Fabricated machine room modular installation method and system based on digital twinning

Abstract

The invention discloses an assembly type machine room modular installation method and system based on digital twinning, and relates to the technical field of building construction.The method comprises the steps that static data are collected, a BIM model is established, the component installation process is simulated and optimized, and the component position and the butt joint state are collected in real time through the Internet of Things; and establishing a digital twinborn model for modular installation of the assembly type machine room, and dynamically adjusting the installation process of the modular components. The modular installation method is provided for solving the problems that an installation sequence is difficult to plan, module butt joint is inaccurate and the like, the installation sequence and butt joint precision are optimized to a certain degree, errors are reduced, the installation efficiency and quality of the assembly type machine room are improved, and theoretical and technical supports are provided for modular installation of the assembly type machine room.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction, and in particular to a modular installation method and system for an assembled computer room based on digital twins. Background Art

[0002] In the field of prefabricated buildings, the installation efficiency and accuracy of modular computer rooms are key, but existing installation methods often face difficulties in planning the installation sequence and inaccurate module docking, which affects the overall structural performance and safety. Although BIM technology has been used in building construction, solutions for real-time monitoring and precise docking still need to be improved.

[0003] BIM technology is an integrated working method and technology platform that uses digital models to represent the physical and functional characteristics of a building project. The BIM model not only contains the geometric information of the building, but also integrates a large amount of data related to the building life cycle.

[0004] By connecting the physical world with the digital world, IoT technology enables real-time collection, transmission, processing and analysis of massive amounts of data. The data comes from sensors, RFID tags, GPS positioning and other devices throughout the entire process of modular component installation, providing strong support for intelligent control, remote monitoring and data-driven decision-making.

[0005] Digital twins use the real-time perception of the Internet of Things to simulate the state of the physical world and construct twins through physical, geometric, behavioral, and rule information. They integrate multi-source data for continuous learning and updating, realize the visualization of the installation process of prefabricated computer rooms, and adjust the installation process through simulation and real-time monitoring, providing new ideas for the installation of modular components of prefabricated computer rooms. Summary of the invention

[0006] In view of the above existing problems, the present invention aims to improve installation efficiency and quality and reduce human errors.

[0007] In order to solve the above technical problems, a modular installation method of prefabricated computer room based on digital twin is proposed, including:

[0008] Collect static data and establish BIM models; simulate and optimize the component installation process; collect component positions and docking status in real time through the Internet of Things; establish a digital twin model of modular installation of prefabricated computer rooms; dynamically adjust the installation process of modular components.

[0009] As a preferred solution of the modular installation method of a prefabricated computer room based on digital twins described in the present invention, the static data includes: using RFID tags attached to modular components to store basic information of the components leaving the factory, including production batch PB a , actual material properties MPa , Design Specification Information DS a .

[0010] The interface information between modules includes connection method, clearance requirements, and installation sequence.

[0011] Use high-resolution cameras to capture multi-view images of components in real time.

[0012] Use 3D laser scanners to obtain the geometric dimensions and shapes of modular components, compare them with historical data, determine whether they meet the design requirements, whether there are quality problems, and calculate the actual geometric dimensions GD a Design Specifications DS a Deviation between:

[0013] ΔGD a =GD a -DS a

[0014] Conduct a quality assessment:

[0015] Q a =f(ΔGD a ,MP a ,PB a )

[0016] When |ΔGD a |≤∈ and MP a =MP d And PB a When compliant, Q a =1 means qualified. If any one of the conditions does not meet the requirements, then Q a =0 means unqualified, where MP d Design material properties, Q a is the quality assessment indicator, i is the variable index, and ∈ is the deviation threshold.

[0017] As a preferred solution of the modular installation method of an assembled computer room based on digital twins described in the present invention, wherein: the establishment of the BIM model includes modularizing the assembled computer room drawings through a clustering algorithm, and the similarity S between different modules is ij for:

[0018]

[0019] Among them, μ i and μ j is the eigenvalue of module i and module j, is the mean of all module eigenvalues.

[0020] Set the geometric characteristics GD of module i i is a high-dimensional vector: GDi =(len i ,wid i ,hei i ,sur i ,vol i ) Among them, len i is the length of module i, wid i is the width of module i, hei i is the height of module i, sur i is the surface area of ​​module i, vol i is the volume of module i.

[0021] The distance d between module i and module j considering the relative position and angle in space ij for:

[0022]

[0023] Among them, x i ,y i 、z i are the coordinates of module i in three-dimensional space, x j ,y j 、z j are the coordinates of module j in three-dimensional space, α ij The rotation angle difference between module i and module j.

[0024] Define the overall assembly error ΔE:

[0025]

[0026] Where I is the total number of modules, Δ i is the error of module i, q i is the configuration correlation matrix of module i, β1, β2, β3 are the weight coefficients of different error factors, λ i are thermodynamic variables related to the assembly process.

[0027] The mechanical model and static data of the module material are presented as follows:

[0028]

[0029] Among them, MP i is the material property of module i, η is the material strength coefficient, f mat (T i ,GD i ) is a material property function that depends on the temperature T i and GD a , g i is the material attenuation coefficient.

[0030] Build a BIM model of modular components and integrate static data:

[0031]

[0032] Among them, M BIM For the final constructed BIM model, γ1 and γ2 are adjustment coefficients, is the normalized similarity between module i and module j, θ is the environment parameter, μ j is the loss coefficient of module j.

[0033] As a preferred solution of the modular installation method of prefabricated computer room based on digital twin described in the present invention, the installation process includes collecting project data including component type, installation environment, and construction period requirements, generating feature reports by applying data analysis tools, identifying potential risks and constraints, listing the installation steps of each module component and defining key performance indicators for each step, breaking down each step into sub-steps, using a directed graph model to represent the dependencies between steps, and generating a topological sort to determine the execution order.

[0034] According to the execution order, the location, installation order and resource allocation of all components are input into Nivisworks to set resource limits and time constraints, increase the simulation of abnormal situations, perform global simulation, evaluate the time consumption and cost of each installation step, and select the best installation plan:

[0035]

[0036] Among them, δ t is the time cost coefficient, δ c is the direct cost coefficient, t k is the time consumption of step k, c k is the cost of step k, w k is the importance weight of step k, and K is the total number of steps.

[0037] Select O min For the best installation solution, simulate the optimal installation path according to the best installation solution:

[0038]

[0039] Select P min is the optimal installation path, where P is the total cost of the optimal installation path, d k is the distance consumption of step k.

[0040] As a preferred solution of the modular installation method of an assembled computer room based on digital twins described in the present invention, the collecting of component positions and docking states includes denoising, enhancing and perspective correcting the acquired multi-view images, extracting the features F of the components by using an image recognition algorithm, comparing the extracted features with the design drawings, and verifying whether the components are placed in the correct positions and angles:

[0041]

[0042] The identified component position and angle data are recorded in the database, where Bar is the centroid coordinate of feature F. is the position vector in three-dimensional space, Ω 3 For all points in three-dimensional space, It is a multivariable function that describes the characteristics of the component and depends on the spatial coordinate x; σ is the standard deviation of the Gaussian distribution.

[0043] Place sensors s at key connection points to form a state vector:

[0044]

[0045] Where D is the aggregate value of the sensor state, N is the total number of sensors, and s n is the state value of the nth sensor, is the state function, reflecting the actual state of the sensor. p is the sensitivity parameter for controlling the activation degree, ε n is the threshold value of each sensor.

[0046] Real-time monitoring of the comprehensive effectiveness of the docking status of modular components:

[0047]

[0048] When E≥0.7 and the contact pressure is 1MPa,5MPa(and the maximum allowable displacement is ≤0.2mm, it indicates that all docking has been successful.

[0049] When 0.4≤E<0.7 and the contact pressure belongs to (0.5MPa, 1MPa) or (5MPa, 6MPa) and the maximum allowable displacement belongs to (0.2mm, 1mm), it indicates that the docking is partially successful.

[0050] When E<0.4 and the maximum allowable displacement>1.0mm and the contact pressure satisfies the contact pressure<0.5MPa or the contact pressure>6.0MPa, it indicates that all docking has failed. Image recognition technology is used to re-identify the spatial position and angle of the components and perform secondary docking.

[0051] in, is the mean of all sensor states. All components with successfully docked states interact with each other in real time through the RFID reader / writer. The tag information vector R is defined. The integrated model C = (Bar, eff, R) is used. The Darwin evolutionary tree model is used to dynamically adjust the weights and feed back the results to the sensor in real time for updating:

[0052]

[0053] Among them, A final is the final decision model output, Λ is the number of features that affect the decision, and C m is the mth component of the comprehensive information vector, max(C) is the maximum value in vector C, ζ m To control the adjustment coefficient of the influence degree, eff m Expected effectiveness in different decision situations.

[0054] As a preferred solution of the modular installation method of an assembled computer room based on digital twin described in the present invention, the digital twin model includes a physical layer, a model layer, a data layer, an application layer and a connection layer.

[0055] When the docking is successful and all threshold requirements are met, the system triggers the establishment of the digital twin model, records the timestamp and status information of the successful docking, starts the construction of the digital twin model, and transmits the static and dynamic data of the physical layer to the data layer. The data layer cleans and analyzes data from different sources in real time, establishes a model layer that reflects the physical layer in real time based on the analysis results of the data layer, updates the information in the model layer, performs digital mapping, uses simulation tools to generate a three-dimensional model based on real-time data, and transmits it to the application layer synchronously. The application layer uses the real-time data provided by the model layer to dynamically simulate the installation process, perform optimization calculations on the plan, analyze the efficiency and cost of different installation plans, and realize the connection between the various levels through the connection layer.

[0056] As a preferred solution of the modular installation method of a prefabricated computer room based on digital twins described in the present invention, the dynamic adjustment includes modeling the displacement field of the component based on the twin model to monitor the installation position and structural stress:

[0057]

[0058] Where field(x) represents the displacement field at the spatial point x, Γ represents the area where data is collected, represents the shape function describing the local characteristics of the component in three-dimensional space, g x Represents the attenuation factor that controls the range of influence.

[0059] The installation simulation process is compared with the construction process in real time.

[0060]

[0061] Where ΔE represents the error at time t, Dis sim (t') represents the displacement field of the simulated data at time t', Dis act (t-t') represents the displacement field of the actual data at time t', and * represents the convolution operation, which indicates the interaction between the two functions.

[0062] Adjust the position and stress state of modular components in real time according to the comparison results:

[0063]

[0064] Where B represents the sum of the adjusted force parameters and displacement parameters, L is the number of components, Error function ρ l The gradient of Δω indicates the sensitivity of each component to error. l (u) The adjustment amount of component l at time uu.

[0065] Integrate the feedback optimization results into the control system and dynamically adjust according to the feedback results:

[0066]

[0067] Among them, W new (t) Displacement and force parameters after update at time t, W old B(t) is the parameter before updating at time t, B(t') is the adjustment factor at time t', g t A decay factor that controls the effect of history adjustments on the current state.

[0068] Another purpose of the present invention is to provide a modular installation system for prefabricated machine rooms based on digital twins. The present invention aims to achieve an efficient, accurate, and monitorable installation process through integrated innovative technical means, and solve the key issues of accuracy, efficiency, cost, risk, and quality control faced by prefabricated buildings during installation. The system ensures the quality of components, reduces installation risks and costs, improves installation efficiency and accuracy, realizes digital management of the installation process, and has the ability to adjust and optimize in real time, thereby promoting the digital transformation and intelligent upgrading of the construction industry.

[0069] As a preferred solution of the modular installation system of an assembled computer room based on digital twin described in the present invention, it is characterized by including a data acquisition and modeling module, a simulation optimization module, a real-time monitoring and feedback module, a digital twin model construction module and a dynamic adjustment module.

[0070] The data acquisition and modeling module uses RFID tags to store component information, high-resolution cameras to capture multi-view images, and three-dimensional laser scanners to obtain geometric dimensions, modularize the machine room drawings, define module feature vectors, calculate the distance between modules, and establish a digital BIM model.

[0071] The simulation optimization module analyzes project data, generates risk and constraint reports, builds a directed graph model, determines the execution order, sets resource limits and time constraints in Nivisworks, simulates the installation process, evaluates time consumption and cost, and selects the best solution.

[0072] The real-time monitoring and feedback module removes noise, enhances and corrects perspective of multi-view images, extracts features and compares them with design drawings, places sensors at key connection points, forms state vectors, monitors docking status, performs data interaction based on sensor data and RFID tag information, and dynamically adjusts sensor status.

[0073] The digital twin model construction module constructs a digital twin model, realizes the mapping and synchronization of the physical layer and the virtual layer, transmits the static and dynamic data of the physical layer to the data layer, establishes the model layer, generates a three-dimensional model of real-time data, and transmits it to the application layer.

[0074] The dynamic adjustment module models the displacement field, monitors the installation position and force, compares the error between the simulation process and the actual construction process, adjusts the component position and force state according to the error results, and feeds back the optimization results to the control system.

[0075] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of a modular installation method for an assembled computer room based on digital twins.

[0076] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a modular installation method of an assembled computer room based on digital twins are implemented.

[0077] The beneficial effects of the invention are as follows: the invention significantly shortens the construction period and improves the construction efficiency; significantly reduces the module docking error and improves the building quality and structural stability; real-time monitoring and adjustment mechanism reduces construction risks and optimizes resource allocation; applies BIM, Internet of Things, digital twins, image recognition and other intelligent technologies to optimize the installation sequence and docking accuracy, reduce errors, and improve the installation efficiency and quality of the prefabricated computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0079] Figure 1 An overall flow chart of a modular installation method for an assembled computer room based on digital twins is provided for one embodiment of the present invention.

[0080] Figure 2 A digital twin architecture diagram of a modular installation of an assembled computer room, which is a modular installation method of an assembled computer room based on digital twins, is provided as an embodiment of the present invention.

[0081] Figure 3 A system solution flow chart of a modular installation system for an assembled computer room based on digital twins is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0082] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0083] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0084] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0085] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0086] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0087] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0088] Example 1, reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and provides a modular installation method for an assembled computer room based on digital twins, comprising:

[0089] The present invention can monitor and control the modular installation of prefabricated computer rooms. The method is based on the concept of digital twins, combined with BIM technology, Internet of Things technology, etc., to collect static and dynamic data of the installation process of modular components of prefabricated computer rooms, integrate the data into the established BIM model, map the construction process in real time, and adjust and control the installation process based on the comparison between the existing simulation results and the construction process.

[0090] S1: Collect static data and build BIM model.

[0091] Furthermore, the RFID tags attached to the modular components are used to store the basic information of the components, including the production batch PB. a , actual material properties MP a , Design Specification Information DS a .

[0092] The interface information between modules includes connection method, clearance requirements, and installation sequence.

[0093] Use high-resolution cameras to capture multi-view images of components in real time.

[0094] Use 3D laser scanners to obtain the geometric dimensions and shapes of modular components, compare them with historical data, determine whether they meet the design requirements, whether there are quality problems, and calculate the actual geometric dimensions GD a Design Specifications DS a Deviation between:

[0095] ΔGD a =GD a -DS a

[0096] Conduct a quality assessment:

[0097] Qa=f(ΔGDa,MPa,PBa)

[0098] When |ΔGD a |≤∈ and MP a =MP d And PB a When compliant, Q a =1 means qualified. If any one of the conditions does not meet the requirements, then Q a =0 means unqualified, where MP d Design material properties, Q a is the quality assessment indicator, i is the variable index, and ∈ is the deviation threshold.

[0099] It should be noted that the prefabricated computer room drawings are modularized by clustering algorithm, and the similarity S between different modules is ij for:

[0100]

[0101] Among them, μ i and μ j is the eigenvalue of module i and module j, is the mean of all module eigenvalues.

[0102] Set the geometric characteristics GD of module i i is a high-dimensional vector: GD i =(len i ,wid i ,hei i ,sur i ,vol i ) Among them, len i is the length of module i, wid i is the width of module i, hei i is the height of module i, sur i is the surface area of ​​module i, vol i is the volume of module i.

[0103] The distance d between module i and module j considering the relative position and angle in space ij for:

[0104]

[0105] Among them, x i ,yi 、z i are the coordinates of module i in three-dimensional space, x j ,y j 、z j are the coordinates of module j in three-dimensional space, α ij The rotation angle difference between module i and module j.

[0106] Define the overall assembly error ΔE:

[0107]

[0108] Where I is the total number of modules, Δ i is the error of module i, q i is the configuration correlation matrix of module i, β1, β2, β3 are the weight coefficients of different error factors, λ i are thermodynamic variables related to the assembly process.

[0109] The mechanical model and static data of the module material are presented as follows:

[0110]

[0111] Among them, MP i is the material property of module i, η is the material strength coefficient, f mat (T i ,GD i ) is a material property function that depends on the temperature T i and GD a ; g i is the material attenuation coefficient.

[0112] Build a BIM model of modular components and integrate static data:

[0113]

[0114] Among them, M BIM For the final constructed BIM model, γ1 and γ2 are adjustment coefficients, is the normalized similarity between module i and module j, θ is the environment parameter, μ j is the loss coefficient of module j.

[0115] S2: Simulate and optimize the component installation process.

[0116] Furthermore, project data including component type, installation environment, and construction period requirements are collected, and feature reports are generated by applying data analysis tools to identify potential risks and constraints. The installation steps of each module component are listed and key performance indicators are defined for each step. Each step is broken down into sub-steps, and a directed graph model is used to represent the dependencies between steps. A topological sort is generated to determine the execution order.

[0117] According to the execution order, the location, installation order and resource allocation of all components are input into Nivisworks to set resource limits and time constraints, increase the simulation of abnormal situations, perform global simulation, evaluate the time consumption and cost of each installation step, and select the best installation plan:

[0118]

[0119] Among them, δ t is the time cost coefficient, δ c is the direct cost coefficient, t k is the time consumption of step k, c k is the cost of step k, w k is the importance weight of step k, and K is the total number of steps.

[0120] Select O min For the best installation solution, simulate the optimal installation path according to the best installation solution:

[0121]

[0122] Select P min is the optimal installation path, where P is the total cost of the optimal installation path, d k is the distance consumption of step k.

[0123] S3: Collect component location and docking status in real time through the Internet of Things.

[0124] Furthermore, multi-view images are acquired for denoising, enhancement and perspective correction, and the features F of the components are extracted using image recognition algorithms. The extracted features are compared with the design drawings to verify whether the components are placed in the correct position and angle:

[0125]

[0126] The identified component position and angle data are recorded in the database, where Bar is the centroid coordinate of feature F. is the position vector in three-dimensional space, Ω 3 For all points in three-dimensional space, It is a multivariable function that describes the characteristics of the component and depends on the spatial coordinate x; σ is the standard deviation of the Gaussian distribution.

[0127] Place sensors s at key connection points to form a state vector:

[0128]

[0129] Where D is the aggregate value of the sensor state, N is the total number of sensors, and s n is the state value of the nth sensor, is the state function, reflecting the actual state of the sensor. p is the sensitivity parameter for controlling the activation degree, ε n is the threshold value of each sensor.

[0130] Real-time monitoring of the comprehensive effectiveness of the docking status of modular components:

[0131]

[0132] When E ≥ 0.7 and the contact pressure is (1MPa, 5MPa) and the maximum allowable displacement is ≤ 0.2mm, it indicates that all docking has been successful.

[0133] When 0.4≤E<0.7 and the contact pressure belongs to (0.5MPa, 1MPa) or (5MPa, 6MPa) and the maximum allowable displacement belongs to (0.2mm, 1mm), it indicates that the docking is partially successful.

[0134] When E<0.4 and the maximum allowable displacement>1.0mm and the contact pressure satisfies the contact pressure<0.5MPa or the contact pressure>6.0MPa, it indicates that all docking has failed. Image recognition technology is used to re-identify the spatial position and angle of the components and perform secondary docking.

[0135] in, is the mean of all sensor states. All components with successfully docked states interact with each other in real time through the RFID reader / writer. The tag information vector R is defined. The integrated model C = (Bar, eff, R) is used. The Darwin evolutionary tree model is used to dynamically adjust the weights and feed back the results to the sensor in real time for updating:

[0136]

[0137] Among them, A final is the final decision model output, Λ is the number of features that affect the decision, and C m is the mth component of the comprehensive information vector, max(C) is the maximum value in vector C, ζ m To control the adjustment coefficient of the influence degree, eff m Expected effectiveness in different decision situations.

[0138] S4: Establish a digital twin model of the modular installation of the prefabricated computer room.

[0139] Furthermore, the digital twin model includes the physical layer, model layer, data layer, application layer and connection layer.

[0140] When the docking is successful and all threshold requirements are met, the system triggers the establishment of the digital twin model, records the timestamp and status information of the successful docking, starts the construction of the digital twin model, and transmits the static and dynamic data of the physical layer to the data layer. The data layer cleans and analyzes data from different sources in real time, establishes a model layer that reflects the physical layer in real time based on the analysis results of the data layer, updates the information in the model layer, performs digital mapping, uses simulation tools to generate a three-dimensional model based on real-time data, and transmits it to the application layer synchronously. The application layer uses the real-time data provided by the model layer to dynamically simulate the installation process, perform optimization calculations on the plan, analyze the efficiency and cost of different installation plans, and realize the connection between the various levels through the connection layer.

[0141] S5: Dynamically adjust the installation process of modular components.

[0142] Furthermore, the displacement field of the component is modeled based on the twin model to monitor the installation position and structural stress:

[0143]

[0144] Where field(x) represents the displacement field at the spatial point x, Γ represents the area where data is collected, represents the shape function describing the local characteristics of the component in three-dimensional space, g x Represents the attenuation factor that controls the range of influence.

[0145] The installation simulation process is compared with the construction process in real time.

[0146]

[0147] Where ΔE represents the error at time t, Dis sim (t') represents the displacement field of the simulated data at time t', Dis act (t-t') represents the displacement field of the actual data at time t', and * represents the convolution operation, which indicates the interaction between the two functions.

[0148] Adjust the position and stress state of modular components in real time according to the comparison results:

[0149]

[0150] Where B represents the sum of the adjusted force parameters and displacement parameters, L is the number of components, Error function ρ lThe gradient of Δω indicates the sensitivity of each component to error. l (u) The adjustment amount of component l at time uu.

[0151] Integrate the feedback optimization results into the control system and dynamically adjust according to the feedback results:

[0152]

[0153] Among them, W new (t) Displacement and force parameters after update at time t, W old B(t) is the parameter before updating at time t, B(t') is the adjustment factor at time t', g t A decay factor that controls the effect of history adjustments on the current state.

[0154] To sum up, the present invention points out a modular installation method of prefabricated computer room based on digital twin, which applies intelligent technologies such as BIM, Internet of Things, digital twin, image recognition, etc. to optimize the installation sequence and docking accuracy, reduce errors, and improve the installation efficiency and quality of the prefabricated computer room.

[0155] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0156] Embodiment 2, the third embodiment of the present invention, is different from the first two embodiments in that:

[0157] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Reid-Only Memory), random access memory (Rim, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0158] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0159] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RIM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0160] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGi), a field programmable gate array (FPGi), etc.

[0161] Example 3, reference Figure 3 , which is the fourth embodiment of the present invention, provides a modular installation system for prefabricated computer rooms based on digital twins, including a data acquisition and modeling module, a simulation optimization module, a real-time monitoring and feedback module, a digital twin model construction module and a dynamic adjustment module.

[0162] The data acquisition and modeling module uses RFID tags to store component information, high-resolution cameras to capture multi-view images, and 3D laser scanners to obtain geometric dimensions. It modularizes the machine room drawings, defines module feature vectors, calculates the distance between modules, and establishes a digital BIM model.

[0163] The simulation optimization module analyzes project data, generates risk and constraint reports, builds directed graph models, determines the execution order, sets resource limits and time constraints in Nivisworks, simulates the installation process, evaluates time consumption and cost, and selects the best solution.

[0164] The real-time monitoring and feedback module denoises, enhances and perspective corrects multi-view images, extracts features and compares them with design drawings, places sensors at key connection points, forms state vectors, monitors docking status, interacts with sensor data and RFID tag information, and dynamically adjusts sensor status.

[0165] The digital twin model construction module constructs the digital twin model, realizes the mapping and synchronization of the physical layer and the virtual layer, transmits the static and dynamic data of the physical layer to the data layer, establishes the model layer, generates a three-dimensional model of the real-time data, and transmits it to the application layer.

[0166] The dynamic adjustment module models the displacement field, monitors the installation position and force, compares the errors between the simulation process and the actual construction process, adjusts the component position and force state according to the error results, and feeds back the optimization results to the control system.

[0167] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A modular installation method for an assembled computer room based on digital twins, characterized in that: include, Collect static data and build BIM models; Simulate and optimize component installation process; Collect component locations and docking status in real time through the Internet of Things; Establish a digital twin model of modular installation of prefabricated computer rooms; Dynamically adjust the installation process of modular components.

2. A modular installation method for an assembled computer room based on digital twins according to claim 1, characterized in that: The static data includes storing basic information of the components shipped out of the factory using RFID tags attached to the modular components, including the production batch PB. a , actual material properties MP a , Design Specification Information DS a ; Interface information between modules includes connection method, clearance requirements, and installation sequence; Use high-resolution cameras to capture multi-view images of components in real time; Use 3D laser scanners to obtain the geometric dimensions and shapes of modular components, compare them with historical data, determine whether they meet the design requirements, whether there are quality problems, and calculate the actual geometric dimensions GD a Design Specifications DS a Deviation between: ΔGD a =GD a -DS a Conduct a quality assessment: Q a =f(ΔGD a ,MP a ,PB a ) When |ΔGD a |≤∈ and MP a =MP d And PB a When compliant, Q a =1 means qualified. If any one of the conditions does not meet the requirements, then Q a =0 means unqualified, where MP d Design material properties, Q a is the quality assessment indicator, i is the variable index, and ∈ is the deviation threshold.

3. A modular installation method for an assembled computer room based on digital twins as claimed in claim 2, characterized in that: The BIM model is established by dividing the drawings of the prefabricated machine room into modules through a clustering algorithm, and the similarity S between different modules is calculated. ij for: Among them, μ i and μ j is the eigenvalue of module i and module j, is the mean of all module feature values; Set the geometric characteristics GD of module i i is a high-dimensional vector: GD i =(len i ,wid i ,hei i ,sur i ,vol i Among them, len i is the length of module i, wid i is the width of module i, hei i is the height of module i, sur i is the surface area of ​​module i, vol i is the volume of module i; The distance d between module i and module j considering the relative position and angle in space ij for: Among them, x i ,y i 、z i are the coordinates of module i in three-dimensional space, x j ,y j 、z j are the coordinates of module j in three-dimensional space, α ij The rotation angle difference between module i and module j; Define the overall assembly error ΔE: Where I is the total number of modules, Δ i is the error of module i, q i is the configuration correlation matrix of module i, β1, β2, β3 are the weight coefficients of different error factors, λ i are thermodynamic variables related to the assembly process; The mechanical model and static data of the module material are presented as follows: Among them, MP i is the material property of module i, η is the material strength coefficient, f mat (T i ,GD i ) is a material property function that depends on the temperature T i and GD a ; g i is the material attenuation coefficient; Build a BIM model of modular components and integrate static data: Among them, M BIM For the final constructed BIM model, γ1 and γ2 are adjustment coefficients, is the normalized similarity between module i and module j, θ is the environment parameter, μ j is the loss coefficient of module j.

4. A modular installation method for an assembled computer room based on digital twins as claimed in claim 3, characterized in that: The installation process includes collecting project data including component type, installation environment, and construction period requirements, generating feature reports by applying data analysis tools, identifying potential risks and constraints, listing the installation steps of each module component and defining key performance indicators for each step, breaking down each step into sub-steps, using a directed graph model to represent dependencies between steps, and generating a topological sort to determine the execution order; According to the execution order, the location, installation order and resource allocation of all components are input into Nivisworks to set resource limits and time constraints, increase the simulation of abnormal situations, perform global simulation, evaluate the time consumption and cost of each installation step, and select the best installation plan: Among them, δ t is the time cost coefficient, δ c is the direct cost coefficient, t k is the time consumption of step k, c k is the cost of step k, w k is the importance weight of step k, K is the total number of steps; Select O min For the best installation solution, simulate the optimal installation path according to the best installation solution: Select P min is the optimal installation path, where P is the total cost of the optimal installation path, d k is the distance consumption of step k.

5. A modular installation method for an assembled computer room based on digital twins as claimed in claim 4, characterized in that: The collecting of the component position and docking status includes denoising, enhancing and perspective correction of the acquired multi-view images, extracting the features F of the components by using an image recognition algorithm, and comparing the extracted features with the design drawings to verify whether the components are placed at the correct position and angle: The identified component position and angle data are recorded in the database, where Bar is the centroid coordinate of feature F. is the position vector in three-dimensional space, Ω 3 For all points in three-dimensional space, is a multivariable function describing the component characteristics, which depends on the spatial coordinate x; σ is the standard deviation of the Gaussian distribution; Sensors are placed at key connection points to form a state vector: Where D is the aggregate value of the sensor state, N is the total number of sensors, and s n is the state value of the nth sensor, is the state function, reflecting the actual state of the sensor; p is the sensitivity parameter for controlling the activation degree, ε n is the threshold value of each sensor; Real-time monitoring of the comprehensive effectiveness of the docking status of modular components: When E ≥ 0.7 and the contact pressure is (1MPa, 5MPa) and the maximum allowable displacement is ≤ 0.2mm, it indicates that all docking has been successful; When 0.4≤E<0.7 and the contact pressure belongs to (0.5MPa, 1MPa) or (5MPa, 6MPa) and the maximum allowable displacement belongs to (0.2mm, 1mm), it indicates that the docking is partially successful; When E<0.4 and the maximum allowable displacement>1.0mm and the contact pressure meets the contact pressure<0.5MPa or the contact pressure>6.0MPa, it indicates that the docking has failed completely. The image recognition technology is used to re-identify the spatial position and angle of the components and perform secondary docking. in, is the mean of all sensor states. All components with successfully docked states interact with each other in real time through the RFID reader / writer. The tag information vector R is defined. The integrated model C = (Bar, eff, R) is used. The Darwin evolutionary tree model is used to dynamically adjust the weights and feed back the results to the sensor in real time for updating: Among them, A final is the final decision model output, Λ is the number of features that affect the decision, and C m is the mth component of the comprehensive information vector, max(C) is the maximum value in vector C, ζ m To control the adjustment coefficient of the influence degree, eff m Expected effectiveness in different decision situations.

6. A modular installation method for an assembled computer room based on digital twins as claimed in claim 5, characterized in that: The digital twin model includes a physical layer, a model layer, a data layer, an application layer and a connection layer; When the docking is successful and all threshold requirements are met, the system triggers the establishment of the digital twin model, records the timestamp and status information of the successful docking, starts the construction of the digital twin model, and transmits the static and dynamic data of the physical layer to the data layer. The data layer cleans and analyzes data from different sources in real time, establishes a model layer that reflects the physical layer in real time based on the analysis results of the data layer, updates the information in the model layer, performs digital mapping, uses simulation tools to generate a three-dimensional model based on real-time data, and transmits it to the application layer synchronously. The application layer uses the real-time data provided by the model layer to dynamically simulate the installation process, perform optimization calculations on the plan, analyze the efficiency and cost of different installation plans, and realize the connection between the various levels through the connection layer.

7. A modular installation method for an assembled computer room based on digital twins as claimed in claim 6, characterized in that: The dynamic adjustment includes modeling the displacement field of the component based on the twin model to monitor the installation position and structural stress: Where field(x) represents the displacement field at the spatial point x, Γ represents the area where data is collected, represents the shape function describing the local characteristics of the component in three-dimensional space, g x The attenuation factor that represents the range of control influence; Real-time comparison between the installation simulation process and the construction process; Where ΔE represents the error at time t, Dis sim (t') represents the displacement field of the simulated data at time t', Dis act (t-t') represents the displacement field of the actual data at time t', * represents the convolution operation, which indicates the interaction between the two functions; Adjust the position and stress state of modular components in real time according to the comparison results: Where B represents the sum of the adjusted force parameters and displacement parameters, L is the number of components, Error function ρ l The gradient of Δω indicates the sensitivity of each component to the error; l (u) The adjustment of component l at time uu; Integrate the feedback optimization results into the control system and dynamically adjust according to the feedback results: Among them, W new (t) Displacement and force parameters after update at time t, W old B(t) is the parameter before updating at time t, B(t') is the adjustment factor at time t', g t A decay factor that controls the effect of history adjustments on the current state.

8. A system using a modular installation method for an assembled computer room based on digital twins as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition and modeling module, simulation optimization module, real-time monitoring and feedback module, digital twin model construction module and dynamic adjustment module; The data acquisition and modeling module uses RFID tags to store component information, high-resolution cameras to capture multi-view images, and 3D laser scanners to obtain geometric dimensions, modularize the room drawings, define module feature vectors, calculate the distance between modules, and establish a digital BIM model; The simulation optimization module analyzes project data, generates risk and constraint reports, builds a directed graph model, determines the execution order, sets resource limits and time constraints in Nivisworks, simulates the installation process, evaluates time consumption and cost, and selects the best solution; The real-time monitoring and feedback module removes noise, enhances and corrects perspective of multi-view images, extracts features and compares them with design drawings, places sensors at key connection points, forms state vectors, monitors docking status, performs data interaction based on sensor data and RFID tag information, and dynamically adjusts sensor status; The digital twin model construction module constructs the digital twin model, realizes the mapping and synchronization between the physical layer and the virtual layer, transmits the static and dynamic data of the physical layer to the data layer, establishes the model layer, generates a three-dimensional model of the real-time data, and transmits it to the application layer; The dynamic adjustment module models the displacement field, monitors the installation position and force, compares the error between the simulation process and the actual construction process, adjusts the component position and force state according to the error results, and feeds back the optimization results to the control system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a modular installation method of an assembled computer room based on digital twins as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a modular installation method of an assembled computer room based on digital twins as described in any one of claims 1 to 7 are implemented.

Images