A BIM-based engineering supervision method and system

Abstract

The application relates to the technical field of engineering supervision, and particularly discloses an engineering supervision and management method and system based on BIM, which comprises the following steps: importing engineering design drawings and material information tracing databases into professional BIM modeling software through format conversion technology, introducing geographic information system data, obtaining a BIM model, collecting construction progress data in the BIM model, obtaining a progress evaluation factor, determining a construction progress evaluation grade, determining a construction quality evaluation grade based on a fuzzy comprehensive evaluation model, constructing a BIM construction safety risk evaluation model, outputting a construction safety evaluation grade in combination with a BP neural network model, and issuing a BIM engineering supervision risk early warning. The application solves the problems of low information transmission efficiency, easy misunderstanding and omission of traditional supervision methods, easy information island and low management efficiency, and lack of real-time and comprehensive monitoring means in quality control, and can timely find and solve quality hidden dangers.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering supervision, in particular to an engineering supervision method and system based on BIM. BACKGROUND

[0002] With the rapid development of information technology, the construction industry is moving towards informatization and digitization. Traditional building engineering management mode gradually cannot meet the complex needs of modern construction projects, and using advanced information technology to improve the efficiency and quality of building engineering management has become an inevitable trend of industry development. BIM technology, as an important means of informatization in the construction industry, can integrate various information throughout the life cycle of a construction project, providing new ideas and methods for engineering supervision. BIM technology can create a three-dimensional visual building model, allowing supervisors to intuitively understand the structure, layout and construction process of the construction project. Through construction simulation, potential problems in construction can be identified in advance, providing strong decision support for supervision.

[0003] Nowadays, there are still some deficiencies in the research on BIM-based engineering supervision, which are mainly reflected in the following aspects: the information of traditional supervision methods is mainly transmitted through drawings, documents and other forms, the transmission efficiency of information is low and misunderstandings and omissions are easy to occur, there are many problems in information communication and coordination management, which easily lead to information silos and low management efficiency. In terms of quality control, it mainly relies on manual inspection and sampling detection, lacks real-time and comprehensive monitoring means, and it is difficult to discover and solve quality hidden dangers in time. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a BIM-based engineering supervision method and system, which can effectively solve the problems involved in the background art.

[0005] To achieve the above object, the present application is realized by the following technical solutions: the present application provides a BIM-based engineering supervision method, comprising the following steps: importing engineering design drawings and material information tracing database into professional BIM modeling software through format conversion technology, extracting basic building structure and mechanical and electrical equipment information, and obtaining an initial BIM model; introducing geographic information system data, obtaining construction site coordinates, and fusing the construction site coordinates with the initial BIM model through a coordinate matching algorithm to obtain a BIM model; assigning time attributes to each construction task in the BIM model, collecting construction progress data, constructing a progress analysis model, obtaining progress evaluation factors, and determining construction progress evaluation levels; analyzing construction quality states based on component attributes in the BIM model and quality monitoring data, determining construction quality evaluation levels based on a fuzzy comprehensive evaluation model; obtaining construction safety risk influence data, analyzing the construction safety risk influence data, constructing a BIM construction safety risk evaluation model, and the construction safety risk influence data specifically including personnel state data, equipment operation state data, and environmental state data; outputting construction safety evaluation levels based on the output of the BIM construction safety risk evaluation model and combining a BP neural network model; and issuing BIM engineering supervision risk early warnings based on the construction progress evaluation levels, the construction quality evaluation levels, and the construction safety evaluation levels.

[0006] As a further method, geographic information system data is introduced to obtain construction site coordinates, and the construction site coordinates are fused with the initial BIM model through a coordinate matching algorithm to obtain a BIM model, and the specific analysis process is as follows: geographic information system data is introduced to obtain construction site coordinates (X GIS , Y GIS , Z GIS ); the construction site coordinates are fused with the initial BIM model based on a coordinate matching algorithm to obtain the coordinates (X BIM , Y BIM , Z BIM ) of the construction site in the BIM model, and the coordinate matching formula is as follows:

[0007]

[0008] In the formula, X GIS is the horizontal coordinate of the construction site, Y GIS is the vertical coordinate of the construction site, Z GIS is the vertical coordinate of the construction site, X BIM is the horizontal coordinate of the construction site in the BIM model, Y BIM is the vertical coordinate of the construction site in the BIM model, Z BIM is the vertical coordinate of the construction site in the BIM model, S x is the scaling factor in the x-axis direction, and S yS is a scaling factor in the y-axis direction z T is a scaling factor in the z-axis direction x T is a translation factor in the x-axis direction y T is a translation factor in the y-axis direction z T is a translation factor in the z-axis direction

[0009] The coordinates of the construction site in the BIM model are fused with the initial BIM model to obtain the BIM model.

[0010] As a further method, a time attribute is given to each construction task in the BIM model, construction progress data is collected, a progress analysis model is constructed, a progress evaluation factor is obtained, a construction progress evaluation level is determined, and the specific analysis process is as follows: a time attribute is given to each construction task in the BIM model, construction progress data is collected, the total number of construction tasks, the number of completed construction tasks, the completion ratio of each construction task, and the planned completion ratio of each construction task are obtained; based on the total number of construction tasks, the number of completed construction tasks, the completion ratio of each construction task, and the planned completion ratio of each construction task, a progress analysis model is constructed, a progress evaluation factor is output, and the progress evaluation factor is used as an analysis basis for determining the construction progress evaluation level; a pre-stored progress evaluation factor-construction progress evaluation level mapping table in the database is obtained, and by looking up the mapping table, the matching construction progress evaluation level is found according to the progress evaluation factor.

[0011] As a further method, the progress analysis model, and the specific analysis process is as follows:

[0012]

[0013] In the formula, sv is the progress evaluation factor, finish is the number of completed construction tasks, ev i is the completion ratio of the i-th construction task, and pv i is the planned completion ratio of the i-th construction task, i is the construction task number, i = 1, 2, 3,..., w, and w is the total number of construction tasks.

[0014] As a further method, based on the component attributes and quality monitoring data in the BIM model, the construction quality state is analyzed, and the specific analysis process is as follows: the actual strength f actual of the concrete is obtained, the design strength f design of the concrete is obtained, and the concrete strength quality factor fy is calculated:

[0015]

[0016] The appearance defect rate d defect of the concrete component is obtained, and the concrete component appearance quality factor dy is calculated:

[0017]

[0018] In the formula, e is the natural constant;

[0019] Obtain the actual dimension L of the concrete component actual With the design dimension L of the concrete component design Calculate the dimensional mass factor Ly of concrete components;

[0020]

[0021] As a further method, based on the fuzzy comprehensive evaluation model, the construction quality assessment level is determined. The specific analysis process is as follows: Determine the fuzzy comprehensive evaluation factor set U, U = {u1, u2, u3}, where u1 represents the concrete strength quality factor, u2 represents the concrete component appearance quality factor, and u3 represents the concrete component size quality factor; determine the construction quality evaluation level V, V = {v1, v2, v3}, where v1 is level one, v2 is level two, and v3 is level three; obtain the membership degree r of each evaluation factor to each evaluation level stored in the database. mn Given m = 1, 2, 3 and n = 1, 1, 2, 3, the single-factor evaluation matrix R is: r mn Indicates evaluation factor u m Belongs to rating level v n The membership degree, and 0≤r mn ≤1, m is the number of the evaluation factor, and n is the number of the evaluation level;

[0022] The weight 'a' of each evaluation factor is determined using the analytic hierarchy process (AHP). m Obtain the factor weight vector A = [a1, a2, a3], and Input the single-factor evaluation matrix R and the factor weight vector A; calculate the comprehensive evaluation vector B through fuzzy transformation: in, Represents a fuzzy composition operator;

[0023] Output the comprehensive evaluation vector B, where B = [b1, b2, b3]. These represent the comprehensive membership degree of construction quality to each evaluation level; based on the principle of maximum membership degree, the level with the highest membership degree in the comprehensive evaluation vector B is selected as the final evaluation level of construction quality.

[0024] As a further method, personnel status data specifically includes personnel density ρ people The equipment operating status data specifically includes the number of equipment failures (f). equn Equipment failure frequency f equp Environmental status data specifically includes environmental precipitation (env).t , the environmental wind speed env f ; constructing a BIM construction safety risk assessment model based on construction safety risk influence data:

[0025]

[0026] In the formula, BIMf is a BIM construction safety risk assessment factor, and e is a natural constant.

[0027] As a further method, in combination with a BP neural network model, a construction safety assessment level is output, and the specific analysis process is as follows: a BP neural network model training data set is obtained, and input variables and output variables are normalized to be mapped to the [0, 1] interval; the number of neurons of the input layer of the BP neural network model is determined to be equal to the number of input variables, the input variables are BIM construction safety risk assessment factors in the training data set, and there is 1; the number of neurons of the output layer is equal to the number of categories of the construction safety assessment level, and the number of categories of the construction safety assessment level in the training data set is 3, that is, 1, 2 and 3, which respectively represent the first level, the second level and the third level, and are converted into a numerical vector by using one-hot encoding, that is, the first level is represented as [1, 0, 0], the second level is represented as [0, 1, 0], and the third level is represented as [0, 0, 1]; the number of neurons of the hidden layer is h; the connection weights from the input layer to the hidden layer and from the hidden layer to the output layer and the thresholds of the hidden layer and the output layer are randomly initialized; the BIM construction safety risk assessment factors in the training data set after preprocessing are input;

[0028] The output yc of the s-th neuron of the hidden layer is calculated using a Sigmoid activation function s : In the formula, qz s is the connection weight from the input layer to the s-th neuron of the hidden layer, cy s is the threshold of the s-th neuron of the hidden layer, s is the neuron number of the hidden layer, and s = 1, 2, 3... h; the output oc t of the t-th neuron of the output layer is calculated using a Sigmoid activation function : st In the formula, b t is the connection weight from the s-th neuron of the hidden layer to the t-th neuron of the output layer, d t is the threshold of the t-th neuron of the output layer, t is the neuron number of the output layer, and t = 1, 2, 3; for the t-th neuron of the output layer, the error e t is calculated according to the formula: e t = t t -o t ; in the formula, t tis the actual output of the output layer tth neuron;The connection weight and threshold value are updated by using gradient descent method until the error of the network is less than the accuracy threshold value stored in the database or the maximum iteration number is reached;

[0029] In the trained BP neural network model, the preprocessed current BIM construction safety risk assessment factor is input;The output vector of the output layer is obtained;According to the output vector, the maximum membership principle is adopted to determine the construction safety evaluation grade.

[0030] As a further method, based on the construction progress evaluation grade, the construction quality evaluation grade and the construction safety evaluation grade, the BIM project supervision risk early warning is issued, and the specific analysis process is as follows: the construction progress evaluation grade, the construction quality evaluation grade and the construction safety evaluation grade are accumulated to obtain the BIM project supervision risk grade;The BIM project supervision risk grade is compared with the BIM project supervision risk critical grade stored in the database;If the BIM project supervision risk grade is not higher than the BIM project supervision risk critical grade, the BIM project supervision risk grade is transmitted to the data center, and the data center sends the BIM project supervision safety reminder to the construction management control end;If the BIM project supervision risk grade is higher than the BIM project supervision risk critical grade, the BIM project supervision risk grade is transmitted to the data center, the data center sends the BIM project supervision risk early warning to the construction management control end, and the construction progress evaluation grade, the construction quality evaluation grade and the construction safety evaluation grade are displayed on the construction management control end.

[0031] The second aspect of the present application provides a BIM-based project supervision system, comprising an initial BIM model acquisition module, an initial BIM model updating module, a construction progress evaluation grade determination module, a construction quality evaluation grade determination module, a safety risk influence data analysis module, a construction safety evaluation grade matching module and a supervision risk early warning issuing module, wherein: the initial BIM model acquisition module is used to import professional BIM modeling software through format conversion technology by engineering design drawings and material information tracing database, extract basic building structure and mechanical and electrical equipment information, and obtain the initial BIM model;The initial BIM model updating module is used to introduce geographic information system data, obtain construction site coordinates, fuse the construction site coordinates with the initial BIM model through coordinate matching algorithm, and obtain the BIM model;

[0032] The construction progress evaluation grade determination module is configured to assign time attributes to each construction task in the BIM model, collect construction progress data, construct a progress analysis model, obtain progress evaluation factors, and determine a construction progress evaluation grade; the construction quality evaluation grade determination module is configured to analyze construction quality states based on component attributes and quality monitoring data in the BIM model, and determine a construction quality evaluation grade based on a fuzzy comprehensive evaluation model; the construction safety risk influence data analysis module is configured to obtain construction safety risk influence data, analyze the construction safety risk influence data, construct a BIM construction safety risk evaluation model, and the construction safety risk influence data specifically includes personnel state data, equipment operation state data, and environmental state data; the construction safety evaluation grade matching module is configured to output a construction safety evaluation grade based on the output of the BIM construction safety risk evaluation model and in combination with a BP neural network model; and the supervision risk early warning issuing module is configured to issue a BIM engineering supervision risk early warning based on the construction progress evaluation grade, the construction quality evaluation grade, and the construction safety evaluation grade.

[0033] Compared with the prior art, the embodiments of the present application have at least the following advantages or beneficial effects:

[0034] (1) The present application provides a BIM-based engineering supervision method and system, which imports engineering design drawings into professional BIM modeling software, integrates basic information such as building structures and mechanical and electrical equipment, changes the situation that various types of information are dispersed in different drawings and documents in the traditional mode, makes project information more concentrated and clear, introduces geographic information system data and performs coordinate matching and fusion, makes the BIM model accurately correspond to the actual geographic position of the construction site, provides an accurate spatial positioning basis for subsequent construction management, and can effectively avoid construction problems caused by geographic position deviation.

[0035] (2) The present application can provide comprehensive and integrated information for engineering supervision and project management based on the evaluation grades of construction progress, quality, and safety, so that managers can grasp the project status as a whole and make more scientific and reasonable decisions, avoiding management errors caused by focusing on a single factor.

[0036] (3) The present application can comprehensively cover various influencing factors of construction safety risks by combining a BP neural network model to output a construction safety evaluation grade and including personnel state data, equipment operation state data, and environmental state data in the analysis scope. The BP neural network model has strong non-linear mapping capability and data learning capability, and can accurately output the prediction result of the safety risk probability according to historical data and current risk influence factors. BRIEF DESCRIPTION OF DRAWINGS

[0037] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of the method steps of the present invention.

[0039] Figure 2 This is a schematic diagram of the system module connections of the present invention. Detailed Implementation

[0040] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0041] Reference Figure 1 As shown, the first aspect of the present invention provides a BIM-based engineering supervision and management method, including: importing engineering design drawings and material information traceability databases into professional BIM modeling software through format conversion technology, extracting basic building structure and electromechanical equipment information, and obtaining an initial BIM model.

[0042] Geographic Information System (GIS) data is introduced to obtain the coordinates of the construction site. The coordinates of the construction site are then fused with the initial BIM model using a coordinate matching algorithm to obtain the BIM model.

[0043] The specific analysis process is as follows: Geographic Information System (GIS) data is imported to obtain the coordinates of the construction site (X...). GIS Y GIS Z GIS Based on a coordinate matching algorithm, the coordinates of the construction site are fused with the initial BIM model to obtain the coordinates (X, Y, F) of the construction site in the BIM model. BIM Y BIM Z BIM The coordinate matching formula is:

[0044]

[0045] In the formula, X GIS Y represents the horizontal axis of the construction site. GIS Z represents the longitudinal coordinate of the construction site. GIS X represents the vertical coordinates of the construction site. BIM Let Y be the x-coordinate of the construction site in the BIM model. BIM Z represents the vertical coordinate of the construction site in the BIM model. BIMS is the vertical coordinate of the construction site in the BIM model x S is the scaling factor in the x-axis direction y S is the scaling factor in the y-axis direction z T is the scaling factor in the z-axis direction x T is the translation factor in the x-axis direction y T is the translation factor in the y-axis direction z T is the translation factor in the z-axis direction

[0046] The coordinates of the construction site in the BIM model are fused with the initial BIM model to obtain a BIM model.

[0047] GIS focuses on macro geographical environmental information such as terrain, surrounding building distribution, and transportation network, while BIM focuses on the micro details of the construction project itself, such as building structure and internal facilities. After fusion, the macro geographical background of the construction site can be intuitively presented in the BIM model. Supervisors can not only view the internal structure and construction details of the building, but also understand its relationship with the surrounding environment, which helps to grasp the overall situation of the project, such as judging the influence of the surrounding terrain on the layout of the construction site and the material transportation route.

[0048] Through the coordinate matching algorithm, accurate conversion and fusion of GIS coordinates and BIM model coordinates are realized, providing a unified and accurate coordinate system for the positioning of the construction site. This helps supervisors accurately determine the construction position, for example, when performing foundation construction, the pile position and foundation boundary can be accurately measured according to the fused coordinate information, ensuring that the construction position meets the design requirements.

[0049] Combined with the construction progress information in the geographical information and BIM model, more realistic construction progress simulation can be performed. Considering the influence of the geographical environment on construction, the progress under different construction schemes is simulated to optimize the construction plan, and the supervisor can more accurately assess whether the construction progress is reasonable, timely discover potential progress delay risks and take measures.

[0050] Each construction task is assigned a time attribute in the BIM model, construction progress data is collected, a progress analysis model is constructed, a progress evaluation factor is obtained, and a construction progress evaluation level is determined.

[0051] The specific analysis process is: time attributes are given to each construction task in the BIM model, construction progress data is collected, the total number of construction tasks, the number of completed construction tasks, the completion proportion of each construction task, and the planned completion proportion of each construction task are obtained; based on the total number of construction tasks, the number of completed construction tasks, the completion proportion of each construction task, and the planned completion proportion of each construction task, a progress analysis model is constructed, a progress evaluation factor is output, and the progress evaluation factor is used as an analysis basis for determining the construction progress evaluation level; a pre-stored progress evaluation factor-construction progress evaluation level mapping table in the database is obtained, and by looking up the mapping table, the matching construction progress evaluation level is found according to the progress evaluation factor.

[0052] The progress analysis model, and the specific analysis process is:

[0053]

[0054] In the formula, sv is the progress evaluation factor, finish is the number of completed construction tasks, ev i is the completion proportion of the i-th construction task, pv i is the planned completion proportion of the i-th construction task, i is the construction task number, i=1, 2, 3,..., w, and w is the total number of construction tasks.

[0055] By giving time attributes to construction tasks in the BIM model and collecting multi-dimensional data such as the total number of construction tasks, the number of completed construction tasks, the completion proportion of each construction task, and the planned completion proportion, the progress analysis model can output accurate progress evaluation factors. This makes the construction progress evaluation no longer a fuzzy qualitative judgment, but a quantitative analysis based on specific data. For example, the supervisor can accurately know the deviation degree of the current engineering progress from the planned progress according to the progress evaluation factor, providing solid data support for decision-making and avoiding mistakes caused by experience or subjective judgment.

[0056] The calculation of the progress evaluation factor takes into account the completion of each construction task and can be refined to the specific task level. This helps the supervisor to deeply understand the progress of each link in the project and find out which tasks are ahead of or behind schedule, so that targeted measures can be taken.

[0057] The construction progress analysis is automated and standardized by constructing the progress analysis model and determining the evaluation level by querying the pre-stored progress evaluation factor-construction progress evaluation level mapping table. Compared with the traditional manual statistical and analysis progress method, the human and time costs are greatly reduced, and the work efficiency is improved.

[0058] Based on the component attributes and quality monitoring data in the BIM model, the construction quality state is analyzed, and the construction quality evaluation level is determined based on the fuzzy comprehensive evaluation model.

[0059] The specific analysis process is: obtaining the actual strength f of the concrete actual and the design strength f of the concrete design , calculating the concrete strength quality factor fy:

[0060]

[0061] Obtaining the appearance defect rate d of the concrete member defect , calculating the concrete member appearance quality factor dy:

[0062]

[0063] In the formula, e is a natural constant;

[0064] Obtaining the actual size L of the concrete member actual and the design size L of the concrete member design , calculating the concrete member size quality factor Ly;

[0065]

[0066] By calculating the concrete strength quality factor, the appearance quality factor and the size quality factor respectively, the quality of the concrete member is quantitatively evaluated from multiple key dimensions. Not only the core performance index of concrete strength is considered, but also important factors such as appearance defect rate and size deviation that affect the quality are covered, which can comprehensively and accurately reflect the actual quality status of the concrete member, avoiding the one-sidedness of single index evaluation.

[0067] As an information carrier, the BIM model integrates various attribute information and quality monitoring data of the concrete member. This enables all parties involved in the project to obtain and share quality-related information on the same platform, avoiding the problem of information island and poor information transmission.

[0068] The specific analysis process is: determining the fuzzy comprehensive evaluation factor set U, U={u1, u2, u3}, u1 represents the concrete strength quality factor, u2 represents the concrete member appearance quality factor, and u3 represents the concrete member size quality factor; determining the construction quality evaluation level V, V={v1, v2, v3}, v1 is the first level, v2 is the second level, and v3 is the third level; obtaining the membership degree r mn of each evaluation factor to each evaluation level stored in the database, m=1, 2, 3, n=1, 1, 2, 3, and the single-factor evaluation matrix R is: r mn represents the membership degree of the evaluation factor u m to the evaluation level v n , and 0≤r mn ≤1, m is the number of evaluation factors, and n is the number of evaluation levels;

[0069] The weight 'a' of each evaluation factor is determined using the analytic hierarchy process (AHP). m The factor weight vector A = [a1, a2, a3], and Input the single-factor evaluation matrix R and the factor weight vector A; calculate the comprehensive evaluation vector B through fuzzy transformation: in, Represents a fuzzy composition operator;

[0070] Output the comprehensive evaluation vector B, where B = [b1, b2, b3]. These represent the comprehensive membership degree of construction quality to each evaluation level; based on the principle of maximum membership degree, the level with the highest membership degree in the comprehensive evaluation vector B is selected as the final evaluation level of construction quality.

[0071] In construction quality evaluation, quality grades are not always clearly defined and involve considerable ambiguity. For example, the quality of a concrete component may fall between two grades, making precise definition difficult. Fuzzy comprehensive evaluation models, by introducing the concept of membership, can effectively handle this uncertainty.

[0072] Construction quality is influenced by a variety of factors, and the relationships between these factors are complex and difficult to describe using precise mathematical models. The fuzzy comprehensive evaluation model, based on the principles of fuzzy mathematics, can effectively handle these complex relationships, comprehensively consider multiple quality factors, and avoid evaluation biases caused by simplistic treatment.

[0073] A set of evaluation factors, including concrete strength quality factors, appearance quality factors, and dimensional quality factors, was clearly defined to evaluate construction quality from multiple key dimensions. This covers the main aspects affecting the quality of concrete components, avoiding the one-sidedness of evaluating quality based on only a single factor, and can comprehensively and accurately reflect the actual level of construction quality.

[0074] Based on the principle of maximum membership, the level with the highest membership degree is selected from the comprehensive evaluation vector as the final evaluation level of construction quality, providing a clear standard for determining the level of construction quality.

[0075] The data on the impact of construction safety risks are analyzed, including personnel status data, equipment operation status data, and environmental status data, to construct a BIM-based construction safety risk assessment model.

[0076] The specific analysis process is as follows: Personnel status data specifically includes personnel density ρ people The equipment operating status data specifically includes the number of equipment failures (f). equn Equipment failure frequency f equp Environmental status data specifically includes environmental precipitation (env).t , an environmental wind speed env f ; constructing a BIM construction safety risk assessment model based on construction safety risk influence data:

[0077]

[0078] In the formula, BIMf is a BIM construction safety risk assessment factor, and e is a natural constant.

[0079] Comprehensive consideration is given to personnel state, equipment operating state, and environmental state and other aspects of data, and key factors influencing construction safety risk are comprehensively covered. Personnel density influences the safety and work efficiency of the construction site, equipment failure frequency reflects the reliability of the equipment, and environmental factors such as environmental precipitation and wind speed have a direct influence on construction safety. By fusing these data, construction safety risk can be assessed from multiple dimensions, avoiding one-sidedness caused by focusing on a single factor, and more accurately reflecting the real safety risk situation of the construction site.

[0080] The BIM construction safety risk assessment factor BIMf is calculated through a specific formula, and the construction safety risk is quantified. This quantification method makes the safety risk have a specific numerical measurement standard, and compared with traditional qualitative or fuzzy evaluation, it can more accurately reflect the risk degree.

[0081] Based on the output of the BIM construction safety risk assessment model, a BP neural network model is combined to output a construction safety assessment level.

[0082] The specific analysis process is as follows: obtain the BP neural network model training data set, normalize the input variables and output variables, and map them to the [0, 1] interval; determine the number of neurons in the input layer of the BP neural network model to be equal to the number of input variables, and the input variable is the BIM construction safety risk assessment factor in the training data set, which is 1; the number of neurons in the output layer is equal to the number of categories of the construction safety assessment level, and the number of categories of the construction safety assessment level in the training data set is 3, which is 1, 2, and 3, respectively, representing first, second, and third levels, and is converted into a numerical vector using one-hot encoding, first level indicating [1, 0, 0], second level indicating [0, 1, 0], and third level indicating [0, 0, 1]; the number of neurons in the hidden layer is h; randomly initialize the connection weights from the input layer to the hidden layer and from the hidden layer to the output layer, and the thresholds of the hidden layer and the output layer; input the BIM construction safety risk assessment factor in the training data set after preprocessing;

[0083] The output yc of the s-th neuron in the hidden layer is calculated using the Sigmoid activation function s : In the formula, qz scy is the connection weight value from the input layer to the s-th neuron of the hidden layer s is the threshold value of the s-th neuron of the hidden layer, s is the neuron number of the hidden layer, s = 1, 2, 3... h; the output of the t-th neuron of the output layer is calculated using the Sigmoid activation function t : st is the connection weight value from the s-th neuron of the hidden layer to the t-th neuron of the output layer, d t is the threshold value of the t-th neuron of the output layer, t is the neuron number of the output layer, t = 1, 2, 3; the error e t of the t-th neuron of the output layer is calculated as follows: e t = t t -o t ; in which, t t is the expected output of the t-th neuron of the output layer, o t is the actual output of the t-th neuron of the output layer; the connection weight value and the threshold value are updated using the gradient descent method until the error of the network is less than the accuracy threshold stored in the database or the maximum number of iterations is reached.

[0084] The pre-processed current BIM construction safety risk assessment factors are input into the trained BP neural network model; the output vector of the output layer is obtained; according to the output vector, the maximum membership principle is used to determine the construction safety assessment grade.

[0085] The BP neural network model has strong non-linear mapping ability and can learn the complex relationship between BIM construction safety risk assessment factors and safety risk grades from a large amount of training data. Through learning and training of input variables (BIM construction safety risk assessment factors), it can capture the hidden rules and characteristics in the data, so as to more accurately predict the construction safety assessment grade. Compared with simple linear models or empirical judgments, BP neural network can handle the interaction between more complex safety risk influencing factors, improving the accuracy of assessment.

[0086] The BIM construction safety risk assessment model has integrated personnel, equipment, environment and other data to calculate risk assessment factors. On this basis, the BP neural network further processes these assessment factors, making full use of the information of multi-source data. It can integrate the influence of different types of data, avoid the limitations brought by single data source or simple calculation, make the assessment results more comprehensive and reliable, and more truly reflect the safety situation of the construction site.

[0087] ​The construction safety risk itself has certain uncertainty and fuzziness, and the BP neural network model can process these uncertainties by learning a large amount of historical data. It can give the corresponding safety evaluation level according to different risk evaluation factor combinations, and even in the case of certain noise or incompleteness of data, it can relatively stably output a more reliable evaluation result, adapting to the challenges brought by the complex and changeable construction environment. The construction safety evaluation level output by the BP neural network model provides a clear and accurate reference for construction safety management. According to different safety levels, corresponding safety management strategies and measures can be developed.

[0088] Based on the construction progress evaluation level, the construction quality evaluation level and the construction safety evaluation level, the BIM project supervision risk early warning is issued. Based on the construction progress evaluation level, the construction quality evaluation level and the construction safety evaluation level, the BIM project supervision risk early warning is issued.

[0089] The specific analysis process is: the construction progress evaluation level, the construction quality evaluation level and the construction safety evaluation level are accumulated to obtain the BIM project supervision risk level; the BIM project supervision risk level is compared with the BIM project supervision risk critical level stored in the database; if the BIM project supervision risk level is not higher than the BIM project supervision risk critical level, the BIM project supervision risk level is transmitted to the data center, and the data center issues a BIM project supervision safety reminder to the construction management control end; if the BIM project supervision risk level is higher than the BIM project supervision risk critical level, the BIM project supervision risk level is transmitted to the data center, and the data center issues a BIM project supervision risk early warning to the construction management control end, and the construction progress evaluation level, the construction quality evaluation level and the construction safety evaluation level are displayed on the construction management control end.

[0090] This method accumulates the evaluation levels of construction progress, quality and safety, which are three important dimensions for engineering construction, to form the BIM project supervision risk level. It changes the limitation of only focusing on single aspect risk in the past, and can comprehensively reflect the overall risk situation of the project. Construction progress lag may lead to cost increase and safety risk rise, quality problems may cause rework and affect progress and safety, through this comprehensive evaluation, hidden dangers caused by ignoring the risk of a certain dimension can be effectively avoided.

[0091] Through comparison with the BIM project supervision risk critical level stored in the database, graded early warning is implemented. When the risk level is higher than the critical level, risk early warning is issued, clearly informing that the project has a high risk and immediate measures need to be taken. This grading method can reasonably allocate resources and attention according to the severity of the risk, improving the efficiency of risk response. The display of risk early warning information on the construction management control end facilitates the collaborative work of all parties involved in the project, improving the collaboration and efficiency of project management.

[0092] Referring Figure 2 The second aspect of the present application provides a BIM-based engineering supervision system, comprising an initial BIM model acquisition module, an initial BIM model updating module, a construction progress evaluation level determination module, a construction quality evaluation level determination module, a safety risk influence data analysis module, a construction safety evaluation level matching module, and a supervision risk early warning issuing module.

[0093] The initial BIM model acquisition module is used to import professional BIM modeling software through format conversion technology by using engineering design drawings and material information tracing databases, extract basic building structure and mechanical and electrical equipment information, and obtain an initial BIM model.

[0094] The initial BIM model updating module is used to introduce geographic information system data, obtain construction site coordinates, and fuse the construction site coordinates with the initial BIM model through a coordinate matching algorithm to obtain a BIM model.

[0095] The construction progress evaluation level determination module is used to assign time attributes to each construction task in the BIM model, collect construction progress data, construct a progress analysis model, obtain progress evaluation factors, and determine a construction progress evaluation level.

[0096] The construction quality evaluation level determination module is used to analyze the construction quality state based on the component attributes in the BIM model and quality monitoring data, and determine a construction quality evaluation level based on a fuzzy comprehensive evaluation model.

[0097] The safety risk influence data analysis module is used to analyze construction safety risk influence data, which specifically includes personnel state data, equipment operation state data, and environment state data, and construct a BIM construction safety risk evaluation model.

[0098] The construction safety evaluation level matching module is used to output a construction safety evaluation level based on the output of the BIM construction safety risk evaluation model and in combination with a BP neural network model.

[0099] The supervision risk early warning issuing module is used to issue a BIM engineering supervision risk early warning based on the construction progress evaluation level, the construction quality evaluation level, and the construction safety evaluation level.

[0100] The above content is only an example and description of the structure of the present application, and those skilled in the art can make various modifications or supplements or use similar ways to replace the described specific embodiments, as long as they do not deviate from the structure of the present application or exceed the scope defined by the present claims, and should be within the protection scope of the present application.

Claims

1. A BIM-based engineering supervision management method, characterized by, The method comprises the following steps: The engineering design drawings and material information traceability database are imported into professional BIM modeling software through format conversion technology, basic building structure and mechanical and electrical equipment information are extracted, and an initial BIM model is obtained; Geographic information system data is introduced, construction site coordinates are obtained, and the construction site coordinates are fused with the initial BIM model through a coordinate matching algorithm to obtain a BIM model; Each construction task is given a time attribute in the BIM model, construction progress data is collected, a progress analysis model is constructed, a progress evaluation factor is obtained, and a construction progress evaluation level is determined, and the specific process is as follows: Each construction task is given a time attribute in the BIM model, construction progress data is collected, the total number of construction tasks, the number of completed construction tasks, the completion proportion of each construction task, and the planned completion proportion of each construction task are obtained; Based on the total number of construction tasks, the number of completed construction tasks, the completion proportion of each construction task, and the planned completion proportion of each construction task, a progress analysis model is constructed, and a progress evaluation factor is outputted, which serves as an analysis basis for determining the construction progress evaluation level, and the progress analysis model is as follows: ； wherein, is a progress evaluation factor, is a number of completed construction tasks, is a completion ratio of the i-th construction task, is a planned completion ratio of the i-th construction task, i is a construction task number, i = 1, 2, 3,..., w, and w is a total number of construction tasks; A pre-stored progress evaluation factor-construction progress evaluation level mapping table in the database is obtained, and by looking up the mapping table, the matching construction progress evaluation level is found according to the progress evaluation factor; Based on the component attributes in the BIM model and the quality monitoring data, the construction quality state is analyzed, and the specific process is as follows: Obtaining actual strength of concrete with a designed strength of concrete , calculating a concrete strength quality factor : ； Obtaining a rate of appearance defects of a concrete component , calculating a quality factor of appearance of a concrete component : ； In the formula, e is a natural constant; Obtaining actual dimensions of a concrete member Design dimensions of a concrete member Calculating a dimension quality factor for a concrete member ; ； Based on the fuzzy comprehensive evaluation model, the construction quality evaluation level is determined; Construction safety risk influence data is obtained, and the construction safety risk influence data is analyzed to construct a BIM construction safety risk evaluation model, and the construction safety risk influence data specifically includes personnel state data, equipment operation state data, and environment state data; Based on the output of the BIM construction safety risk evaluation model, a construction safety evaluation level is outputted in combination with a BP neural network model. Based on the construction progress evaluation level, the construction quality evaluation level, and the construction safety evaluation level, a BIM engineering supervision risk early warning is issued.

2. The BIM-based engineering supervision method according to claim 1, characterized in that: The geographic information system data is introduced, the construction site coordinates are obtained, and the construction site coordinates are fused with the initial BIM model through a coordinate matching algorithm to obtain a BIM model, and the specific analysis process is as follows: Introducing geographic information system data, obtaining construction site coordinates ; Based on the coordinate matching algorithm, the construction site coordinates are fused with the initial BIM model to obtain the coordinates of the construction site in the BIM model , and the coordinate matching formula is ； wherein is a horizontal coordinate of the construction site, is a vertical coordinate of the construction site, is an elevation coordinate of the construction site, is a horizontal coordinate of the construction site in the BIM model, is a vertical coordinate of the construction site in the BIM model, is an elevation coordinate of the construction site in the BIM model, is a scaling factor in the x-axis direction, is a scaling factor in the y-axis direction, is a scaling factor in the z-axis direction, is a translation factor in the x-axis direction, is a translation factor in the y-axis direction, is a translation factor in the z-axis direction; The coordinates of the construction site in the BIM model are fused with the initial BIM model to obtain a BIM model.

3. The BIM-based engineering supervision method according to claim 1, characterized in that: The fuzzy comprehensive evaluation model is used to determine the construction quality evaluation level, and the specific analysis process is as follows: Determination of fuzzy comprehensive evaluation factor set , , characterizing a concrete strength quality factor, characterizing a concrete member appearance quality factor, characterizing a concrete member dimension quality factor; determining construction quality evaluation grades , , first grade, second grade, third grade; obtaining the membership of each evaluation factor stored in the database to each evaluation grade , m = 1, 2, 3, n = 1, 1, 2, 3, single-factor evaluation matrix is: ； represents the evaluation factor belongs to the evaluation grade the membership degree, and , m is the number of evaluation factors, and n is the number of evaluation grades The weight of each evaluation factor is determined by using analytic hierarchy process , to obtain a factor weight vector , and ; Input single-factor evaluation matrix and factor weight vector ; By fuzzy transformation calculation comprehensive evaluation vector : ； wherein denotes a fuzzy composition operator; Output comprehensive evaluation vector , , , , , respectively represent the comprehensive membership degree of the construction quality belonging to each evaluation grade; according to the maximum membership degree principle, the grade with the maximum membership degree in the comprehensive evaluation vector is selected as the final evaluation grade of the construction quality.

4. The BIM-based engineering supervision method according to claim 1, characterized in that: The personnel status data specifically includes a personnel density ; The device running state data specifically includes device fault times , device fault frequency ; The environmental state data specifically includes environmental precipitation , environmental wind speed ; A BIM construction safety risk evaluation model is constructed based on the construction safety risk influence data: ； In the formula, is a BIM construction safety risk assessment factor, and e is a natural constant.

5. The BIM-based engineering supervision method according to claim 4, characterized in that: The BP neural network model is combined to output a construction safety evaluation level, and the specific analysis process is as follows: A BP neural network model training data set is obtained, and input variables and output variables are normalized and mapped to the [0, 1] interval; The number of neurons in the input layer of the BP neural network model is equal to the number of input variables, and the input variable is one BIM construction safety risk evaluation factor in the training data set. The number of neurons of the output layer is equal to the number of categories of the construction safety assessment level, and the number of categories of the construction safety assessment level in the training data set is 3, i.e., 1, 2 and 3, representing first, second and third levels respectively, which are converted into numerical vectors by using one-hot encoding, i.e., first level is represented as [1, 0, 0], second level is represented as [0, 1, 0] and third level is represented as [0, 0, 1]; The number of neurons of the hidden layer is h; The connection weights from the input layer to the hidden layer and from the hidden layer to the output layer and the thresholds of the hidden layer and the output layer are randomly initialized; The BIM construction safety risk assessment factors in the training data set after preprocessing are inputted; calculating an output of the s-th neuron of the hidden layer using a sigmoid activation function : ； wherein is the connection weight from the input layer to the s-th neuron of the hidden layer, is the threshold value of the s-th neuron of the hidden layer, s is the neuron number of the hidden layer, s = 1, 2, 3... h; calculating an output of the tth neuron of the output layer using a sigmoid activation function : ； In the formula, is the connection weight of the s-th neuron in the hidden layer to the t-th neuron in the output layer, is the threshold value of the t-th neuron in the output layer, t is the neuron number of the output layer, t = 1, 2, 3. For the output layer, the error of the tth neuron is given by The formula is: ； wherein is the desired output of the tth neuron of the output layer, is the actual output of the tth neuron of the output layer. The connection weights and the thresholds are updated by using the gradient descent method until the error of the network is less than the accuracy threshold stored in the database or the maximum number of iterations is reached; The current BIM construction safety risk assessment factors after preprocessing are inputted into the trained BP neural network model; The output vector of the output layer is obtained; The construction safety assessment level is determined according to the output vector by using the maximum membership principle.

6. The BIM-based engineering supervision method according to claim 1, characterized in that: The BIM project supervision risk early warning is issued based on the construction progress assessment level, the construction quality assessment level and the construction safety assessment level, and the specific analysis process is as follows: The construction progress assessment level, the construction quality assessment level and the construction safety assessment level are accumulated to obtain the BIM project supervision risk level; The BIM project supervision risk level is compared with the BIM project supervision risk critical level stored in the database; If the BIM project supervision risk level is not higher than the BIM project supervision risk critical level, the BIM project supervision risk level is transmitted to the data center, and the data center issues a BIM project supervision safety reminder to the construction management control end; If the BIM project supervision risk level is higher than the BIM project supervision risk critical level, the BIM project supervision risk level is transmitted to the data center, the data center issues a BIM project supervision risk early warning to the construction management control end, and the construction progress assessment level, the construction quality assessment level and the construction safety assessment level are displayed on the construction management control end.

7. A BIM-based engineering supervision management system applied to the BIM-based engineering supervision management method of any one of claims 1-6, characterized in that, The system comprises an initial BIM model acquisition module, an initial BIM model updating module, a construction progress assessment level determination module, a construction quality assessment level determination module, a safety risk influence data analysis module, a construction safety assessment level matching module and a supervision risk early warning issuing module, wherein: The initial BIM model acquisition module is used to import professional BIM modeling software by format conversion technology through engineering design drawings and material information tracing databases, extract basic building structure and mechanical and electrical equipment information, and obtain an initial BIM model; The initial BIM model updating module is used to introduce geographic information system data, obtain construction site coordinates, fuse the construction site coordinates with the initial BIM model by a coordinate matching algorithm, and obtain a BIM model; The construction progress assessment level determination module is used to assign time attributes to each construction task in the BIM model, collect construction progress data, construct a progress analysis model, obtain progress assessment factors, and determine a construction progress assessment level; The construction quality evaluation grade determination module is configured to analyze the construction quality state based on the component attributes in the BIM model and the quality monitoring data, and determine the construction quality evaluation grade based on a fuzzy comprehensive evaluation model; The safety risk influence data analysis module is configured to acquire construction safety risk influence data, analyze the construction safety risk influence data, and construct a BIM construction safety risk evaluation model, wherein the construction safety risk influence data specifically includes personnel state data, equipment operation state data, and environment state data; The construction safety evaluation grade matching module is configured to output the construction safety evaluation grade based on the output of the BIM construction safety risk evaluation model and in combination with a BP neural network model; The supervision risk early warning issuing module is configured to issue a BIM engineering supervision risk early warning based on the construction progress evaluation grade, the construction quality evaluation grade, and the construction safety evaluation grade.

Images