk signal on the original node based on the dynamic change value of the risk status, recalculate the risk priority and status level of the construction node, update the global risk status based on the propagation path, and output the risk priority and status update value of the construction node.

2. The BIM-based construction risk early warning method according to claim 1 is characterized in that: The risk coupling matrix value includes the risk transmission intensity value between nodes, the node risk correlation degree value, and the risk transmission rate level value; the risk level partition data includes the regional risk level identification, regional boundary information, and key node regional distribution; the environmental variable dynamic impact value includes the temperature impact weight, humidity impact weight, and vibration impact weight; the risk status dynamic change value includes the node risk change trend value, the node risk transfer probability value, and the resource allocation adjustment ratio; the construction node risk priority and status update value includes the node priority adjustment value, the node status level change value, and the global risk update data.

3. The BIM-based construction risk early warning method according to claim 1 is characterized in that: For the risk factors of each node in the construction process, a correlation matrix between risk nodes is constructed based on the time and space dimensions. The risk propagation intensity value between nodes is calculated, the risk correlation relationship between nodes is determined, and the risk coupling degree is graded according to the propagation rate. The specific steps for outputting the risk coupling matrix value are as follows: S101: Based on the risk factors of nodes in the construction process, extract the time attributes and spatial location data of each node, calculate the time series difference value, analyze the spatial distance, cross-compare the difference value and distance parameters, analyze the risk association relationship between nodes, calibrate the association parameters to construct the association matrix between nodes, and generate node association relationship data; S102: Based on the node association relationship data, the risk propagation intensity between nodes is calculated, and node pairs with propagation intensity values greater than a set threshold are screened. The strong and weak relationships are calculated by the calibration values of the associated nodes and the difference in propagation intensity. The risk propagation characteristics between the nodes are classified and recorded to generate node risk propagation intensity data. S103: Based on the node risk propagation intensity data and combined with the propagation rate, the cumulative risk value on the path is calculated, the risk gradient is defined according to the cumulative risk value, the coupling degree is graded and marked, and the propagation path information of the graded corresponding nodes is recorded at the same time, and the risk coupling matrix value is output.

4. The BIM-based construction risk early warning method according to claim 1 is characterized in that: Based on the risk coupling matrix value, a risk propagation threshold is set, and nodes with higher intensity in the risk propagation path are extracted. Combined with the spatial distribution data, the risk level of the area surrounding the node is calculated. The construction area is divided according to the risk level and the regional risk level boundary is demarcated. The specific steps for outputting the risk level partition data are as follows: S201: Based on the risk coupling matrix value, a reference threshold value of the propagation strength is set, the strength value of each node in the matrix is calculated one by one, and node pairs with strength values greater than the threshold are screened out. The associated parameters of the risk propagation path in the node pairs are analyzed, the screening results are marked and node group data is established to generate high-intensity node group data; S202: Based on the high-intensity node group data, extract the spatial location parameters and distribution relationship of the nodes, calculate the distance weights and distribution densities between the nodes one by one, analyze the impact of the spatial distribution on the risk value in combination with the influence radius around the nodes, delineate the node spatial distribution association information within the area, and generate node spatial distribution impact data; S203: Based on the node spatial distribution impact data, combined with the node risk propagation intensity and regional distribution relationship, calculate the comprehensive risk value of the region, set the gradient level according to the risk value, grade the gradient level information and calibrate the regional boundary range to generate risk level zoning data.

5. The BIM-based construction risk early warning method according to claim 1 is characterized in that: Based on the risk level zoning data, environmental variables in the construction area are extracted. By quantifying the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level in the area, the correlation between environmental variables and risk status is analyzed. The specific steps for generating dynamic impact values of environmental variables are as follows: S301: Based on the risk level partition data, extract the spatial range and distribution information of the nodes in the area, match the environmental variable data such as temperature, humidity, and vibration, classify the risk level of the area and the environmental variable values one by one, establish an initial association between the environmental variables and the partition data, and generate initial distribution data of the environmental variables; S302: Based on the initial distribution data of the environmental variables, the influence of the change range of the environmental variables on the regional risk level is calculated, the matching relationship between the variables and the risk level is analyzed, the values with larger change ranges among the variables are extracted and assigned dynamic weights, the influence range and weight information of different variables are calibrated, and dynamic weight data of the environmental variables are generated; S303: Based on the dynamic weight data of the environmental variables, calculate the dynamic correlation between the environmental variables and the regional risk status, extract the parameter trend of the variables and the risk level changes, calibrate the risk impact value of the dynamic change of the variables, and integrate the variable association results in the region to generate the dynamic impact value of the environmental variables.

6. The BIM-based construction risk early warning method according to claim 1 is characterized in that: The dynamic impact value of the environmental variables is used to analyze the node risk status change trend, calculate the node risk transfer probability and evaluate the dynamic change of the risk intensity in the propagation path. The node priority and resource allocation ratio are adjusted according to the change results. The specific steps for generating the dynamic change value of the risk status are as follows: S401: Based on the dynamic impact value of the environmental variable, extract the time series risk status data of the node, calculate the change range of the risk status in segments, analyze the risk rate in each time period, calibrate the change trend of the node in the time dimension, and record the trend data to generate node risk status trend data; S402: Based on the node risk status trend data, calculate the risk status transition probability between nodes, extract the transition path data of adjacent nodes, perform cumulative calculations on the transition intensity, and perform comparative analysis based on the risk intensity change parameters within the path to generate node risk transition probability data; S403: Based on the node risk transfer probability data, calculate the node priority adjustment factor and the resource allocation ratio parameter, proportionally match the node risk change parameter with the resource utilization data, calibrate the resource allocation adjustment value and the node priority dynamic change parameter, and generate a risk status dynamic change value.

7. The BIM-based construction risk early warning method according to claim 6 is characterized in that: The specific calculation formula for the risk state transition probability is: ; in, Representative Node and nodes The risk state transition probability between and Represents nodes and nodes In the The risk status value of each time period, Indicates time period The weight value of Indicates the total number of time periods between nodes, Indicates the sum of all time periods. Represents the sum of squared weights.

8. The BIM-based construction risk early warning method according to claim 1 is characterized in that: The specific steps for analyzing the impact of the new risk signal on the original nodes based on the dynamic change value of the risk status, recalculating the risk priority and status level of the construction node, and updating the global risk status based on the propagation path are as follows: S501: Based on the risk status dynamic change value, extract the propagation path and impact range of the new risk signal, calculate the risk association strength value of the new signal on the existing node, analyze the impact of the signal on the node risk status change, record the node change parameters and generate analysis results, and generate the new risk signal impact parameter; S502: Based on the newly added risk signal impact parameters, recalculate the risk priority values of the affected nodes, analyze the difference between the priority adjustment value and the original status level, calibrate the new status level parameters of the nodes, dynamically update the priority and level of the node data, and generate node priority and status level data; S503: Based on the node priority and status level data, combined with the risk propagation path, the global risk status change parameters are calculated, the status relationship and priority distribution between nodes are updated, the dynamic adjustment information of the nodes in the global network is recorded, and the construction node risk priority and status update value are generated.

9. The BIM-based construction risk early warning method according to claim 8, characterized in that: The specific calculation formula of the risk association intensity value is: ； in, Represents a newly added signal pair node and nodes The risk correlation strength value between and Represents the newly added signal in the time period For Node and nodes The impact strength, Indicates time period The weight value of Indicates the total number of time periods, Indicates the cumulative sum of all time periods. Represents the cumulative sum of weighted squares.

10. The BIM-based construction risk early warning system is characterized by: The BIM-based construction risk early warning method according to any one of claims 1 to 9, wherein the system comprises: The risk association module targets the risk factors of each node in the construction process, constructs an association matrix between risk nodes based on time and space dimensions, calculates the risk propagation intensity value between nodes, grades the risk coupling degree according to the propagation rate, and outputs the risk coupling matrix value; The regional division module sets the risk propagation threshold based on the risk coupling matrix value, extracts nodes with higher intensity in the risk propagation path, calculates the risk level of the area around the node, divides the construction area according to the risk level, demarcates the regional risk level boundary, and outputs the risk level partition data; The environmental weight module extracts environmental variables of the construction area based on the risk level zoning data, and generates dynamic impact values of environmental variables by quantifying the dynamic impact weights of variables such as temperature, humidity, and vibration on the risk level in the area; The state analysis module uses the dynamic impact value of the environmental variable to analyze the node risk state change trend, calculate the node risk transfer probability and evaluate the dynamic change of the risk intensity in the propagation path, and generate a risk state dynamic change value; The priority update module analyzes the propagation impact of the new risk signal on the original node according to the dynamic change value of the risk status, recalculates the risk priority and status level of the construction node, and outputs the risk priority and status update value of the construction node.

Images