Precision control method and installation method of inverted frustum structure installation

Abstract

The present invention provides a precision control method and installation method for the installation of an inverted frustum structure, which belongs to the field of structural construction technology. A design model is created based on BIM technology, and a corresponding relationship is established between the design model and the construction data and management data, and then the model is stored in a preset collaborative management platform to obtain a digital model that records the entire construction process and management data for guiding construction; an error prediction model is used to predict the error of the current construction process according to the acquired real-time installation process data, so as to timely and accurately predict the possibility of error or deviation in the current construction process, and error problems in the construction process can be discovered in time. If there is a possibility of error, an error optimization solution is obtained to modify the parameters of the current construction process of the digital model to optimize the digital model, and then the optimized digital model is used to continue to guide the progress of construction, so as to achieve the effect of timely controlling the precision of the current construction process; and since the error is predicted in advance, there is no need for large-scale rework.

Description

Technical Field

[0001] The present invention relates to the technical field of structural construction, and more specifically, to a precision control method and an installation method for an inverted frustum structure. Background Art

[0002] During the aerial assembly of independent inverted frustum structures, errors in each step accumulate over time, ultimately determining the quality of the aerial installation. Therefore, precise construction data measurements are necessary at certain stages of construction to ensure that the installation proceeds as planned.

[0003] Conventional measurement methods are commonly used to measure the installation of inverted frustum structures. These methods primarily rely on manual measurement and calculation, and then control installation accuracy based on the measurement results. Because this method relies on manual operation, it is prone to errors and inefficient. Currently, there are also methods that use laser scanning devices to measure and adjust installation accuracy, but these are expensive and complex to operate, making them unsuitable for large-scale application. However, regardless of which method is used, measurements are taken after the construction process has been completed. If a significant error is discovered, rework and readjustment of the construction data are necessary, making real-time accuracy monitoring impossible.

[0004] In summary, the existing installation accuracy control method of the inverted frustum structure cannot provide real-time feedback on errors during the installation process, which can easily lead to the accumulation of installation errors and affect the final installation quality. In addition, after the errors are discovered, a large amount of rework is required, affecting the construction progress. Summary of the Invention

[0005] In view of the above problems, the purpose of the present invention is to provide an installation precision control method and installation method for an inverted frustum structure, so as to solve the problems in the prior art of the installation precision control method for an inverted frustum structure, such as the inability to provide real-time feedback on errors during the installation process, which easily leads to the accumulation of installation errors and affects the final installation quality; and the need for a large amount of rework after errors are discovered, which affects the construction progress.

[0006] The present invention provides a method for precision control of the installation of an inverted frustum structure, comprising the following steps:

[0007] Based on the design data of the inverted frustum structure, the design model of the inverted frustum structure is created using BIM technology;

[0008] A correspondence is established between the design model and the construction data and management data, and the data is imported into a preset collaborative management platform to obtain a digital model of the inverted frustum structure; wherein the preset collaborative management platform is provided with a real-time data interface, an error prediction model connected to the real-time data interface, and an error optimization solution library storing error optimization solutions; the construction data includes installation procedures and installation process data corresponding to the installation procedures;

[0009] guiding the installation and construction of the inverted frustum structure based on the digital model, and obtaining real-time installation process data of the current installation process in real time through the real-time data interface;

[0010] Inputting the real-time installation process data into the error prediction model, and performing error prediction on the current installation process using the error prediction model;

[0011] When the result of the error prediction for the current installation process shows that there is a prediction error, obtaining an error optimization solution that matches the prediction error value of the current installation process from the error optimization solution library;

[0012] According to the error optimization scheme, the installation process data of the current installation process is optimized on the digital model to control the accuracy of the current installation process until the installation of the inverted frustum structure is completed.

[0013] The present invention provides an inverted frustum structure installation method, which is characterized in that during the installation of the inverted frustum structure, the accuracy of the inverted frustum structure is controlled by using the accuracy control method as described above.

[0014] As can be seen from the above technical solutions, the present invention provides a precision control method and installation method for the installation of an inverted frustum structure. By creating a design model based on BIM technology, establishing a correspondence between the design model and construction data and management data, and then storing it on a preset collaborative management platform, a digital model that records the entire construction process and management data is obtained to guide construction. The real-time installation process data of the current construction process is obtained in real time through a real-time data interface on the preset collaborative management platform. The error prediction model then predicts the error of the current construction process based on the real-time installation process data, and timely and accurately predicts the possibility of error or deviation in the current construction process. Once the possibility of error is found, the preset error optimization solution is obtained to modify the parameters of the current construction process on the digital model to optimize the digital model. The optimized digital model is then used to continue to guide the construction process, achieving the effect of timely controlling the accuracy of the current construction process. Moreover, since the error is predicted in advance, there is no need for large-scale rework. Compared with existing precision control methods, the present invention combines BIM technology with machine learning algorithms to achieve precise installation of independent inverted frustum structure aerial joints, which not only improves the accuracy and efficiency of installation, but also reduces the cost of error measurement, which is conducive to large-scale application.

[0015] In order to achieve the above and related purposes, one or more aspects of the present invention include the features that will be described in detail later. The following description and the accompanying drawings describe some exemplary aspects of the present invention in detail. However, these aspects indicate only some of the various ways in which the principles of the present invention can be used. In addition, the present invention is intended to include all of these aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By referring to the following description in conjunction with the accompanying drawings, and with a more complete understanding of the present invention, other objects and results of the present invention will become more clear and easy to understand. In the accompanying drawings:

[0017] Figure 1 The figure is a flow chart of a method for precision control of an inverted frustum structure installation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. However, it will be apparent that these embodiments may be practiced without these specific details.

[0019] In view of the problems of the installation precision control method of the inverted frustum structure in the above-mentioned existing technology, which cannot provide real-time feedback on errors during the installation process, and the accumulation of installation errors is easy to occur due to untimely feedback, affecting the final installation quality; and rework is required after errors are discovered, affecting the construction progress. A precision control method and installation method for the installation of an inverted frustum structure are proposed.

[0020] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] In order to illustrate the precision control method and installation method of the inverted frustum structure provided by the present invention, Figure 1 The flowchart of the precision control method for installing an inverted frustum structure according to an embodiment of the present invention is shown.

[0022] like Figure 1 As shown, the precision control method for installing an inverted frustum structure provided by the present invention includes the following steps:

[0023] Step S1: Create a design model of the inverted frustum structure using BIM technology based on the design data of the inverted frustum structure.

[0024] Specifically, a design model of the inverted frustum structure can be created using a tool such as Revit software based on the design data of the inverted frustum structure, wherein the design data includes but is not limited to size, shape, and material.

[0025] As a preferred solution of the present invention, a design model of the inverted frustum structure is created using BIM technology based on the design data of the inverted frustum structure, including:

[0026] Determining the size, shape, and material of each component of the inverted frustum structure based on the design data of the inverted frustum structure; wherein the design data includes the names of the components of each part of the inverted frustum structure and the sizes, shapes, and materials corresponding to the component names;

[0027] Based on the size, shape and material of each component of the inverted frustum structure, the BIM technology is used to create the component models of the inverted frustum structure respectively;

[0028] The component models of the inverted frustum structure are assembled to obtain a design model of the inverted frustum structure; wherein the name, size and material of each component are marked on the design model.

[0029] Specifically, the component models of the inverted frustum structure are constructed separately through tools such as Revit software, and the component models are assembled and spliced ​​to obtain the design model of the frustum structure.

[0030] Step S2: Establish a correspondence between the design model and the construction data and management data, and import them into a preset collaborative management platform to obtain a digital model of the inverted cone structure; wherein the preset collaborative management platform creates a real-time data interface, an error prediction model connected to the real-time data interface, and an error optimization solution library storing error optimization solutions; the construction data includes installation procedures and installation process data corresponding to the installation procedures.

[0031] Specifically, the design model is mapped to construction and management data, and then imported into a pre-defined collaborative management platform, such as ProjectWise. This completes the digital modeling of the inverted frustum structure, resulting in a digital model. This digital model guides subsequent construction and provides data support for precision control during installation.

[0032] The construction data includes the installation process and the installation process data corresponding to the installation process. The installation process data includes but is not limited to the following:

[0033] Installation progress data: Record the installation start time, estimated completion time, actual completion time, etc. of each part. For example, the installation of steel structure A starts on May 1, 2024, is expected to be completed on May 10, and is actually completed on May 8.

[0034] Installation condition data: This includes construction site environmental conditions such as wind speed, temperature, and humidity. These data have a significant impact on installation accuracy and safety. For example, during one installation, the wind speed was a force 3 northeast wind, the temperature was 25°C, and the humidity was 60%.

[0035] Measurement data: Precise measurements of spatial position, angles, dimensions, and other parameters collected in real time during the installation process. For example, the actual position of steel structure B after installation is essentially consistent with the theoretical position.

[0036] Installation step record data: Detailed records of each installation step, including the methods, tools, personnel, etc. For example, the bottom support structure is installed first, and then the main structure is lifted by a crane, and then precisely aligned and fixed.

[0037] Error record data: The error values ​​measured after each installation, such as horizontality and verticality deviation, etc. For example, after installing steel structure C, the verticality deviation was measured to be ±2mm, which is within the allowable range.

[0038] During the construction process, real-time construction data (such as installation conditions, measurement data, and error records) is input into the error prediction model to predict errors and deviations during the installation process and optimize the installation plan based on the predicted results. The real-time data interface receives real-time construction data from actual construction and interacts with the error prediction model. It can then be used to display installation progress, predicted errors, and recommended adjustment plans to guide on-site personnel to adjust installation strategies in a timely manner.

[0039] Management data mainly involves various information in the project management and coordination process, including but not limited to the following:

[0040] Project planning data: Overall installation and construction schedule, milestones, critical paths, etc. For example, the entire installation and construction plan is to be completed within 6 months and is divided into four phases: design, procurement, prefabrication, and installation. Each phase has a specific start and end time.

[0041] Resource allocation data: The allocation of human resources, material resources, and equipment resources. For example, the installation phase requires 50 workers, including 10 senior welders and 40 general workers; 5 cranes and 20 sets of welding equipment are required.

[0042] Quality control record data: records of regular inspections and assessments of installation quality, including inspection time, inspectors, inspection results, etc. For example, a weekly quality inspection revealed minor scratches on the surface of a steel structure, and on-site repairs were requested.

[0043] Safety management records: Safety management status at the construction site, including safety accidents, safety hazards, and safety training. For example, two safety training sessions were conducted this month, and a safety hazard of exposed electrical wiring was discovered and rectified.

[0044] Communication and coordination records: Records of the process and results of communication and coordination with the design company, supervision company, suppliers, etc. For example, after communicating with the design company, it was decided to optimize the design of steel structure C to reduce installation difficulty.

[0045] When constructing the digital model of the inverted frustum structure, management data such as project plans and resource allocation can be integrated into the ProjectWise platform to enable full lifecycle information management and collaborative design. Management data plays a management and coordination role during the installation and construction process and can be used throughout the entire installation process. For example, by reviewing project plan data and resource allocation data, timely adjustments to the installation schedule and resource allocation can be made. By reviewing quality control and safety management records, compliance with regulations and safety requirements can be ensured during the installation process.

[0046] As a preferred solution of the present invention, a correspondence is established between the design model, construction data, and management data, and the data is imported into a preset collaborative management platform to obtain a digital model of the inverted frustum structure, including:

[0047] On the design model, the corresponding installation processes are divided according to the construction data, and the installation process data and the corresponding management data based on the design model are recorded corresponding to the installation process, so that the design model records the construction data and management data;

[0048] The design model that records the construction data and management data is imported into the preset collaborative management platform to obtain a digital model of the inverted frustum structure.

[0049] Specifically, the design model can reflect the installation process and the installation process data corresponding to the installation process, as well as record the corresponding management data, so that the digital model can realize information management and collaborative design of the entire life cycle of installation construction, and provide guidance for actual construction.

[0050] As a preferred embodiment of the present invention, the training method of the error prediction model includes:

[0051] Collecting historical data of the inverted frustum structure installation; wherein the historical data includes historical installation process data corresponding to different installation procedures and historical error result data corresponding to the historical installation process data based on the same installation procedure;

[0052] Extracting feature data related to the prediction error from the historical installation process data, thereby obtaining a training data set including the feature data and historical error result data corresponding to the feature data;

[0053] Divide the training dataset into training set, validation set and test set;

[0054] Taking the feature data in the training set as input and the historical error result data corresponding to the feature data as output, the preset basic model is trained for error prediction to obtain a primary prediction model;

[0055] Taking the feature data in the validation set as input and the historical error result data corresponding to the feature data as output, the parameters of the primary prediction model are adjusted to obtain the validation prediction model;

[0056] Based on the same installation process, the feature data in the test set is input into the verification prediction model, and the error prediction accuracy of the verification prediction model is calculated based on the historical error result data output by the verification prediction model and the historical error result data corresponding to the feature data in the test set;

[0057] When the error prediction accuracy is greater than or equal to the preset accuracy threshold, the verification prediction model is used as the error prediction model.

[0058] Specifically, through machine learning algorithms, historical data on the installation of inverted frustum structures is trained and learned to identify the patterns and characteristics of the installation process of the aerial converging joints of the inverted frustum structures, and then predict possible errors and deviations. During the construction process, these prediction results are used to optimize and adjust the installation plan to ensure the smooth progress of the construction process. For example, a machine learning algorithm is written using the TensorFlow framework through Python (online programming). The main function of this algorithm is to identify the patterns and characteristics of the installation process of the aerial converging joints of the inverted frustum structures through training and learning of historical data, and then predict possible errors and deviations. In actual applications, a large amount of historical data is first input into the algorithm to allow the algorithm to learn and train. Then, real-time construction data is input into the algorithm, and the algorithm will output the predicted results. Based on these results, the installation plan can be optimized and adjusted.

[0059] One of the preferred solutions is to use TensorFlow's high-level API (such as Keras) to simplify the model building and training process.

[0060] Collect data: Collect historical data on the installation of the inverted frustum structure, including installation conditions (such as wind speed, temperature, humidity, installer experience, etc.), installation steps, measurement data during the installation process (such as angles, positions, dimensions, etc.), and final error and deviation records.

[0061] Feature extraction: Extracting features from historical data that are useful for predicting errors and deviations. These features may include physical parameters of the installation environment, specific steps and parameters of the installation process, etc.

[0062] Data partitioning: Divide the data into training, validation, and test sets. Typically, you can use 70% of the data as a training set, 15% as a validation set, and the remaining 15% as a test set.

[0063] Data standardization / normalization: Standardize or normalize features to speed up the training process and improve model performance.

[0064] Select the model type: Since this is a regression problem (predicting the error and bias of a numerical value), you can choose models such as linear regression, decision tree regression, random forest regression, or neural networks (such as fully connected neural networks or convolutional neural networks if the features are suitable). Considering the complexity, neural networks are preferred.

[0065] For example, using TensorFlow / Keras to build a neural network model (the basic model), you can use several fully connected layers (Dense layers) to build a simple neural network model. The basic model is trained, verified, and tested using the above data. Finally, when the error prediction accuracy is greater than or equal to the preset accuracy threshold, the verification prediction model is used as the error prediction model.

[0066] As a preferred solution of the present invention, collecting historical data of the inverted frustum structure installation includes:

[0067] Collect primary historical data of inverted frustum structure installation;

[0068] The primary historical data is cleaned to remove data that does not meet the preset standards and obtain historical data.

[0069] Specifically, since the collected primary historical data may contain defective data, such as missing values, abnormal values, and inconsistent data, the primary historical data needs to be cleaned to obtain usable historical data.

[0070] Step S3: guiding the installation and construction of the inverted frustum structure based on the digital model, and obtaining real-time installation process data of the current installation process in real time through a real-time data interface.

[0071] Specifically, the digital model is used to guide the installation and construction of the inverted cone structure. During the actual construction process, the real-time installation process data of the current installation process is obtained in real time through the real-time data interface.

[0072] As a preferred solution of the present invention, the installation and construction of the inverted frustum structure is guided by a digital model, and the real-time installation process data of the current installation process is obtained in real time through a real-time data interface, including:

[0073] Determine the current installation process based on the digital model;

[0074] Through the real-time data interface, real-time installation process data is obtained from the data measurement parts installed in the actual construction corresponding to the current installation process.

[0075] Specifically, in actual construction, measuring parts are set on the components, for example, to measure the installation conditions (wind speed, temperature, etc.) and the construction installation structure (such as position, angle, size, etc.). According to the digital model, the current installation process is determined, and then the real-time installation process data is obtained from the above-mentioned data measuring parts in real time through the real-time data interface.

[0076] Step S4: input the real-time installation process data into the error prediction model, and perform error prediction on the current installation process through the error prediction model.

[0077] Specifically, the real-time installation process data is input into the error prediction model, and the error prediction model performs error analysis on the real-time installation process data to obtain an error prediction result.

[0078] As a preferred embodiment of the present invention, after inputting the real-time installation process data into the error prediction model and performing error prediction on the current installation process using the error prediction model, the present invention further includes:

[0079] When the result of the error prediction for the current installation process is that there is no prediction error, the current installation process is continued according to the digital model.

[0080] Specifically, when the result of error prediction for the current installation process is that there is no prediction error, it means that the process is carried out according to plan and there is no error or deviation risk. The current installation process can be continued according to the digital model.

[0081] Step S5: When the result of the error prediction for the current installation process shows that there is a prediction error, an error optimization solution that matches the prediction error value of the current installation process is obtained from the error optimization solution library.

[0082] Specifically, if the error prediction results for the current installation process indicate a prediction error, it indicates a risk of error or deviation in the current construction process. Therefore, the digital model needs to be optimized to prevent subsequent error accumulation. Based on these prediction results, on-site construction personnel can adjust and optimize the specific construction sections where problems have occurred. This can be done by adjusting installation parameters, changing installation procedures, or taking other corrective measures to ensure smooth subsequent construction and ultimately high installation quality. These adjustments are typically local and targeted, designed to quickly respond to prediction results, reduce error accumulation, and improve installation accuracy and efficiency.

[0083] As a preferred solution of the present invention, when the result of error prediction for the current installation process shows that there is a prediction error, an error optimization solution matching the prediction error value of the current installation process is obtained from the error optimization solution library, including:

[0084] When the result of the error prediction for the current installation process shows that there is a prediction error, the prediction error value is compared with the preset error threshold based on the current process;

[0085] When the prediction error value is less than or equal to the preset error threshold, an automatic optimization adjustment plan is obtained from the error optimization plan library; when the prediction error value is greater than the preset error threshold, an auxiliary selection adjustment plan is obtained from the error optimization plan library;

[0086] Among them, the automatic optimization and adjustment scheme is to automatically modify the installation process data of the current installation process of the digital model into real-time installation process data;

[0087] Assisted selection of adjustment plans is to generate a forecast report and recommended adjustment plans based on the forecast error value, and display them on the display page of the preset collaborative management platform;

[0088] According to the selection result of the recommended adjustment plan, the installation process data of the current installation process of the digital model is modified.

[0089] Specifically, when the error prediction model predicts an error or deviation, the predicted error value is compared with a preset error threshold. The preset error threshold or rules are used to determine the severity and urgency of the prediction result. If the predicted error value is small and falls within the automatically adjustable range—that is, when the predicted error value is less than or equal to the preset error threshold—the model parameters are directly modified according to the built-in algorithm or rules to correct the predicted error. For example, if a deviation in the predicted position of a component is detected, the position parameters of that component in the digital model may be automatically adjusted. For more complex errors or deviations, direct automatic adjustment may not be possible, but information can be provided to assist in decision-making. Specifically, when the predicted error value exceeds the preset error threshold, an error optimization solution library is retrieved to assist in selecting an adjustment solution. Based on this selected adjustment solution, a prediction report is generated, the error is visualized, and an adjustment solution is recommended. This information can also be clearly presented to the user through the user interface (UI), helping them quickly understand the problem and make appropriate adjustment decisions. Based on the prediction results and the user's adjustment decisions, new construction instructions can be generated or existing construction plans can be updated. These construction guidance documents will include revised installation steps, precautions, new model parameters and other information to ensure that the subsequent installation process can be carried out according to the revised plan.

[0090] Step S6: Optimize the installation process data of the current installation process on the digital model according to the error optimization solution to control the accuracy of the current installation process until the installation of the inverted frustum structure is completed.

[0091] Specifically, according to the error optimization plan, the installation process data of the current installation process is optimized on the digital model, and then the optimized digital model is used as a construction guide until the installation of the inverted frustum structure is completed.

[0092] As a preferred embodiment of the present invention, after optimizing the installation process data of the current installation process on the digital model according to the error optimization scheme to control the accuracy of the current installation process until the installation of the inverted frustum structure is completed, the method further includes:

[0093] The optimized data of the installation process data of the installation process and the error data corresponding to the optimized data are used as the performance optimization data of the error prediction model.

[0094] Specifically, the new real-time data and the adjusted results—the optimized installation process data and the error data corresponding to that optimized data—can be used to further train and optimize the error prediction model to improve its prediction accuracy and generalization capabilities. This allows the error prediction model to continuously learn and improve its performance as construction progresses and data accumulates, providing more reliable support for precise control of the installation process.

[0095] The inverted frustum structure installation method provided by the present invention uses the precision control method provided by the present invention to control the precision of the inverted frustum structure during the installation process of the inverted frustum structure.

[0096] The above embodiments show that the precision control method and cantilever assembly method for the installation of an inverted frustum structure provided by the present invention creates a design model based on BIM technology, establishes a correspondence between the design model and construction data and management data, and then stores the data in a preset collaborative management platform to obtain a digital model that records the entire construction process and management data for guiding construction; obtains real-time installation process data of the current construction process in real time through a real-time data interface on the preset collaborative management platform, and then uses an error prediction model to predict the error of the current construction process based on the real-time installation process data, so as to timely and accurately predict the possibility of error or deviation in the current construction process, thereby enabling timely detection of error problems in the construction process; once the possibility of error is found, the parameters of the current construction process on the digital model are modified by obtaining a preset error optimization solution to optimize the digital model, and then the optimized digital model is used to continue to guide the construction process, thereby achieving the effect of timely controlling the accuracy of the current construction process; and because the error is predicted in advance, there is no need for large-scale rework. Compared with existing precision control methods, the present invention combines BIM technology with machine learning algorithms to achieve precise installation of independent inverted frustum structure aerial joints, which not only improves the accuracy and efficiency of installation, but also reduces the cost of error measurement, which is conducive to large-scale application.

[0097] The above description uses the accompanying drawings as an example to describe the precision control method for installing an inverted frustum structure and the cantilevered assembly method according to the present invention. However, those skilled in the art will appreciate that various modifications may be made to the precision control method for installing an inverted frustum structure and the cantilevered assembly method described above without departing from the scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A precision control method for installing an inverted frustum structure, characterized in that: The steps include: Based on the design data of the inverted frustum structure, the design model of the inverted frustum structure is created using BIM technology; A correspondence is established between the design model and the construction data and management data, and the data is imported into a preset collaborative management platform to obtain a digital model of the inverted frustum structure; wherein the preset collaborative management platform is provided with a real-time data interface, an error prediction model connected to the real-time data interface, and an error optimization solution library storing error optimization solutions; the construction data includes installation procedures and installation process data corresponding to the installation procedures; guiding the installation and construction of the inverted frustum structure based on the digital model, and obtaining real-time installation process data of the current installation process in real time through the real-time data interface; Inputting the real-time installation process data into the error prediction model, and performing error prediction on the current installation process using the error prediction model; When the result of the error prediction for the current installation process shows that there is a prediction error, obtaining an error optimization solution that matches the prediction error value of the current installation process from the error optimization solution library; According to the error optimization scheme, the installation process data of the current installation process is optimized on the digital model to control the accuracy of the current installation process until the installation of the inverted frustum structure is completed.

2. The method for controlling the installation precision of an inverted frustum structure according to claim 1, characterized in that: The method of creating a design model of the inverted frustum structure using BIM technology based on the design data of the inverted frustum structure includes: Determining the size, shape, and material of each component of the inverted frustum structure according to the design data of the inverted frustum structure; wherein the design data includes the names of the components of each part of the inverted frustum structure and the sizes, shapes, and materials corresponding to the component names; Based on the size, shape and material of each component of the inverted frustum structure, using BIM technology, create a model of each component of the inverted frustum structure; The component models of the inverted frustum structure are assembled to obtain a design model of the inverted frustum structure; wherein the name, size and material of each component are marked on the design model.

3. The precision control method for installing an inverted frustum structure according to claim 1, characterized in that: The design model is established in correspondence with the construction data and the management data, and is imported into a preset collaborative management platform to obtain a digital model of the inverted frustum structure, including: On the design model, corresponding installation processes are divided according to the construction data, and installation process data corresponding to the installation processes and corresponding management data based on the design model are recorded, so that the design model has construction data and management data recorded; The design model that records the construction data and management data is imported into the preset collaborative management platform to obtain a digital model of the inverted frustum structure.

4. The method for controlling the installation precision of an inverted frustum structure according to claim 1, wherein: The training method of the error prediction model includes: Collecting historical data of the installation of the inverted frustum structure; wherein the historical data includes historical installation process data corresponding to different installation procedures and historical error result data corresponding to the historical installation process data based on the same installation procedure; Extracting feature data related to the prediction error from the historical installation process data, thereby obtaining a training data set including the feature data and historical error result data corresponding to the feature data; Dividing the training data set into a training set, a validation set, and a test set; Using the feature data in the training set as input and the historical error result data corresponding to the feature data as output, performing error prediction training on the preset basic model to obtain a prediction primary model; Taking the feature data in the validation set as input and the historical error result data corresponding to the feature data as output, adjusting the parameters of the primary prediction model to obtain a validation prediction model; Based on the same installation process, the feature data in the test set is input into the verification prediction model, and the error prediction accuracy of the verification prediction model is calculated based on the historical error result data output by the verification prediction model and the historical error result data in the test set corresponding to the feature data; When the error prediction accuracy is greater than or equal to a preset accuracy threshold, the verification prediction model is used as the error prediction model.

5. The method for controlling the installation precision of an inverted frustum structure according to claim 4, characterized in that: The historical data collected for the installation of the inverted frustum structure includes: Collect primary historical data of inverted frustum structure installation; The primary historical data is cleaned to remove data that does not meet preset standards in the primary historical data to obtain historical data.

6. The method for controlling the installation precision of an inverted frustum structure according to claim 1, characterized in that: The method of guiding the installation construction of the inverted frustum structure based on the digital model and obtaining real-time installation process data of the current installation process in real time through the real-time data interface includes: determining a current installation process according to the digital model; Through the real-time data interface, real-time installation process data is obtained from the data measurement components installed in the actual construction corresponding to the current installation process.

7. The method for controlling the installation precision of an inverted frustum structure according to claim 1, characterized in that: After inputting the real-time installation process data into the error prediction model and performing error prediction on the current installation process using the error prediction model, the method further includes: When the result of error prediction for the current installation process is that there is no prediction error, the current installation process is continued according to the digital model.

8. The method for controlling the installation precision of an inverted frustum structure according to claim 1, characterized in that: When the result of performing error prediction on the current installation process indicates that a prediction error exists, obtaining an error optimization solution that matches the prediction error value of the current installation process from the error optimization solution library includes: When the result of the error prediction for the current installation process is that a prediction error exists, comparing the prediction error value with a preset error threshold based on the current process; When the prediction error value is less than or equal to the preset error threshold, an automatic optimization adjustment solution is obtained from the error optimization solution library; when the prediction error value is greater than the preset error threshold, an auxiliary selection adjustment solution is obtained from the error optimization solution library; The automatic optimization and adjustment scheme is to automatically modify the installation process data of the current installation process of the digital model into real-time installation process data; The auxiliary selection of the adjustment plan is to generate a forecast report and a recommended adjustment plan according to the forecast error value, and display them on a display page of the preset collaborative management platform; According to the selection result of the recommended adjustment solution, the installation process data of the current installation process of the digital model is modified.

9. The method for controlling the installation precision of an inverted frustum structure according to claim 1, characterized in that: After optimizing the installation process data of the current installation process on the digital model according to the error optimization scheme to control the accuracy of the current installation process until the installation of the inverted frustum structure is completed, the method further includes: The optimized data of the installation process data of the installation process and the error data corresponding to the optimized data are used as the performance optimization data of the error prediction model.

10. A method for installing an inverted frustum structure, characterized in that: During the installation of the inverted frustum structure, the accuracy of the inverted frustum structure is controlled by using the accuracy control method according to any one of claims 1 to 9.

Images