Engineering collaborative design method and system based on BIM technology

Abstract

The invention discloses an engineering collaborative design method and system based on a BIM technology, and relates to the technical field of construction collaborative management, and the method comprises the steps: extracting associated geological parameters from an initial BIM model, and generating a parameter adjustment instruction set through a multi-objective optimization algorithm by taking structure safety and construction cost as constraint conditions in combination with a high-risk component; performing block chain evidence storage on the parameter adjustment instruction set to generate an encryption instruction block; performing hierarchical compression on the encrypted instruction block by adopting a lightweight algorithm, and outputting a lightweight collaborative instruction set; and the lightweight collaborative instruction set is distributed to the AR terminal through the 5G-UWB network, and the geological risk area and the component change scheme are displayed in the construction scene in an overlapping manner. The timeliness and scientificity of risk early warning are remarkably improved by solving the surrounding rock-support structure multi-physics coupling equation in real time on the basis of the initial BIM model and outputting the risk state tensor.

Description

TECHNICAL FIELD

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

[0002] With the in-depth application of building information modeling (BIM) technology in the field of civil and construction engineering, the integration, visualization and intelligentization based on digital collaborative design have become the mainstream trend of industry development. BIM technology realizes information integration and sharing of the whole life cycle of design, construction and operation by constructing a three-dimensional digital model containing geometric information and non-geometric attributes. BIM has begun to integrate geological survey data, structural monitoring information and construction progress plan, forming preliminary multi-source data collaborative analysis capability. Data middleware or general interface standards (such as IFC, CityGML) are used to realize the format conversion and model integration of heterogeneous data, thereby supporting cross-stage and cross-professional design collaboration. Some research attempts to embed finite element analysis modules into the BIM platform to realize preliminary simulation evaluation of structural performance and provide certain basis for design optimization.

[0003] In the process of engineering collaborative design under complex geological environment, in underground engineering with variable geological conditions, there is often a semantic gap and spatial matching deviation between survey data, monitoring information and design model, which makes it difficult for geological attribute parameters to be effectively identified and utilized by BIM model, thereby affecting the accuracy of structural safety evaluation. At present, there is generally a lack of real-time solving capability of multi-physical field coupling of surrounding rock-supporting system, which cannot dynamically identify potential high-risk components in the design stage, resulting in time delay between risk warning and design adjustment. The traceability and safety guarantee mechanism of design change instruction in the multi-party collaboration environment is not perfect, which is easy to cause information distortion or difficulty in responsibility definition. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides an engineering collaborative design method and system based on BIM technology, which solves the problems of insufficient fusion of multi-source heterogeneous geological data and dynamic response lag of high-risk components.

[0006] To solve the above technical problems, the present application provides the following technical solutions: In a first aspect, the present application provides a BIM technology-based engineering collaborative design method, which comprises: collecting multi-source heterogeneous data and converting the multi-source heterogeneous data into standardized geological attribute parameters; generating an initial BIM model based on a spatial topology matching principle; solving a surrounding rock-supporting structure multi-physical field coupling equation based on the initial BIM model in real time, and outputting a risk state tensor; when any component in the risk state tensor exceeds a dynamic risk threshold set, marking a high-risk component; extracting associated geological parameters from the initial BIM model, combining the high-risk component, and generating a parameter adjustment instruction set through a multi-objective optimization algorithm with structural safety and construction cost as constraint conditions; performing blockchain notarization on the parameter adjustment instruction set to generate an encrypted instruction block; performing hierarchical compression on the encrypted instruction block using a lightweight algorithm to output a lightweight collaborative instruction set; and distributing the lightweight collaborative instruction set to an AR terminal through a 5G-UWB network to superimpose and display a geological risk area and a component change scheme in a construction scene.

[0007] As a preferred scheme of the BIM technology-based engineering collaborative design method, the conversion of the multi-source heterogeneous data into the standardized geological attribute parameters comprises the following specific steps: Obtaining surrounding rock strain values, rock mass fracture energy and rock mass score values to obtain multi-source heterogeneous data; Aligning time stamps of the multi-source heterogeneous data and performing spatial position registration, calculating structural complexity weights of the surrounding rock strain values, the rock mass fracture energy and the rock mass score values through a Hausdorff dimension algorithm, and fusing to generate standardized geological attribute parameters.

[0008] As a preferred scheme of the BIM technology-based engineering collaborative design method, the generation of the initial BIM model based on the spatial topology matching principle comprises the following specific steps: Analyzing anchor rod end points and lining connection points in a roadway design drawing and defining them as topology nodes, establishing a connection line between adjacent topology nodes and labeling attributes, and composing a spatial topology graph from the topology nodes and the connection line; Taking the topology nodes in the spatial topology graph as target positions, mapping the standardized geological attribute parameters to the target positions through a Kriging spatial interpolation algorithm, calculating adjacent topology node weights by analyzing spatial correlation of adjacent geological points, and obtaining horizontal principal stresses and damage factors; Assigning the horizontal principal stresses and the damage factors as attribute values to corresponding topology nodes in the spatial topology graph to obtain a geological attribute topology graph; Creating a three-dimensional anchor rod entity based on the topology nodes in the geological attribute topology graph, generating a roadway lining surface along the topology nodes, seamlessly connecting the anchor rod end points and the lining surface, and forming an initial BIM model.

[0009] As a preferred scheme of the engineering collaborative design method based on the BIM technology, the output risk state tensor has the following specific steps: The supporting member geometric parameters and real-time data of surrounding rock are extracted from the initial BIM model, the stress field equation is obtained by describing the stress balance of the surrounding rock strain value and the supporting structure, the seepage field equation is obtained by the impact effect of groundwater pressure on the supporting structure, and the damage field equation is obtained by quantifying the rock mass crack propagation and supporting fatigue accumulation; the stress field equation, the seepage field equation and the damage field equation are integrated to obtain the surrounding rock-supporting structure multi-physical field coupling equation. The roadway grid is generated by taking the roadway lining surface in the initial BIM model as the boundary, the damage field equation is solved by quantum annealing, the stress field equation and the seepage field equation are solved by GPU, and the risk state tensor is output.

[0010] As a preferred scheme of the engineering collaborative design method based on the BIM technology, the output risk state tensor has the following specific steps: The rock mass creep rate, roadway exposure time, rock mass score value and microseismic event frequency are collected; Based on the rock mass creep rate and the roadway exposure time, the stress threshold value is calculated by a nonlinear function, the damage threshold value is obtained by using a hierarchical down-regulation mechanism according to the microseismic event frequency, and the seepage threshold value is calculated based on the rock mass score value and the pore water pressure; the stress threshold value, the damage threshold value and the seepage threshold value are integrated into a dynamic risk threshold set; When any component of the risk state tensor exceeds the corresponding dynamic risk threshold set, the spatial coordinates of the corresponding roadway grid are located and the risk type is attached to obtain the high-risk component.

[0011] As a preferred scheme of the engineering collaborative design method based on the BIM technology, the output risk state tensor has the following specific steps: Based on the high-risk component and the initial BIM model, the spatial range is determined by taking the geometric center of the high-risk component as the center and the engineering influence as the radius in the initial BIM model according to the spatial proximity principle, all geological attribute parameters in the spatial range generated by the Kriging interpolation are extracted and associated to form a risk-parameter association graph; The risk-parameter association graph is input into a multi-objective optimization algorithm, and collaborative decision is made to obtain a high-risk component parameter adjustment amount set, and the parameter adjustment instruction set is formed by structured binding in the initial BIM model.

[0012] As a preferred scheme of the engineering collaborative design method based on the BIM technology, the output risk state tensor has the following specific steps: ​Based on the parameter adjustment instruction set, a hash value is calculated, and the hash value is digitally signed using a private key, and the parameter adjustment instruction set is uploaded to a distributed storage network to obtain a unique content identifier; Based on the parameter adjustment instruction set and the dynamic risk threshold set, a compliance proof is generated through privacy protection verification logic, and the hash value, digital signature, unique content identifier and compliance proof are assembled into a blockchain transaction and verified by consensus to generate an encrypted instruction block.

[0013] As a preferred scheme of the engineering collaborative design method based on BIM technology, the output lightweight collaborative instruction set has the following specific steps: Based on the content identifier in the encrypted instruction block, the parameter adjustment instruction set is retrieved and parsed from the distributed storage network, the parameter adjustment instruction set is converted into a semantic association graph structure representing the association relationship between components, and a low-dimensional semantic vector is generated through a neural network encoder; According to the terminal performance and network state, a corresponding hierarchical compression strategy is selected to quantize and encode the low-dimensional semantic vector to obtain a discrete symbol sequence; Based on the hierarchical compression strategy, the corresponding decoder identifier and codebook identifier are extracted from the decoding element database, and the discrete symbol sequence, the decoder identifier and the codebook identifier are encapsulated to generate the lightweight collaborative instruction set.

[0014] As a preferred scheme of the engineering collaborative design method based on BIM technology, the output lightweight collaborative instruction set has the following specific steps: The lightweight collaborative instruction set is transmitted to the target AR terminal through the 5G-UWB heterogeneous network, and the discrete symbol sequence is neural decoded to reconstruct the parameter adjustment instruction information to obtain the geological risk area and the component change scheme; The real-time high-precision pose of the AR terminal is calculated through the tight coupling sensor fusion algorithm, and the geological risk area and the component change scheme are superimposed and displayed in the field of view of the terminal in combination with the parameter adjustment instruction information.

[0015] In a second aspect, the application provides a BIM technology-based engineering collaborative design system, comprising: a BIM generation module, configured to collect multi-source heterogeneous data, and convert the multi-source heterogeneous data into standardized geological attribute parameters, and generate an initial BIM model based on a spatial topology matching principle; a monitoring module, configured to solve a surrounding rock-supporting structure multi-physical field coupling equation based on the initial BIM model in real time, and output a risk state tensor, and mark a high-risk component when any component in the risk state tensor exceeds a dynamic risk threshold set; an adjustment module, configured to extract associated geological parameters from the initial BIM model, combine the high-risk component, and generate a parameter adjustment instruction set by a multi-objective optimization algorithm with structural safety and construction cost as constraint conditions; a block module, configured to store the parameter adjustment instruction set in a blockchain, and generate an encrypted instruction block; a collaborative module, configured to perform hierarchical compression on the encrypted instruction block by using a lightweight algorithm, and output a lightweight collaborative instruction set; and a display module, configured to distribute the lightweight collaborative instruction set to an AR terminal through a 5G-UWB network, and superimpose and display a geological risk area and a component change scheme in a construction scene.

[0016] The application has the following beneficial effects: by converting multi-source heterogeneous data into standardized geological attribute parameters and generating an initial BIM model based on a spatial topology matching principle, accurate integration and structured modeling of geological information are achieved, and the uniformity of basic data and the accuracy of model construction are improved; by solving a surrounding rock-supporting structure multi-physical field coupling equation based on the initial BIM model in real time and outputting a risk state tensor, high-precision and real-time simulation analysis of the dynamic coupling of multi-physical fields in complex underground engineering is achieved, high-risk components can be identified in time, and the timeliness and scientificity of risk early warning are significantly improved, not only the mapping capability of the BIM model to the real geological environment is enhanced, but also the depth fusion and systematic improvement of engineering collaborative design to intelligence, safety and traceability are realized as a whole. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0018] Figure 1 The flowchart of the BIM technology-based engineering collaborative design method.

[0019] Figure 2 The schematic diagram of the BIM technology-based engineering collaborative design system.

[0020] Figure 3 The flowchart of obtaining the high-risk component.

[0021] Figure 4 A flowchart for generating a parameter adjustment instruction set. DETAILED DESCRIPTION

[0022] In order to make the above objectives, features and advantages of the present application more apparent, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0023] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details given herein. In other instances, well-known methods have not been described in detail in order to avoid unnecessarily obscuring the present application. Therefore, the specific embodiments given herein are not to be interpreted as limiting the scope of the application.

[0024] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments.

[0025] Reference Figure 1 For one embodiment of the present application, the embodiment provides a BIM technology-based engineering collaborative design method, comprising the following steps: S1, collecting multi-source heterogeneous data and converting the multi-source heterogeneous data into standardized geological attribute parameters.

[0026] S1.1, obtaining surrounding rock strain value, rock mass fracture energy and rock mass score value to obtain multi-source heterogeneous data.

[0027] Specifically, the surrounding rock strain value is measured by a resistance strain gauge installed on the surface of the surrounding rock. The resistance strain gauge converts the micro-deformation of the surrounding rock into a resistance change signal, and a data acquisition instrument records the resistance change at a sampling frequency of 100 times per second and converts it into a micro-strain value to obtain the surrounding rock strain value.

[0028] The rock mass fracture energy is collected by a microseismic monitoring sensor array arranged inside the rock mass. The sensor records the elastic wave vibration signal generated by the rock mass fracture, and calculates the energy value of each fracture event according to the amplitude and frequency integral of the vibration signal to obtain the rock mass fracture energy.

[0029] The rock mass score value is obtained by field geological logging. The rock mass structure surface spacing, rock block strength and groundwater conditions and other parameters are measured using a geological compass and a rock mass quality measuring gauge, and the values are assigned and summed according to the rock mass quality rating table to obtain the rock mass score value. The surrounding rock strain value, rock mass fracture energy and rock mass score value jointly constitute the multi-source heterogeneous data.

[0030] It should be noted that the energy value of each rupture event is expressed as: ; wherein, E represents the energy value of each rupture event, represents the ratio of the circumference of a circle to its diameter, represents the density of the rock mass, represents the propagation speed of the elastic wave in the rock mass, represents the distance from the source to the sensor, represents the signal duration, represents the particle, represents the particle propagation speed in the rock mass, represents the time, is a differential symbol, representing "infinitesimal increment of time".

[0031] S1.2, align the timestamps of the multi-source heterogeneous data, and perform spatial position registration, calculate the structural complexity weight of the rock mass strain value, rock mass rupture energy and rock mass score value through the Hausdorff dimension algorithm, and fuse to generate standardized geological attribute parameters.

[0032] Specifically, the precise clock synchronization protocol uses the IEEE 1588 precise time protocol to align the collection timestamps of the rock mass strain value, rock mass rupture energy and rock mass score value, so that all data can achieve microsecond-level time synchronization.

[0033] Spatial position registration: Collect the three-dimensional coordinates of each sensor installation point measured by the total station, establish a unified roadway coordinate system, and unify the measurement positions of the rock mass strain value, rock mass rupture energy and rock mass score value to the roadway coordinate system.

[0034] The Hausdorff dimension algorithm calculates the fractal dimension of the rock mass strain value time series, the rock mass rupture energy time series and the spatial distribution of the rock mass score value, to obtain the structural complexity weight of the rock mass strain value, the structural complexity weight of the rock mass rupture energy and the structural complexity weight of the rock mass score value.

[0035] The Hausdorff dimension algorithm calculates the fractal dimension of the rock mass strain value time series, the rock mass rupture energy time series and the spatial distribution of the rock mass score value: divide the rock mass strain value time series according to different time intervals (for example: 1, 2, 4, …, 1024 seconds), count the minimum box number of the coverage curve, and fit the double logarithmic coordinate slope to obtain the fractal dimension of the rock mass strain value; based on the rock mass rupture energy time series, construct an accumulated energy curve, divide and count the number of covered boxes according to the time interval, and fit the double logarithmic coordinate slope to obtain the fractal dimension of the rock mass rupture energy. Divide the grid in the projection plane of the roadway, count the number of grids containing the sampling points, and fit the double logarithmic coordinate slope to obtain the fractal dimension of the spatial distribution of the rock mass score value.

[0036] The surrounding rock strain value structure complexity weight, the rock mass fracture energy structure complexity weight and the rock mass score value structure complexity weight are obtained: by using a weighted fusion method, the surrounding rock strain value, the rock mass fracture energy and the rock mass score value are respectively weighted and data integrated according to the surrounding rock strain value structure complexity weight, the rock mass fracture energy structure complexity weight and the rock mass score value structure complexity weight, to obtain the standardized geological attribute parameters.

[0037] S2, based on the spatial topology matching principle, an initial BIM model is generated.

[0038] S2.1, the anchor rod endpoints and the lining connection points in the roadway design drawings are analyzed and defined as topology nodes, and connection lines are established between adjacent topology nodes and labeled with attributes, and the topology nodes and the connection lines form a spatial topology graph.

[0039] Specifically, the anchor rod endpoints and the lining connection points in the roadway design drawings are analyzed, each anchor rod endpoint and lining connection point is defined as a topology node, a connection line is established between adjacent topology nodes and each connection line is labeled with material type and cross-sectional size attributes, and the spatial topology graph is formed by all topology nodes and all connection lines labeled with attributes.

[0040] S2.2, taking the topology nodes in the spatial topology graph as target positions, the standardized geological attribute parameters are mapped to the target positions by the Kriging spatial interpolation algorithm, the spatial correlation of adjacent geological points is analyzed, the weights of adjacent topology nodes are calculated, and the horizontal principal stress and the damage factor are obtained.

[0041] Specifically, taking the topology nodes in the spatial topology graph as target positions, the standardized geological attribute parameters are mapped to the target positions by the Kriging spatial interpolation algorithm, the spatial correlation between the standardized geological attribute parameter sampling points is obtained by the semi-variogram function, the weight coefficients of the adjacent standardized geological attribute parameter sampling points around each topology node are obtained, the standardized geological attribute parameters are weighted based on the weight coefficients, and the horizontal principal stress and the damage factor corresponding to each topology node are generated.

[0042] It should be noted that the spatial correlation between the standardized geological attribute parameter sampling points includes the mathematical relationship between the change degree of the geological attribute parameters and the distance between the sampling points, the difference in the change of the geological attribute parameters in different directions, and the change pattern of the geological attribute in the spatial scale.

[0043] S2.3, taking the horizontal principal stress and the damage factor as attribute values, the corresponding topology nodes in the spatial topology graph are assigned, and a geological attribute topology graph is obtained.

[0044] Specifically, the horizontal principal stress value and the damage factor value are assigned to the corresponding topological nodes in the spatial topological graph as attribute values: traversing each topological node in the spatial topological graph, the node horizontal principal stress obtained by the Kriging spatial interpolation algorithm is written into the node attribute field "horizontal principal stress", and the damage factor is written into the node attribute field "damage factor"; at the same time, the original topological node spatial coordinate information and the connection line attributes between nodes in the spatial topological graph are retained; and a geological attribute topological graph is formed.

[0045] S2.4, based on the topological nodes in the geological attribute topological graph, creating a three-dimensional anchor rod entity, and at the same time generating a roadway lining surface along the topological nodes, seamlessly connecting the anchor rod end points and the lining surface to form an initial BIM model.

[0046] Specifically, based on the topological nodes in the geological attribute topological graph, a three-dimensional anchor rod entity is created, and the three-dimensional anchor rod entity is generated by the stretch command of the BIM software. The stretch command takes the topological node as the starting point and extends to the designed length along the anchor rod design direction to form an entity.

[0047] At the same time, a roadway lining surface is generated along the topological nodes, and the roadway lining surface is generated by the loft command of the BIM software. The loft command takes the topological node as the control point and forms a continuous surface according to the roadway design contour, seamlessly connects the anchor rod end points and the lining surface, and seamlessly connects the anchor rod end points and the lining surface through the geometry trimming command of the BIM software. The geometry trimming command accurately trims the intersection part of the anchor rod entity and the lining surface, so that the anchor rod end points are completely embedded in the lining surface to form a complete connection, and an initial BIM model is formed.

[0048] S3, based on the initial BIM model, real-time solving of the surrounding rock-supporting structure multi-physical field coupling equation, outputting the risk state tensor.

[0049] S3.1, extracting supporting member geometric parameters and surrounding rock real-time data from the initial BIM model, and obtaining the stress field equation by describing the stress balance between the surrounding rock strain value and the supporting structure.

[0050] Specifically, the supporting member geometric parameters and the surrounding rock real-time data are extracted from the initial BIM model. The supporting member geometric parameters include the anchor rod length, the anchor rod diameter and the lining thickness, and the surrounding rock real-time data include the surrounding rock strain value and the rock mass fracture energy.

[0051] The Hooke's law provides the material properties of the rock mass itself, and the balance equation provides the physical law that must be followed. By combining the two and introducing the force of the supporting structure as an external force into the balance equation, the stress field equation is established.

[0052] S3.2, obtain the seepage field equation by the impact effect of groundwater pressure on the supporting structure, and obtain the damage field equation by quantifying the rock mass fracture expansion and supporting fatigue accumulation; integrate the stress field equation, the seepage field equation and the damage field equation to obtain the surrounding rock-supporting structure multi-physical field coupling equation.

[0053] Specifically, the seepage field equation is obtained by the impact effect of groundwater pressure on the supporting structure, and the seepage field equation is established based on Darcy's law and the law of conservation of mass; the damage field equation is obtained by quantifying the rock mass fracture expansion and supporting fatigue accumulation, and the damage field equation adopts the continuous medium damage mechanics theory, and the supporting fatigue accumulation adopts the Miner linear cumulative damage theory; the surrounding rock-supporting structure multi-physical field coupling equation is formed by the simultaneous solution of the stress field equation, the seepage field equation and the damage field equation.

[0054] S3.3, taking the roadway lining surface in the initial BIM model as the boundary, generating the roadway grid, solving the damage field equation by quantum annealing, solving the stress field equation and the seepage field equation by GPU, and outputting the risk state tensor.

[0055] Specifically, taking the roadway lining surface in the initial BIM model as the boundary, generating the roadway grid, the roadway grid is discretized in space by tetrahedron, and the roadway grid size is determined according to the geometric characteristics of the roadway, for example, the roadway grid size is 5 cm in the area with large curvature, and the roadway grid size is 10 cm in the flat area.

[0056] Solving the damage field equation by quantum annealing, quantum annealing converts the solution of the damage field equation into a quadratic unconstrained binary optimization problem, and uses the superposition and tunneling effect of quantum bits to find the global optimal solution to obtain the damage variable; solving the stress field equation and the seepage field equation by GPU in parallel, the GPU uses the CUDA architecture for parallel computing, and the finite element discrete equation set of the stress field equation and the seepage field equation is decomposed into multiple parallel threads for simultaneous solution; the stress field equation is solved by the preconditioned conjugate gradient method to obtain the node displacement vector, and the seepage field equation is solved by Darcy's law to calculate the seepage velocity field; based on the displacement solution, the stress tensor components of each roadway grid are calculated, combined with the seepage velocity components and the independently solved damage variables, and the risk state tensor is assembled and output according to the roadway grid number.

[0057] S4, when any component in the risk state tensor exceeds the dynamic risk threshold set, marking the high-risk component, for details, please refer to Figure 3 .

[0058] S4.1, collect the rock mass creep rate, roadway exposure time, rock mass score value and microseismic event frequency.

[0059] Specifically, the rock mass creep rate, the roadway exposure time and the microseismic event frequency are collected, the rock mass creep rate is recorded by a creep measuring instrument installed on the surface of the roadway surrounding rock in millimeters per hour, the roadway exposure time is recorded by the construction log in hours from the completion of roadway excavation to the current time, and the microseismic event frequency is counted by a microseismic monitoring sensor array in the number of events per day; and the rock mass score value is obtained through field geological recording.

[0060] S4.2, based on the rock mass creep rate and the roadway exposure time, the stress threshold value is calculated by a nonlinear function, according to the microseismic event frequency, the damage threshold value is obtained by using a hierarchical down-regulation mechanism, and based on the rock mass score value and the pore water pressure, the seepage threshold value is calculated, and the stress threshold value, the damage threshold value and the seepage threshold value are integrated into a dynamic risk threshold value set.

[0061] Specifically, the stress threshold value is set: based on the rock mass creep rate and the roadway exposure time, the stress threshold value is calculated by a nonlinear function, and the nonlinear function adopts an exponential decay form; The damage threshold value is set: according to the microseismic event frequency, the damage threshold value is obtained by using a hierarchical down-regulation mechanism, and the hierarchical down-regulation mechanism sets three microseismic event frequency intervals: for example, 0-5 times / day corresponds to a damage threshold value of 0.8, 5-10 times / day corresponds to a damage threshold value of 0.6, and more than 10 times / day corresponds to a damage threshold value of 0.4; The seepage threshold value is set: based on the rock mass score value and the pore water pressure, the seepage threshold value is calculated; and the stress threshold value, the damage threshold value and the seepage threshold value are sequentially integrated into a dynamic risk threshold value set.

[0062] It should be noted that the expression for calculating the stress threshold value is: ; Wherein, represents the stress threshold value, represents the strength reference coefficient, represents the natural exponential, represents the creep sensitivity coefficient, represents the rock mass creep rate, represents the time-dependent strengthening coefficient, represents the roadway exposure time, represents the reference time, which is a reference time for dimensionless normalization, and is taken as , is a dimensionless quantity, which ensures the mathematical rationality of the logarithmic function.

[0063] The expression for calculating the seepage threshold value is: ; Wherein, represents the seepage threshold value, represents the RMR influence coefficient, wherein , representing rock mass quality score, representing reference seepage pressure.

[0064] S4.3, when any component of the risk state tensor exceeds the corresponding dynamic risk threshold set, locate the spatial coordinates of the corresponding roadway grid and attach the risk type to obtain the high-risk component.

[0065] Specifically, traverse all the risk state tensors of the roadway grids, the risk state tensor contains the stress component, seepage velocity component and damage variable of each roadway grid; when the stress component in the risk state tensor exceeds the stress threshold component in the dynamic risk threshold set, or the seepage velocity component exceeds the seepage threshold component in the dynamic risk threshold set, or the damage variable exceeds the damage threshold component in the dynamic risk threshold set, the spatial coordinates of the corresponding roadway grid are located by a quantum search algorithm, the quantum search algorithm uses Grover search algorithm to search the roadway grid number in the roadway grid database that meets the risk overrun condition, and the spatial coordinates of the roadway grid are obtained according to the roadway grid number index, to obtain the high-risk component.

[0066] According to the overrunning risk state tensor component, the high-risk component is determined: the stress component exceeding the stress threshold is marked as a stress risk type, the seepage velocity component exceeding the seepage threshold is marked as a seepage risk type, and the damage variable exceeding the damage threshold is marked as a damage risk type.

[0067] S5, extract the associated geological parameters from the initial BIM model, and combine the high-risk components to generate a parameter adjustment instruction set by a multi-objective optimization algorithm with structural safety and construction cost as constraint conditions, for details, please refer to Figure 4 .

[0068] S5.1, based on the high-risk components and the initial BIM model, through the principle of spatial proximity, the spatial range is determined in the initial BIM model with the geometric center of the high-risk component as the center and the engineering influence as the radius, all geological attribute parameters within the spatial range generated by Kriging interpolation are extracted and associated to form a risk-parameter correlation diagram.

[0069] Specifically, based on the high-risk components and the initial BIM model, through the principle of spatial proximity, the spatial range is determined in the initial BIM model with the geometric center of the high-risk component as the center and the engineering influence radius as an example of 5 meters, all geological attribute parameters within the spatial range generated by Kriging interpolation are extracted, and the geological attribute parameters include the horizontal principal stress value and the damage factor value.

[0070] Correlate the high-risk components with the extracted horizontal principal stress values and damage factor values, with the high-risk components as nodes, the node attributes containing the types, risk levels of the high-risk components, and the associated horizontal principal stress values and damage factor values, and establish edges between the high-risk component nodes that are physically connected or spatially adjacent, with the edge attributes containing the connection type and the influence coefficient, to form a risk-parameter correlation graph.

[0071] It should be noted that the geological attribute parameter extraction process: taking the geometric center of the high-risk component as the center and the engineering influence radius as the search radius, extracting all the horizontal principal stress values and damage factor values generated by the Kriging interpolation within the spatial range, and taking the average value of the geological attribute parameters as the associated parameters of the high-risk component.

[0072] S5.2, input the risk-parameter correlation graph into the multi-objective optimization algorithm, and make a collaborative decision to obtain a set of high-risk component parameter adjustment amounts, and perform structured binding in the initial BIM model to form a parameter adjustment instruction set.

[0073] Specifically, the risk-parameter correlation graph is input into the multi-objective optimization algorithm, and the risk-parameter correlation graph is collaboratively decided based on a deep reinforcement learning algorithm. The deep reinforcement learning algorithm uses a multi-agent collaborative optimization framework, each high-risk component is regarded as an independent agent, and a parameter adjustment scheme is output through a policy network to obtain a set of high-risk component parameter adjustment amounts, which includes the design parameter adjustment values of each high-risk component.

[0074] In the initial BIM model, structured binding is performed by associating and mapping each adjustment value in the high-risk component parameter adjustment amount set with the unique identifier of the corresponding component in the initial BIM model to form a parameter adjustment instruction set.

[0075] It should be noted that the deep reinforcement learning algorithm execution process: each agent observes the state of the adjacent nodes in the risk-parameter correlation graph, generates actions (parameter adjustment amounts) through a policy network, and all agents collaboratively maximize a long-term reward function, which includes safety performance improvement and cost control indicators.

[0076] The structured binding process: traverse each entry in the high-risk component parameter adjustment amount set, locate the corresponding component in the initial BIM model according to the component unique identifier, and establish a mapping relationship between the adjustment value and the component object.

[0077] Parameter adjustment instruction set generation: serialize each component's identifier, type, pre-adjustment parameter value, and post-adjustment parameter value in JSON format to form a parameter adjustment instruction set.

[0078] S6, the parameter adjustment instruction set is stored in the blockchain, and an encrypted instruction block is generated.

[0079] S6.1, based on the parameter adjustment instruction set, calculate the hash value, and use the private key to digitally sign the hash value, upload the parameter adjustment instruction set to the distributed storage network, and obtain a unique content identifier.

[0080] Specifically, based on the parameter adjustment instruction set, the SHA-256 algorithm is used to calculate the JSON string of the parameter adjustment instruction set to obtain a 256-bit hash value.

[0081] The hash value is digitally signed using a private key. The digital signature uses the ECDSA elliptic curve digital signature algorithm, which uses the constructor's private key to sign the hash value to generate a digital signature. The parameter adjustment instruction set is uploaded to the distributed storage network. The distributed storage network uses the IPFS protocol, and the parameter adjustment instruction set is uploaded to the IPFS network in the form of a file to obtain a unique content identifier.

[0082] It should be noted that the hash value calculation process: the JSON string of the parameter adjustment instruction set is UTF-8 encoded, and the SHA-256 hash function is iterated to output a fixed length of 256-bit hash value.

[0083] The digital signature generation process: using the elliptic curve digital signature algorithm, taking the constructor's private key as input, performing encryption operation on the hash value to generate a digital signature.

[0084] The IPFS upload process: The parameter adjustment instruction set file is divided into data blocks with a size of 256KB, and each data block is hashed to build a Merkle DAG structure to obtain a root hash as a content identifier.

[0085] S6.2, based on the parameter adjustment instruction set and the dynamic risk threshold set, generate a compliance proof through a privacy protection verification logic, assemble the hash value, digital signature, unique content identifier and compliance proof into a blockchain transaction, and generate an encrypted instruction block after consensus verification.

[0086] Specifically, based on the parameter adjustment instruction set and the dynamic risk threshold set, generate a compliance proof through a privacy protection verification logic, the privacy protection verification logic uses a zero-knowledge proof algorithm to verify that all risk state tensor components corresponding to the adjustment schemes in the parameter adjustment instruction set are lower than the dynamic risk threshold set. Assemble the hash value, digital signature, unique content identifier and compliance proof into a blockchain transaction, which contains structured fields of these data. After consensus verification, an encrypted instruction block is generated.

[0087] The hash value is generated by SHA-256, and is digitally signed by using a private key of a construction party (ECDSA algorithm), so as to ensure data integrity and identity credibility; the instruction set file is uploaded to an IPFS distributed network, and a unique content identifier (CID) is obtained; in the current engineering construction information management, construction instructions are usually transmitted and recorded through paper files, emails or centralized project management platforms, and are easy to be tampered with, operation records can be deleted, responsibilities are not clear when multiple parties cooperate, and an effective anti-forgery verification mechanism is lacked; compared with the prior art, the compliance proof is generated by using the zero-knowledge proof technology, and it is verified that the adjustment scheme meets the safety threshold requirement without leaking sensitive information; the hash value, signature, CID and compliance proof are packaged into a blockchain transaction, and an encrypted instruction block is generated after consensus, so that the credible evidence and tamper-proof distribution of the instruction are realized.

[0088] S7, a lightweight algorithm is used to compress the encrypted instruction block in stages, and a lightweight collaborative instruction set is output.

[0089] S7.1, based on the content identifier in the encrypted instruction block, the parameter adjustment instruction set is retrieved and parsed from the distributed storage network, the parameter adjustment instruction set is converted into a semantic association graph structure representing the association relationship between components, and a low-dimensional semantic vector is generated through a neural network encoder.

[0090] Specifically, based on the content identifier in the encrypted instruction block, the parameter adjustment instruction set is retrieved and parsed from the distributed storage network, the content identifier is used as an index to locate and obtain the parameter adjustment instruction set file in the IPFS protocol network, and the JSON format file is parsed into structured data containing component identifier, component type, original parameter value and adjusted parameter value.

[0091] The parameter adjustment instruction set is converted into a semantic association graph structure representing the association relationship between components, the semantic association graph structure takes each component in the parameter adjustment instruction set as a node, the node attributes include component type, original parameter value and adjusted parameter value, and edges are established between component nodes with physical connection or spatial distance less than an example value of 2 meters according to the spatial topological relationship in the BIM initial model, and the edge attributes include connection type and spatial distance.

[0092] A low-dimensional semantic vector is generated through a neural network encoder: the neural network encoder adopts a graph autoencoder architecture, the graph autoencoder part includes three layers of graph convolutional networks, each layer uses a ReLU activation function, and the output layer compresses the graph features into a low-dimensional semantic vector.

[0093] S7.2, according to the terminal performance and network state, a corresponding hierarchical compression strategy is selected to quantitatively encode the low-dimensional semantic vector, and a discrete symbol sequence is obtained.

[0094] Specifically, based on the terminal performance classification, the low-dimensional semantic vector is quantized and encoded: the components of the low-dimensional semantic vector are mapped to the nearest discrete value of the selected codebook level (example: a 64-level codebook maps the value 0.73 to the 47th discrete value), a binary symbol sequence is generated, and then compressed according to the network state classification, and a discrete symbol sequence is output.

[0095] It should be noted that according to the combination of engineering experience criteria and communication industry standards, different codebook levels are selected according to the classification of terminal performance: for example, when GPU memory is ≥8GB and CPU core is ≥8, a 256-level codebook quantization is selected; when GPU memory is 4-8GB and CPU core is 4-8, a 128-level codebook quantization is selected; when GPU memory is <4GB and CPU core is <4, a 64-level codebook quantization is selected.

[0096] According to the classification of network state, different compression modes are selected: for example, when the bandwidth is ≥100Mbps, lossless compression (LZ77 algorithm) is enabled; when the bandwidth is 10-100Mbps, lossy compression (compression ratio 0.7) is enabled; when the bandwidth is <10Mbps, lossy compression (compression ratio 0.5) is enabled.

[0097] S7.3, based on the hierarchical compression strategy, extracting the corresponding decoder identifier and codebook identifier from the decoding element database, packaging the discrete symbol sequence, decoder identifier and codebook identifier, and generating a lightweight collaborative instruction set.

[0098] Specifically, based on the hierarchical compression strategy, the corresponding decoder identifier and codebook identifier are extracted from the decoding element database: according to the codebook level (example: 64-level codebook) and compression mode selected by the hierarchical compression strategy, the matching decoder version identifier and codebook identifier are queried in the decoding element database; the discrete symbol sequence, decoder identifier and codebook identifier are packaged into a JSON format data structure, the JSON structure contains three fields: symbol_sequence: stores the discrete symbol sequence; decoder_id: stores the decoder identifier; codebook_id: stores the codebook identifier; generates a lightweight collaborative instruction set.

[0099] It should be noted that based on the initial BIM model and parameter adjustment instruction set data, different versions of neural network decoders are trained, and a multi-level codebook is generated through K-means clustering, and a fixed mapping relationship between the compression strategy and the corresponding decoder identifier and codebook identifier is established, and a decoding element database is obtained.

[0100] S8, distribute the lightweight collaborative instruction set to the AR terminal through the 5G-UWB network, and superimpose and display the geological risk area and the component change scheme in the construction scene.

[0101] S8.1, transmit lightweight collaborative instruction set to target AR terminal through 5G-UWB heterogeneous network, and perform neural decoding on discrete symbol sequence to reconstruct parameter adjustment instruction information, and obtain geological risk area and component change scheme.

[0102] Specifically, based on the lightweight collaborative instruction set, the downlink is dynamically selected to the target AR terminal through the 5G-UWB heterogeneous network (UWB link is enabled when the terminal distance from the UWB base station is less than or equal to 10 meters, otherwise the 5G millimeter wave link is enabled); the decoder identifier and the codebook identifier in the lightweight collaborative instruction set are parsed at the AR terminal, and the neural network decoder and the corresponding codebook are added; the neural network decoder reconstructs the discrete symbol sequence into a semantic associated graph structure through a three-layer graph deconvolution network, and outputs the reconstructed parameter adjustment instruction information.

[0103] The component spatial coordinate set with the risk type of "stress risk type" or "seepage risk type" is extracted from the reconstructed parameter adjustment instruction information as the geological risk area, and the adjusted parameter values of all components are extracted to generate the component change scheme.

[0104] S8.2, calculate the real-time high-precision pose of the AR terminal through the tightly coupled sensor fusion algorithm, and superimpose and display the geological risk area and the component change scheme in the terminal field of view in combination with the parameter adjustment instruction information.

[0105] Specifically, the real-time high-precision pose of the AR terminal is calculated through the tightly coupled sensor fusion algorithm: the UWB positioning signal is combined with the visual-inertial data, the UWB positioning signal calculates the absolute coordinates of the terminal through the TDOA time difference algorithm, the visual-inertial data extracts feature points to track the change in pose through the ORB-SLAM3 algorithm, and the UWB absolute coordinates and the visual-inertial relative pose are fused using an extended Kalman filter, and a 6-degree-of-freedom pose is output.

[0106] In combination with the parameter adjustment instruction information, the geological risk area and the component change scheme are superimposed and displayed in the terminal field of view: the geological risk area rendering, locating the component spatial coordinates with the risk type of "stress risk type" or "seepage risk type" in the reconstructed parameter adjustment instruction information, generating a translucent warning area (example: stress risk with red pulse cover surface, seepage risk with blue ripple cover surface) centered on the component spatial coordinates, and dynamically adjusting the warning area radius according to the risk level.

[0107] Component change scheme rendering: superimpose a green translucent BIM model (such as the adjusted anchor rod entity) at the corresponding component position, and suspend the parameter change value; the rendering process uses perspective projection transformation to map three-dimensional coordinates to terminal screen coordinate system, and uses OpenGL ES 3.0 to realize real-time rendering.

[0108] The optimal link is dynamically selected through the 5G-UWB heterogeneous network, the lightweight instruction set is transmitted to the AR terminal, the semantic information is reconstructed by using the neural network decoder, the high-precision terminal pose is calculated by tightly coupling the UWB positioning and the visual-inertial data, and finally the geological risk area and the component adjustment scheme are accurately visualized in the AR field of view in the form of dynamic color and model superposition, guiding the on-site construction. The prior art usually adopts relatively independent steps: design coordination is performed through the BIM model, and off-line or near real-time safety monitoring is performed depending on the sensor, and the warning information is mainly presented in the form of two-dimensional charts or screen alarms. In comparison, the present scheme ensures lossless and real-time information through dynamic heterogeneous network and intelligent decoding; the industry problem of accurate positioning in a large space is solved through tight coupling of UWB and visual-inertial fusion, so that the AR information can be registered with centimeter-level precision; and finally, the abstract risk data and drawing scheme are converted into immersive and visual three-dimensional guidance and directly superimposed on the real environment, thereby fundamentally eliminating information misreading delay, realizing true human-computer intelligent cooperation and safe and controllable intelligent construction.

[0109] Please refer to Figure 2 The embodiment also provides an engineering collaborative design system based on BIM technology, which comprises a BIM generation module, a monitoring module, an adjustment module, a block module, a collaboration module and a display module. The BIM generation module is used for collecting multi-source heterogeneous data and converting the multi-source heterogeneous data into standardized geological attribute parameters, and generating an initial BIM model based on a spatial topology matching principle. The monitoring module is used for solving a surrounding rock-supporting structure multi-physical field coupling equation based on the initial BIM model in real time, outputting a risk state tensor, and marking a high-risk component when any component in the risk state tensor exceeds a dynamic risk threshold set. The adjustment module is used for extracting associated geological parameters from the initial BIM model, combining the high-risk component, and generating a parameter adjustment instruction set by taking structure safety and construction cost as constraint conditions through a multi-objective optimization algorithm. The block module is used for block chain notarization of the parameter adjustment instruction set and generation of an encrypted instruction block. The collaboration module is used for hierarchical compression of the encrypted instruction block by using a lightweight algorithm and output of a lightweight collaborative instruction set. The display module is used for distributing the lightweight collaborative instruction set to an AR terminal through a 5G-UWB network and superimposed display of a geological risk area and a component change scheme in a construction scene.

[0110] The embodiment also provides a computer device, which comprises a memory and a processor. The memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to realize the engineering collaborative design method based on the BIM technology as proposed in the above embodiment.

[0111] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, a trackball or a touchpad arranged on the shell of the computer device, or an external keyboard, a touchpad or a mouse, etc.

[0112] The embodiment also provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the method for engineering collaborative design based on BIM technology according to the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0113] To sum up, by converting multi-source heterogeneous data into standardized geological attribute parameters and generating an initial BIM model based on the spatial topological matching principle, the application realizes accurate integration and structured modeling of geological information, improves the uniformity of basic data and the accuracy of model construction; by solving the surrounding rock-supporting structure multi-physical field coupling equation in real time on the basis of the initial BIM model and outputting the risk state tensor, the application realizes high-precision and real-time simulation analysis of the dynamic coupling of multi-physical fields in complex underground engineering, can identify high-risk components in time, and significantly improves the timeliness and scientificity of risk warning, not only enhances the mapping ability of the BIM model to the real geological environment, but also realizes the deep integration and systematic improvement of intelligentization, safety and traceability of engineering collaborative design as a whole.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A collaborative engineering design method based on BIM technology, characterized in that: include: Collect multi-source heterogeneous data and transform it into standardized geological attribute parameters. Based on the principle of spatial topology matching, generate an initial BIM model. Based on the initial BIM model, the multiphysics coupling equation of the surrounding rock-support structure is solved in real time, and the risk state tensor is output. When any component of the risk state tensor exceeds the dynamic risk threshold set, the high-risk component is marked. Relevant geological parameters are extracted from the initial BIM model and combined with high-risk components. A multi-objective optimization algorithm is used to generate a parameter adjustment instruction set under the constraints of structural safety and construction cost. The parameter adjustment instruction set is stored on the blockchain to generate encrypted instruction blocks. A lightweight algorithm is used to perform hierarchical compression on the encrypted instruction block, and output a lightweight cooperative instruction set. The lightweight collaborative instruction set is distributed to AR terminals via the 5G-UWB network, and geological risk areas and component change plans are overlaid and displayed in the construction scene.

2. The engineering collaborative design method based on BIM technology as described in claim 1, characterized in that: The specific steps for converting multi-source heterogeneous data into standardized geological attribute parameters are as follows: Obtain surrounding rock strain values, rock mass fracture energy, and rock mass score values ​​to obtain multi-source heterogeneous data; The timestamps of multi-source heterogeneous data are aligned and spatially registered. The structural complexity weights of surrounding rock strain, rock mass fracture energy, and rock mass score are calculated using the Hausdorff dimension algorithm and then fused to generate standardized geological attribute parameters.

3. The engineering collaborative design method based on BIM technology as described in claim 2, characterized in that: The initial BIM model is generated based on the spatial topology matching principle. The specific steps are as follows: Analyze the anchor bolt endpoints and lining connection points in the tunnel design drawings and define them as topological nodes. Establish connection lines between adjacent topological nodes and label their attributes. The topological nodes and connection lines form a spatial topology map. Using the topological nodes in the spatial topology map as the target locations, the standardized geological attribute parameters are mapped to the target locations through the Kriging spatial interpolation algorithm. By analyzing the spatial correlation of neighboring geological points, the weights of neighboring topological nodes are calculated to obtain the horizontal principal stress and damage factor. By assigning the horizontal principal stress and damage factor as attribute values ​​to the corresponding topological nodes in the spatial topology map, a geological attribute topology map is obtained. A three-dimensional anchor bolt entity is created based on the topological nodes in the geological attribute topology map. At the same time, a tunnel lining surface is generated along the topological nodes, and the anchor bolt endpoints are seamlessly connected to the lining surface to form an initial BIM model.

4. The engineering collaborative design method based on BIM technology as described in claim 1, characterized in that: The specific steps for outputting the risk state tensor are as follows: Geometric parameters of support components and real-time data of surrounding rock are extracted from the initial BIM model. Stress field equations are obtained by establishing the stress balance between the strain value of surrounding rock and the force balance of the support structure. The seepage field equation is obtained by analyzing the impact effect of groundwater pressure on the support structure. The damage field equation is obtained by quantifying the rock mass fracture propagation and support fatigue accumulation. The stress field equation, seepage field equation, and damage field equation are integrated to obtain the multi-physics field coupling equation of the surrounding rock-support structure. Using the tunnel lining surface in the initial BIM model as the boundary, a tunnel mesh is generated. The damage field equation is solved by quantum annealing, and the stress field equation and seepage field equation are solved by GPU. The risk state tensor is then output.

5. The engineering collaborative design method based on BIM technology as described in claim 1, characterized in that: The specific steps for marking high-risk components are as follows: Collect rock mass creep rate, tunnel exposure time, rock mass score, and microseismic event frequency; Based on the rock mass creep rate and the roadway exposure time, the stress threshold is calculated by nonlinear function. The damage threshold is obtained by a graded down-adjustment mechanism according to the frequency of microseismic events. The seepage threshold is calculated based on the rock mass score and pore water pressure. The stress threshold, damage threshold and seepage threshold are integrated into a dynamic risk threshold set. When any component of the risk state tensor exceeds the corresponding dynamic risk threshold set, the spatial coordinates of the corresponding roadway grid are located, and the risk type is attached to obtain the high-risk component.

6. The engineering collaborative design method based on BIM technology as described in claim 1, characterized in that: The specific steps for generating the parameter adjustment instruction set are as follows: Based on high-risk components and the initial BIM model, and through the principle of spatial proximity, the spatial range is defined in the initial BIM model with the geometric center of the high-risk component as the center and the engineering impact as the radius. All geological attribute parameters generated by Kriging interpolation within the spatial range are extracted and associated to form a risk-parameter association map. The risk-parameter correlation diagram is input into a multi-objective optimization algorithm and collaborative decision-making is performed to obtain a set of parameter adjustment amounts for high-risk components. These adjustments are then structurally bound in the initial BIM model to form a parameter adjustment instruction set.

7. The engineering collaborative design method based on BIM technology as described in claim 1, characterized in that: The specific steps for generating the encrypted instruction block are as follows: Based on the parameter tuning instruction set, calculate the hash value and digitally sign the hash value using the private key; upload the parameter tuning instruction set to the distributed storage network to obtain a unique content identifier; Based on the parameter adjustment instruction set and dynamic risk threshold set, compliance proof is generated through privacy protection verification logic. The hash value, digital signature, unique content identifier and compliance proof are assembled into a blockchain transaction and generated into an encrypted instruction block after consensus verification.

8. The engineering collaborative design method based on BIM technology as described in claim 1, characterized in that: The specific steps for outputting the lightweight collaborative instruction set are as follows: Based on the content identifier in the encrypted instruction block, the parameter adjustment instruction set is retrieved and parsed from the distributed storage network, and the parameter adjustment instruction set is converted into a semantic association graph structure representing the relationship between components. Then, a low-dimensional semantic vector is generated through a neural network encoder. Based on terminal performance and network status, select the corresponding hierarchical compression strategy to quantize and encode the low-dimensional semantic vector to obtain a discrete symbol sequence; Based on a hierarchical compression strategy, the corresponding decoder identifier and codebook identifier are extracted from the decoding metadata database. The discrete symbol sequence, decoder identifier, and codebook identifier are encapsulated to generate a lightweight cooperative instruction set.

9. The engineering collaborative design method based on BIM technology as described in claim 1, characterized in that: The specific steps for overlaying and displaying geological risk areas and component modification plans in the construction scenario are as follows: The lightweight collaborative instruction set is transmitted to the target AR terminal through a 5G-UWB heterogeneous network, and the discrete symbol sequence is neurally decoded to reconstruct the parameter adjustment instruction information, thereby obtaining the geological risk area and component change plan. The AR terminal's real-time high-precision pose is calculated using a tightly coupled sensor fusion algorithm, and combined with parameter adjustment command information, the geological risk area and component change plan are overlaid and displayed in the terminal's field of view.

10. A BIM-based collaborative engineering design system, based on the BIM-based collaborative engineering design method according to any one of claims 1 to 9, characterized in that: include: The BIM generation module is used to collect multi-source heterogeneous data and transform it into standardized geological attribute parameters. Based on the principle of spatial topology matching, it generates an initial BIM model. The monitoring module is used to solve the multiphysics coupling equation of the surrounding rock-support structure in real time based on the initial BIM model and output the risk state tensor. When any component of the risk state tensor exceeds the dynamic risk threshold set, the high-risk component is marked. The adjustment module is used to extract relevant geological parameters from the initial BIM model, combine them with high-risk components, and generate a set of parameter adjustment instructions through a multi-objective optimization algorithm, with structural safety and construction cost as constraints. The block module is used to store parameter adjustment instruction sets on the blockchain and generate encrypted instruction blocks. The collaboration module is used to perform hierarchical compression of encrypted instruction blocks using a lightweight algorithm, and output a lightweight collaboration instruction set. The display module is used to distribute a lightweight collaborative instruction set to the AR terminal via the 5G-UWB network, and overlay the geological risk area and component change plan in the construction scene.

Images