Intelligent quality detection method used in hyperbolic curtain wall parametric modeling design process

Abstract

The invention provides an intelligent quality detection method used in a hyperbolic curtain wall parameterized modeling design process, and the method comprises the steps: obtaining modeling parameter data corresponding to a hyperbolic curtain wall model when the hyperbolic curtain wall model is modeled in a preset modeling environment, and carrying out the preprocessing of the modeling parameter data; the preprocessing at least comprises data cleaning, formatting and standardization; historical error data corresponding to the hyperbolic curtain wall model and preset expert knowledge are obtained to construct an error pattern library; the error pattern library comprises error characteristics, and the error characteristics at least comprise structure errors, size errors, material matching errors and node closing-in errors; in the modeling process of the hyperbolic curtain wall model, the modeling process is monitored in real time according to the error pattern library; if it is determined that at least one error feature exists in the modeling process according to the error pattern library, error warning information is generated, an error positioning visualization report is generated, and intelligent quality detection in the hyperbolic curtain wall parametric modeling design process is completed.

Description

Technical Field

[0001] The present application relates to the technical field of architectural modeling, and in particular to an intelligent quality detection method for use in a parametric modeling design process of a hyperbolic curtain wall. Background Art

[0002] With the continuous innovation of architectural design, hyperbolic curtain wall, as a building facade material with high visual impact and unique shape, is increasingly widely used in modern buildings. Compared with traditional flat curtain wall, hyperbolic curtain wall has higher structural complexity, more irregular component shape, greater design difficulty and higher process requirements.

[0003] In the process of curtain wall modeling, faced with complex hyperbolic models, modelers may not have a thorough understanding of curtain wall design. When dealing with details such as curtain wall nodes and seams, they may ignore some key factors, which will affect the overall effect of the curtain wall. Especially newcomers, due to lack of experience, they often make some common modeling errors, which may affect the design quality of the curtain wall and increase costs.

[0004] Therefore, a method is urgently needed to solve at least one of the above problems. Summary of the invention

[0005] The present application provides an intelligent quality detection method for the parametric modeling and design process of hyperbolic curtain walls, which aims to solve the problem that in the process of curtain wall modeling, when faced with complex hyperbolic surface models, modelers may not have a thorough understanding of curtain wall design and may ignore some key factors when dealing with details such as curtain wall nodes and seams, thereby affecting the overall effect of the curtain wall. In particular, newcomers often make some common modeling errors due to lack of experience, which may affect the design quality of the curtain wall and increase costs.

[0006] In a first aspect, the present application provides an intelligent quality detection method for use in a parametric modeling design process of a hyperbolic curtain wall, comprising:

[0007] When modeling a hyperbolic curtain wall model in a preset modeling environment, obtaining modeling parameter data corresponding to the hyperbolic curtain wall model, and preprocessing the modeling parameter data; the preprocessing at least includes cleaning, formatting and standardizing the data;

[0008] Acquire historical error data corresponding to the hyperbolic curtain wall model and preset expert knowledge to construct an error pattern library; the error pattern library includes error features, and the error features at least include structural errors, size errors, material matching errors, and node closing errors;

[0009] During the modeling process of the hyperbolic curtain wall model, the modeling process is monitored in real time according to the error pattern library;

[0010] If it is determined according to the error pattern library that there is at least one error feature in the modeling process, an error warning message is generated, the error warning message is displayed on the interface corresponding to the preset modeling environment, and an error location visualization report is generated to complete the intelligent quality detection in the parametric modeling design process of the hyperbolic curtain wall.

[0011] In some embodiments, the error warning information is displayed on an interface corresponding to the preset modeling environment, including: highlighting the erroneous component outline corresponding to the hyperbolic curtain wall model in the preset modeling environment; generating an error propagation link diagram with topological relationship annotations in the preset modeling environment; and displaying error correction suggestions according to a preset voice interaction form.

[0012] In some embodiments, generating the error location visualization report includes: generating a hierarchical error index directory, an interactive error impact domain stress cloud map, and a clause reference comparison table of associated design specifications corresponding to the hyperbolic curtain wall model according to the error warning information; generating the error location visualization report according to the error index directory, the interactive error impact domain stress cloud map, and the clause reference comparison table of associated design specifications.

[0013] In some embodiments, before the generating of the error warning information, it also includes: performing a stress compliance check on the hyperbolic curtain wall model based on finite element analysis; generating a predicted error propagation probability corresponding to the hyperbolic curtain wall model and the error feature according to Monte Carlo; performing a virtual installation rehearsal according to a preset digital twin model based on the predicted error propagation probability and the compliance check result corresponding to the stress compliance check to complete a secondary verification of the error feature, and if the secondary verification passes, generating the error warning information.

[0014] In some embodiments, after completing the intelligent quality inspection in the hyperbolic curtain wall parametric modeling design process, it also includes: obtaining the error correction record corresponding to the error location visualization report; performing feature extraction based on the error correction record to generate an error feature vector; and updating the error pattern library based on the error feature vector.

[0015] Exemplarily, the extracting features according to the error correction record to generate an error feature vector includes: extracting features from the error correction record according to a preset convolutional neural network and outputting the error feature vector; the expression of the error feature vector includes:

[0016] ;in, Indicates that the convolutional neural network is layer The error feature vector of the position output, is the convolution kernel size corresponding to the convolutional neural network, The convolutional neural network is described in The paranoid term of the layer, is the ReLU activation function, It is The relative position of the convolution kernel of the layer ( , ) is a weight parameter used to capture the spatial correlation of local error features, For the Layer at offset position The input feature value reflects the error features transmitted by the previous network layer.

[0017] Exemplarily, the updating of the error pattern library according to the error feature vector includes: dynamically optimizing a weight coefficient of the error pattern library to complete the updating of the error pattern library.

[0018] It should be noted that, in some embodiments, the dynamic optimization equation corresponding to the weight coefficient of the error mode library includes:

[0019] ;in, Represents the time step The weight coefficient corresponding to the error pattern library when , the range of weight coefficient is (0,1), is an attenuation adjustment factor, the attenuation adjustment factor is greater than 0, is the current time step counter, The base time offset is used to set the starting reference point of the pattern library update cycle. is the loss function In the parameters The gradient vector at reflects the optimization direction of the current model training state. It is a 2-norm operator that calculates the Euclidean length of the gradient vector and quantifies the magnitude of the update of the model parameters.

[0020] In some embodiments, before the real-time monitoring of the modeling process according to the error pattern library, it also includes: obtaining version information corresponding to the preset modeling environment; obtaining compatibility information corresponding to the error pattern library and the version information; if it is confirmed according to the compatibility information that the error pattern library is compatible with the preset modeling environment, the modeling process is monitored in real time according to the error pattern library.

[0021] Exemplarily, if it is confirmed according to the compatibility information that the error pattern library is incompatible with the preset modeling environment, the method includes: parsing the API calling protocol of the preset modeling environment based on reverse engineering; performing version-compatible packaging on the open graphical interface of the preset modeling environment; and constructing an independent operating environment sandbox corresponding to the error pattern library based on containerization technology to run the error pattern library in the independent operating environment sandbox to ensure that the error pattern library is compatible with the preset modeling environment.

[0022] In a second aspect, the present application provides an intelligent quality detection device for use in a hyperbolic curtain wall parametric modeling design process, comprising:

[0023] A data acquisition unit, used for acquiring modeling parameter data corresponding to the hyperbolic curtain wall model when modeling the hyperbolic curtain wall model in a preset modeling environment, and preprocessing the modeling parameter data; the preprocessing at least includes data cleaning, formatting and standardization;

[0024] An error acquisition unit is used to acquire historical error data corresponding to the hyperbolic curtain wall model and preset expert knowledge to construct an error pattern library; the error pattern library includes error features, and the error features at least include structural errors, size errors, material matching errors and node closing errors;

[0025] A real-time monitoring unit, used for monitoring the modeling process in real time according to the error pattern library during the modeling process of the hyperbolic curtain wall model;

[0026] The detection completion unit is used to generate error warning information if it is determined according to the error pattern library that there is at least one error feature in the modeling process, display the error warning information on the interface corresponding to the preset modeling environment, and generate an error location visualization report to complete the intelligent quality detection in the parametric modeling design process of the hyperbolic curtain wall.

[0027] In a third aspect, the present application provides a computer device comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement a method provided in any embodiment of the present application when executing the computer program.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer-readable instructions are executed by the processor, one or more processors execute a method as provided in any embodiment of the present application.

[0029] The embodiment of the present application provides an intelligent quality detection method for the parametric modeling design process of a hyperbolic curtain wall. The specific technical process is as follows:

[0030] Modeling parameter data preprocessing: Obtain modeling parameter data: In the preset modeling environment, when the user starts to model the hyperbolic curtain wall model, all relevant parameter data of the model are automatically obtained. Invalid or redundant data is removed to ensure the accuracy and consistency of the data. The data is converted into a unified format for subsequent processing. The data is standardized to meet a specific standard range for easy recognition and processing by the algorithm.

[0031] Build an error pattern library: Collect and organize various error cases that occurred in the past modeling process to form a historical error data set. Combine the knowledge and experience of domain experts to define various possible error features. Based on historical error data and expert knowledge, build an error pattern library containing multiple error features. Common error features include but are not limited to:

[0032] Structural errors: such as insufficient structural strength, unreasonable force distribution, etc.

[0033] Dimension error: such as the dimension exceeds the allowable range, the proportion is out of balance, etc.

[0034] Material matching error: such as using inappropriate materials or material properties not meeting the requirements.

[0035] Node closing errors: such as improper node connection method, poor handling of the closing, etc.

[0036] Real-time monitoring and error detection: During the modeling process, the system will continuously monitor the user's operations and compare the current modeling state with the error pattern library. Once the current modeling state is found to match an error feature in the error pattern library, the system will immediately generate a corresponding error warning message.

[0037] Generate error warning information: The generated error warning information is displayed in the interface corresponding to the preset modeling environment to remind users of potential problems. In addition to simple text prompts, the system will automatically generate a detailed error location visualization report, which graphically displays the specific location and cause of the error, helping users to understand the problem more intuitively.

[0038] The method can be implemented through the following steps: Environment construction: Select professional software that supports parametric modeling, such as Rhino, Grasshopper, etc. Integrate intelligent detection module: Integrate intelligent quality detection module in the modeling software, which is responsible for executing all the above steps.

[0039] Data collection and preprocessing: Automatic collection: When the user starts modeling, the system automatically collects all relevant parameter data. Data cleaning: Automatically remove invalid data by writing scripts or using existing tools. Formatting and standardization: Use standard data processing libraries (such as Pandas) to format and standardize data.

[0040] Build an error pattern library: Data collection: Collect error cases from historical projects and invite experts to participate in discussions to determine the specific characteristics of each error. Pattern library creation: Enter the collected error characteristics into the database and write the corresponding query logic for fast matching in real-time monitoring.

[0041] Real-time monitoring and error detection: Monitoring logic: Write real-time monitoring logic to regularly check the current modeling status and compare it with the error pattern library. Error detection: Once an error is detected, the alarm mechanism is immediately triggered to generate and display error warning information.

[0042] Generate error warning information: Interface display: Pop up an error warning window in the modeling software interface to display specific error information. Visual report: Generate a detailed error location report, showing the specific location of the error in the form of a three-dimensional graphic, with solution suggestions.

[0043] The provided method has at least the following beneficial effects:

[0044] Improve modeling quality: Through real-time monitoring and instant feedback, common modeling errors can be effectively avoided and the overall design quality can be improved.

[0045] Reduce design costs: Reduce rework and modifications caused by design errors, saving time and resources.

[0046] Assisting novices in learning: For inexperienced novice designers, this method can serve as a good guide and help them master the correct modeling techniques more quickly.

[0047] Improve work efficiency: Automated inspection reduces the time for manual review and improves the efficiency of the entire design process.

[0048] Enhanced user experience: Friendly user interface and intuitive error reporting make it easier for users to understand and solve problems, improving user experience.

[0049] In summary, this method has important application value and practical significance in the parametric modeling and design process of hyperbolic curtain walls.

[0050] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 It is a schematic flow chart of the steps of an intelligent quality detection method for a hyperbolic curtain wall parametric modeling design process provided by an embodiment of the present application;

[0053] Figure 2 It is a schematic block diagram of the structure of an intelligent quality detection device used in the parametric modeling design process of a hyperbolic curtain wall provided by an embodiment of the present application;

[0054] Figure 3 It is a schematic block diagram of the structure of a computer device provided in one embodiment of the present application.

[0055] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0058] It should be understood that, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the difference.

[0059] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0060] It should also be understood that the term “and / or” used in the specification and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0061] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0062] With the continuous innovation of architectural design, hyperbolic curtain wall, as a building facade material with high visual impact and unique shape, is increasingly widely used in modern buildings. Compared with traditional flat curtain wall, hyperbolic curtain wall has higher structural complexity, more irregular component shape, greater design difficulty and higher process requirements.

[0063] In the process of curtain wall modeling, faced with complex hyperbolic models, modelers may not have a thorough understanding of curtain wall design. When dealing with details such as curtain wall nodes and seams, they may ignore some key factors, which will affect the overall effect of the curtain wall. Especially newcomers, due to lack of experience, they often make some common modeling errors, which may affect the design quality of the curtain wall and increase costs.

[0064] Therefore, a method is urgently needed to solve at least one of the above problems.

[0065] To solve the above problems, please refer to Figure 1 ,like Figure 1 As shown, the provided intelligent quality detection method for the parametric modeling design process of the hyperbolic curtain wall includes steps S101 to S104. The intelligent quality detection method for the parametric modeling design process of the hyperbolic curtain wall is executed by a computer device, which may be a single server or a server cluster, or may be a handheld terminal, a laptop computer, a wearable device, or a robot, etc.

[0066] like Figure 1 As shown, the details of steps S101-S104 are as follows:

[0067] Step S101. When a hyperbolic curtain wall model is modeled in a preset modeling environment, modeling parameter data corresponding to the hyperbolic curtain wall model is obtained, and the modeling parameter data is preprocessed; the preprocessing at least includes data cleaning, formatting and standardization.

[0068] Specifically, at the beginning of the hyperbolic curtain wall model design, designers usually use professional building information modeling (BIM) software such as Revit, AutoCAD or Rhino for preliminary design. These software can generate detailed three-dimensional models and export data files containing all key parameters. Data extraction: Extract the required parameters from these design files, including but not limited to size (length, width, height), material type, location and shape of structural components, detailed information of connection nodes, etc. In addition, indirect information needs to be extracted from project requirement documents, such as specifications, standards, construction requirements, etc. Data storage: Store the extracted data in a unified database for subsequent processing and analysis.

[0069] Data cleaning includes: Invalid value processing: Check invalid values ​​in the data, such as negative numbers, values ​​outside the reasonable range, null values, etc., and mark and process them. For example, if the width of a panel is negative, it is marked as invalid and removed. Duplicate record processing: Identify and delete duplicate data records to ensure that each data is unique. Outlier detection: Use statistical methods (such as Z-score, IQR, etc.) to detect outliers and decide whether to keep or remove them based on the specific situation.

[0070] Formatting includes: Unit conversion: unify all length units into meters and angle units into radians to ensure data consistency. Timestamp standardization: unify all dates and timestamps into a standard format (such as ISO 8601) for subsequent processing. Text encoding: For descriptive features (such as material name, node type, etc.), use encoding technology to convert them into numerical form for computer processing. Standardization includes: Normalization: use methods such as Z-score normalization or minimum and maximum scaling to adjust the data distribution to a standard range to improve prediction accuracy. Feature engineering: further process the data as needed, such as creating new features, removing redundant features, etc., to improve model performance.

[0071] This step has at least the following beneficial effects:

[0072] Improve data quality: Through data cleaning and formatting, the risk of misjudgment caused by dirty and messy data is reduced, and the quality of data is improved. Promote data exchange: Unified data format and standardized processing promote data exchange and integration capabilities across systems. Improve processing efficiency: Standardized data enables subsequent analysis steps to run more efficiently, speeding up the entire testing process. Enhance readability: Clear data format and standardized processing enhance the readability and ease of use of data, facilitating communication and collaboration among team members.

[0073] Step S102: Acquire historical error data corresponding to the hyperbolic curtain wall model and preset expert knowledge to construct an error pattern library; the error pattern library includes error features, and the error features include at least structural errors, size errors, material matching errors and node closing errors.

[0074] Specifically, historical error data collection includes internal database access: reviewing historical projects in the company's internal database and collecting typical problem cases that have occurred, including error types, manifestations, solutions, etc. Literature review includes reviewing relevant academic papers, industry reports and technical documents to understand common error types and how to deal with them. Expert interviews include inviting professionals with rich practical experience to participate. They can point out some potential risk points based on their own experience and provide corresponding solution suggestions. The introduction of expert knowledge includes expert interview records: recording the opinions and suggestions of experts to form detailed documents. AI-assisted learning: Use natural language processing (NLP) technology to automatically learn the key points of knowledge in a large number of literature reports, extract key information and organize it into structured data.

[0075] Pattern summarization includes definition of error types: Based on the collected data, various common error types are defined, such as structural errors, size errors, material matching errors, node closing errors, etc. Example demonstration: Provide specific example pictures or video demonstrations for each error type to help users understand intuitively. Preventive measures description: For each error type, provide detailed preventive measures and solution descriptions to help users avoid similar errors.

[0076] The continuous update mechanism includes regular review: Regularly review and update the error pattern library to ensure its timeliness and practicality. User feedback: Encourage users to feedback new error types and solutions during use to continuously enrich and improve the pattern library.

[0077] This step has at least the following beneficial effects:

[0078] Theoretical basis: It provides a solid theoretical basis for quality inspection and ensures the accuracy and reliability of detection. Reduce human omissions: It reduces omissions caused by human factors and enhances the reliability and stability of the system. Cultivate newcomers: It helps novice designers quickly master the ability of complex tasks and shorten the learning curve. Continuous improvement: Through the continuous update mechanism, the timeliness and practicality of the pattern library are maintained, and the performance of the system is continuously improved.

[0079] Step S103: During the modeling process of the hyperbolic curtain wall model, the modeling process is monitored in real time according to the error pattern library.

[0080] Specifically, automated tracking includes scripting: using Python, JavaScript and other scripting languages ​​to write programs that automatically capture key indicators in the current state while the user is operating. Event monitoring: setting up event listeners to monitor user operation behaviors in real time and capture data changes at each step.

[0081] Anomaly detection algorithms include: Isolation Forest: Use the Isolation Forest algorithm to detect outliers in the data. This algorithm is suitable for high-dimensional data sets and can effectively identify outliers. Local Outlier Factor: Use the Local Outlier Factor (LOF) algorithm to detect outliers based on the local density of data points. Threshold Setting: Set a reasonable threshold based on historical data and expert experience. When the data exceeds the threshold, anomaly detection is triggered.

[0082] The feedback loop design includes: Immediate warning: Once a potential problem is found, the system will immediately pause the current action and issue a warning to the user to remind the user to pay attention. Confirmation mechanism: The user needs to confirm whether to continue to the next step to ensure that the problem is solved before continuing. Model optimization: Adjust the model training set according to the actual situation, optimize future performance, and gradually improve the accuracy and robustness of the system.

[0083] This step has at least the following beneficial effects:

[0084] Instant error correction: The instant error correction function is realized, which greatly shortens the time cycle from problem discovery to problem solving.

[0085] Reduce additional costs: Reduce additional costs caused by later modifications and improve the economic benefits of the project.

[0086] Enhance user experience: Allow users to understand their mistakes at the first time, improving user experience.

[0087] Improve work efficiency: Through real-time monitoring and instant feedback, designers' work efficiency is improved and unnecessary rework is reduced.

[0088] Step S104. If it is determined according to the error pattern library that there is at least one error feature in the modeling process, an error warning message is generated, the error warning message is displayed on the interface corresponding to the preset modeling environment, and an error location visualization report is generated to complete the intelligent quality detection in the parametric modeling design process of the hyperbolic curtain wall.

[0089] Specifically, information presentation includes: Visual prompts: Once an error is determined, the system will display the specific error location and related information to the user in a striking manner (such as red highlight, pop-up prompt, etc.). Text description: Provide a detailed error description, including the error type, specific location, possible causes, and recommended solutions. Multi-channel notifications: In addition to interface prompts, relevant responsible persons can also be notified through emails, text messages, etc. to ensure the timeliness and accuracy of information transmission.

[0090] Positioning visualization: 3D view: Generate a detailed 3D view to help users accurately locate the specific part where the deviation occurs. 2D plan view: Combined with the 2D plan view, it provides more perspectives and details to facilitate user understanding and processing. Annotation: Mark the specific error area in the view and add detailed annotations to guide how to correct it.

[0091] Report preparation: Basic information: The report should contain basic information about the project, such as project name, designer, test date, etc. Test results: List all problems found, including error type, severity assessment, specific location, etc. Improvement suggestions: Provide detailed improvement suggestions and solutions for each problem to help users solve the problem quickly. Summary and suggestions: Summarize the overall test results and put forward further improvement measures and suggestions for managers' reference. Archive management: Archive the report for future query and reference, and accumulate experience and lessons.

[0092] This step has at least the following beneficial effects:

[0093] Comprehensive and accurate basis: It provides managers with comprehensive and accurate quality control basis to facilitate decision-making and management.

[0094] Communication and collaboration: Facilitate communication and collaboration among team members and avoid ambiguity in the process of information transmission.

[0095] Experience accumulation: It is conducive to the long-term accumulation of experience and lessons, and promotes the overall improvement of the organization.

[0096] Transparency: It improves the transparency of the project, facilitates supervision and management by all parties, and ensures the smooth progress of the project.

[0097] Continuous improvement: Through regular reports and summaries, we continuously improve the design and construction process and enhance the overall quality of the project.

[0098] The method can be implemented through the following steps: Environment construction: Select professional software that supports parametric modeling, such as Rhino, Grasshopper, etc. Integrate intelligent detection module: Integrate intelligent quality detection module in the modeling software, which is responsible for executing all the above steps.

[0099] Data collection and preprocessing: Automatic collection: When the user starts modeling, the system automatically collects all relevant parameter data. Data cleaning: Automatically remove invalid data by writing scripts or using existing tools. Formatting and standardization: Use standard data processing libraries (such as Pandas) to format and standardize data.

[0100] Build an error pattern library: Data collection: Collect error cases from historical projects and invite experts to participate in discussions to determine the specific characteristics of each error. Pattern library creation: Enter the collected error characteristics into the database and write the corresponding query logic for fast matching in real-time monitoring.

[0101] Real-time monitoring and error detection: Monitoring logic: Write real-time monitoring logic to regularly check the current modeling status and compare it with the error pattern library. Error detection: Once an error is detected, the alarm mechanism is immediately triggered to generate and display error warning information.

[0102] Generate error warning information: Interface display: Pop up an error warning window in the modeling software interface to display specific error information. Visual report: Generate a detailed error location report, showing the specific location of the error in the form of a three-dimensional graphic, with solution suggestions.

[0103] The provided method has at least the following beneficial effects:

[0104] Improve modeling quality: Through real-time monitoring and instant feedback, common modeling errors can be effectively avoided and the overall design quality can be improved.

[0105] Reduce design costs: Reduce rework and modifications caused by design errors, saving time and resources.

[0106] Assisting novices in learning: For inexperienced novice designers, this method can serve as a good guide and help them master the correct modeling techniques more quickly.

[0107] Improve work efficiency: Automated inspection reduces the time for manual review and improves the efficiency of the entire design process.

[0108] Enhanced user experience: Friendly user interface and intuitive error reporting make it easier for users to understand and solve problems, improving user experience.

[0109] In summary, this method has important application value and practical significance in the parametric modeling and design process of hyperbolic curtain walls.

[0110] In some embodiments, the error warning information is displayed on an interface corresponding to the preset modeling environment, including: highlighting the erroneous component outline corresponding to the hyperbolic curtain wall model in the preset modeling environment; generating an error propagation link diagram with topological relationship annotations in the preset modeling environment; and displaying error correction suggestions according to a preset voice interaction form.

[0111] Specifically, highlight the outline of the wrong component: In the preset modeling environment, when an error is detected, the system automatically highlights the corresponding wrong component outline in the hyperbolic curtain wall model. This can be achieved by changing the color of the component, adding a border, or using other visual effects. If the position of a node is incorrect, the node and the surrounding area will be marked in red, and there may be a flashing effect to attract the user's attention.

[0112] Generate an error propagation link diagram with topological relationship annotations: An error propagation link diagram with topological relationship annotations will be automatically generated to show how errors propagate from one component to another. This diagram can be two-dimensional or three-dimensional, depending on the specific situation. Assuming that a certain size error causes problems with multiple connected nodes, the system will generate a link diagram to show the topological relationship between these nodes, and use arrows and color coding to indicate the propagation path of the error.

[0113] Display error correction suggestions in the form of voice interaction: Through speech synthesis technology, error correction suggestions are conveyed to users in the form of voice. This can be achieved by integrating a TTS (Text-to-Speech) engine. If a material matching error is detected, the user will be prompted by voice: "Please note that the panel material of layer 5 does not meet the design specifications. Please check and change it to the specified material."

[0114] This embodiment has at least the following beneficial effects:

[0115] Intuitive: Highlighting the outline of erroneous components enables users to quickly locate the problem and improve work efficiency.

[0116] Visualization: The error propagation link diagram with topological relationship annotations helps users understand the error propagation path and grasp the overall impact of the problem.

[0117] Convenience: Error correction suggestions in the form of voice interaction provide a more natural and convenient user experience, especially when multitasking.

[0118] In some embodiments, generating the error location visualization report includes: generating a hierarchical error index directory, an interactive error impact domain stress cloud map, and a clause reference comparison table of associated design specifications corresponding to the hyperbolic curtain wall model according to the error warning information; generating the error location visualization report according to the error index directory, the interactive error impact domain stress cloud map, and the clause reference comparison table of associated design specifications.

[0119] Hierarchical error index directory: Based on the error warning information, the system generates a hierarchical error index directory, listing all detected errors and their categories. Each error entry contains detailed description and location information.

[0120] Example: The directory structure is as follows: structural error; incorrect node position; missing connectors; incorrect size; panel size does not match; incorrect support rod length; incorrect material matching; panel material does not match; incorrect sealant type; incorrect node joint; joint not sealed; poor sealing at joint.

[0121] Interactive error impact domain stress cloud map: Generate an interactive stress cloud map to show the impact of errors on the structural stress distribution. Users can click on different areas to view detailed information. Example: Users can see different stress levels represented by different colors on the stress cloud map, and click on a high stress area to view the specific stress value and related component information.

[0122] Reference table of clauses in associated design specifications: The system generates a table listing each error and its corresponding design specification clause. Users can jump directly to the corresponding specification document by clicking on the clause link. Example: For a node position error, the method lists "GB 50018-2002 Clause 3.2.1" in the table, and users can click on the entry to view the specific specification requirements.

[0123] Generate error location visualization report: Integrate the above three parts into a complete report and provide it to users for download or online viewing. Example: The report includes a directory, stress cloud diagram and clause reference comparison table, which users can easily check and refer to.

[0124] This embodiment has at least the following beneficial effects:

[0125] Clear hierarchy: The hierarchical error index directory enables users to quickly find specific error information and improve search efficiency.

[0126] Intuitive visualization: Interactive stress cloud diagrams intuitively show the impact of errors on structural stress, helping users better understand the severity of the problem.

[0127] Specification guidance: The reference table of related design specifications provides users with clear specification basis to ensure that the design complies with the standards.

[0128] In some embodiments, before the generating of the error warning information, it also includes: performing a stress compliance check on the hyperbolic curtain wall model based on finite element analysis; generating a predicted error propagation probability corresponding to the hyperbolic curtain wall model and the error feature according to Monte Carlo; performing a virtual installation rehearsal according to a preset digital twin model based on the predicted error propagation probability and the compliance check result corresponding to the stress compliance check to complete a secondary verification of the error feature, and if the secondary verification passes, generating the error warning information.

[0129] Finite element analysis Before generating an error warning message, the system performs stress compliance verification on the hyperbolic curtain wall model based on the finite element analysis method. By calculating the stress distribution of the model under various working conditions, it is determined whether there is a stress exceeding the standard. For example, if the stress value of a node under wind load is calculated to be 250 MPa, which exceeds the maximum value of 200 MPa allowed by the design specification, it is determined that the node has a stress exceeding standard problem.

[0130] Monte Carlo simulation: Generate a hyperbolic curtain wall model and the predicted error propagation probability corresponding to the error features using the Monte Carlo method. Estimate the error propagation probability in the model through random sampling and multiple simulations. For example, through Monte Carlo simulation, it is found that there is an 80% probability that a certain size error will cause the displacement of adjacent nodes to exceed the standard, thus triggering a series of chain reactions.

[0131] Digital twin virtual installation rehearsal: Based on the preset digital twin model, the system conducts a virtual installation rehearsal based on the predicted error propagation probability and stress compliance verification results. The actual installation process is simulated in a simulation environment to further verify the impact of errors. For example, when simulating the installation process in a virtual environment, it is found that a certain dimensional error does cause the displacement of adjacent nodes to exceed the standard, confirming the previous analysis results.

[0132] If the secondary verification is passed, an error warning message is generated; otherwise, the model is adjusted and re-verified. After the virtual installation preview, it is confirmed that a certain dimension error does exist and a corresponding error warning message is generated.

[0133] This embodiment has at least the following beneficial effects:

[0134] Accuracy: Finite element analysis and Monte Carlo simulation provide highly accurate analysis results, improving the accuracy of error detection.

[0135] Comprehensiveness: The digital twin virtual installation preview takes into account various factors in the actual installation process, ensuring the comprehensiveness and reliability of the test results.

[0136] Reliability: Through secondary verification, the possibility of false positives and false negatives is reduced, and the reliability and stability of the system are improved.

[0137] In some embodiments, after completing the intelligent quality inspection in the hyperbolic curtain wall parametric modeling design process, it also includes: obtaining the error correction record corresponding to the error location visualization report; performing feature extraction based on the error correction record to generate an error feature vector; and updating the error pattern library based on the error feature vector.

[0138] After completing the intelligent quality inspection, the system obtains the error correction record corresponding to the error location visualization report. These records include the user's error correction operations and results. The system records the user's correction operations on a certain node position error, including the specific coordinate changes of the mobile node. According to the preset convolutional neural network (CNN), the error correction record is feature extracted and the error feature vector is output. For example, the convolutional neural network extracts the spatial correlation of local error features by performing a convolution operation on the image data of the correction record. The error pattern library is updated according to the generated error feature vector, and the weight coefficient of the error pattern library is dynamically optimized. For example, the weight coefficient in the error pattern library is adjusted according to the new error feature vector to make it more suitable for the current design situation.

[0139] This step has at least the following beneficial effects:

[0140] Continuous improvement: By continuously updating the error pattern library, the system can gradually learn new error types and solutions, improving the accuracy and comprehensiveness of detection.

[0141] Adaptability: Dynamic optimization of weight coefficients enables the error pattern library to adapt to different design projects and environments, improving the flexibility and robustness of the system.

[0142] Exemplarily, the extracting features according to the error correction record to generate an error feature vector includes: extracting features from the error correction record according to a preset convolutional neural network and outputting the error feature vector; the expression of the error feature vector includes:

[0143] ;in, Indicates that the convolutional neural network is layer The error feature vector of the position output, is the convolution kernel size corresponding to the convolutional neural network, The convolutional neural network is described in The paranoid term of the layer, is the ReLU activation function, It is The relative position of the convolution kernel of the layer ( , ) is a weight parameter used to capture the spatial correlation of local error features, For the Layer at offset position The input feature value reflects the error features transmitted by the previous network layer.

[0144] For example, the preset convolutional neural network is used to extract features from error correction records. The convolutional neural network captures the spatial correlation of local error features through multi-layer convolution operations. The image data of the correction record is processed by the convolutional neural network to extract features such as node position errors and size errors. The convolutional neural network can efficiently extract complex local features, improving the efficiency and accuracy of feature extraction. Through multi-layer convolution operations, the system can capture multiple types of error features, improving the robustness and adaptability of the system.

[0145] Exemplarily, the updating of the error pattern library according to the error feature vector includes: dynamically optimizing a weight coefficient of the error pattern library to complete the updating of the error pattern library.

[0146] By dynamically adjusting the weight coefficient according to the current training status and gradient information, the error pattern library can better adapt to the current design situation. For example, according to the current loss function gradient information, the weight coefficient is adjusted to make it closer to the optimal solution. Dynamic optimization enables the error pattern library to be adjusted according to the current design situation and training status, improving the adaptability and robustness of the system. By optimizing the weight coefficient, various error types can be more accurately identified and processed, improving the accuracy of detection.

[0147] It should be noted that, in some embodiments, the dynamic optimization equation corresponding to the weight coefficient of the error mode library includes:

[0148] ;in, Represents the time step The weight coefficient corresponding to the error pattern library when , the range of weight coefficient is (0,1), is an attenuation adjustment factor, the attenuation adjustment factor is greater than 0, is the current time step counter, The base time offset is used to set the starting reference point of the pattern library update cycle. is the loss function In the parameters The gradient vector at reflects the optimization direction of the current model training state. It is a 2-norm operator that calculates the Euclidean length of the gradient vector and quantifies the magnitude of the update of the model parameters.

[0149] According to the current training status and gradient information, the weight coefficient is dynamically adjusted so that the error pattern library can better adapt to the current design situation. For example, according to the current loss function gradient information, the weight coefficient is adjusted to make it closer to the optimal solution. Dynamic optimization enables the error pattern library to be adjusted according to the current design situation and training status, improving the adaptability and robustness of the system. By optimizing the weight coefficient, the method can more accurately identify and handle various error types, improving the accuracy of detection.

[0150] In some embodiments, before the real-time monitoring of the modeling process according to the error pattern library, it also includes: obtaining version information corresponding to the preset modeling environment; obtaining compatibility information corresponding to the error pattern library and the version information; if it is confirmed according to the compatibility information that the error pattern library is compatible with the preset modeling environment, the modeling process is monitored in real time according to the error pattern library.

[0151] By obtaining the version information of the preset modeling environment, including software version number, API version, etc.

[0152] If it is detected that the modeling software version currently used is 2025.1.

[0153] Obtain compatibility information: By obtaining the compatibility information between the error pattern library and the preset modeling environment, determine whether the two are compatible. For example, by querying the database, it is found that the error pattern library supports version 2025.1. If compatibility is confirmed, the system continues to monitor the modeling process in real time based on the error pattern library. After confirming compatibility, start real-time monitoring of the modeling process. Through version compatibility checking, ensure that the error pattern library can run normally in the current modeling environment to avoid errors caused by version incompatibility. Improve the stability and reliability of the method and ensure the smooth progress of the detection process.

[0154] Exemplarily, if it is confirmed according to the compatibility information that the error pattern library is incompatible with the preset modeling environment, the method includes: parsing the API calling protocol of the preset modeling environment based on reverse engineering; performing version-compatible packaging on the open graphical interface of the preset modeling environment; and constructing an independent operating environment sandbox corresponding to the error pattern library based on containerization technology to run the error pattern library in the independent operating environment sandbox to ensure that the error pattern library is compatible with the preset modeling environment.

[0155] If the error pattern library is found to be incompatible with the preset modeling environment, the system parses the API call protocol of the modeling environment through reverse engineering to understand its interface details. The API call protocol of 2025.1 is parsed through reverse engineering to understand its interface parameters and return values. The open graphical interface of the modeling environment is packaged for version compatibility to make it compatible with the error pattern library. For example, write adaptation code to convert the API call of 2025.1 to the format supported by the error pattern library. Use containerization technology (such as Docker) to build an independent operating environment sandbox for the error pattern library to ensure that it can run in an isolated environment. For example, create a Docker container, configure the operating environment required by the error pattern library, and run the error pattern library in it.

[0156] Through reverse engineering and version-compatible encapsulation, we ensure that the error pattern library can run normally in modeling environments of different versions. By building an independent operating environment sandbox through containerization technology, we ensure the independence and stability of the error pattern library. This improves the flexibility and adaptability of the method and enables deployment and operation in multiple environments.

[0157] See also Figure 2 As shown, Figure 2 1 is a schematic diagram of the structure of an intelligent quality detection device 200 for use in a hyperbolic curtain wall parametric modeling design process provided by an embodiment of the present application. The intelligent quality detection device 200 for use in a hyperbolic curtain wall parametric modeling design process is used to execute the steps of the intelligent quality detection method for use in a hyperbolic curtain wall parametric modeling design process shown in the above-mentioned embodiments. The intelligent quality detection device 200 for use in a hyperbolic curtain wall parametric modeling design process can be a single server or a server cluster, or the intelligent quality detection device 200 for use in a hyperbolic curtain wall parametric modeling design process can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device, a robot, etc.

[0158] like Figure 2 As shown, the intelligent quality detection device 200 used in the parametric modeling design process of the hyperbolic curtain wall includes:

[0159] The data acquisition unit 201 is used to acquire the modeling parameter data corresponding to the hyperbolic curtain wall model when modeling the hyperbolic curtain wall model in the preset modeling environment, and preprocess the modeling parameter data; the preprocessing at least includes data cleaning, formatting and standardization;

[0160] The error acquisition unit 202 is used to acquire the historical error data corresponding to the hyperbolic curtain wall model and the preset expert knowledge to construct an error pattern library; the error pattern library includes error features, and the error features at least include structural errors, size errors, material matching errors and node closing errors;

[0161] A real-time monitoring unit 203 is used to monitor the modeling process in real time according to the error pattern library during the modeling process of the hyperbolic curtain wall model;

[0162] The detection completion unit 204 is used to generate error warning information if it is determined according to the error pattern library that there is at least one error feature in the modeling process, display the error warning information on the interface corresponding to the preset modeling environment, and generate an error location visualization report to complete the intelligent quality detection in the parametric modeling design process of the hyperbolic curtain wall.

[0163] In some embodiments, the error warning information is displayed on an interface corresponding to the preset modeling environment, including: highlighting the erroneous component outline corresponding to the hyperbolic curtain wall model in the preset modeling environment; generating an error propagation link diagram with topological relationship annotations in the preset modeling environment; and displaying error correction suggestions according to a preset voice interaction form.

[0164] In some embodiments, generating the error location visualization report includes: generating a hierarchical error index directory, an interactive error impact domain stress cloud map, and a clause reference comparison table of associated design specifications corresponding to the hyperbolic curtain wall model according to the error warning information; generating the error location visualization report according to the error index directory, the interactive error impact domain stress cloud map, and the clause reference comparison table of associated design specifications.

[0165] In some embodiments, before the generating of the error warning information, it also includes: performing a stress compliance check on the hyperbolic curtain wall model based on finite element analysis; generating a predicted error propagation probability corresponding to the hyperbolic curtain wall model and the error feature according to Monte Carlo; performing a virtual installation rehearsal according to a preset digital twin model based on the predicted error propagation probability and the compliance check result corresponding to the stress compliance check to complete a secondary verification of the error feature, and if the secondary verification passes, generating the error warning information.

[0166] In some embodiments, after completing the intelligent quality inspection in the hyperbolic curtain wall parametric modeling design process, it also includes: obtaining the error correction record corresponding to the error location visualization report; performing feature extraction based on the error correction record to generate an error feature vector; and updating the error pattern library based on the error feature vector.

[0167] Exemplarily, the extracting features according to the error correction record to generate an error feature vector includes: extracting features from the error correction record according to a preset convolutional neural network and outputting the error feature vector; the expression of the error feature vector includes:

[0168] ;in, Indicates that the convolutional neural network is layer The error feature vector of the position output, is the convolution kernel size corresponding to the convolutional neural network, The convolutional neural network is described in The paranoid term of the layer, is the ReLU activation function, It is The relative position of the convolution kernel of the layer ( , ) is a weight parameter used to capture the spatial correlation of local error features, For the Layer at offset position The input feature value reflects the error features transmitted by the previous network layer.

[0169] Exemplarily, the updating of the error pattern library according to the error feature vector includes: dynamically optimizing a weight coefficient of the error pattern library to complete the updating of the error pattern library.

[0170] It should be noted that, in some embodiments, the dynamic optimization equation corresponding to the weight coefficient of the error mode library includes:

[0171] ;in, Represents the time step The weight coefficient corresponding to the error pattern library when , the range of weight coefficient is (0,1), is an attenuation adjustment factor, the attenuation adjustment factor is greater than 0, is the current time step counter, The base time offset is used to set the starting reference point of the pattern library update cycle. is the loss function In the parameters The gradient vector at reflects the optimization direction of the current model training state. It is a 2-norm operator that calculates the Euclidean length of the gradient vector and quantifies the magnitude of the update of the model parameters.

[0172] In some embodiments, before the real-time monitoring of the modeling process according to the error pattern library, it also includes: obtaining version information corresponding to the preset modeling environment; obtaining compatibility information corresponding to the error pattern library and the version information; if it is confirmed according to the compatibility information that the error pattern library is compatible with the preset modeling environment, the modeling process is monitored in real time according to the error pattern library.

[0173] Exemplarily, if it is confirmed according to the compatibility information that the error pattern library is incompatible with the preset modeling environment, the method includes: parsing the API calling protocol of the preset modeling environment based on reverse engineering; performing version-compatible packaging on the open graphical interface of the preset modeling environment; and constructing an independent operating environment sandbox corresponding to the error pattern library based on containerization technology to run the error pattern library in the independent operating environment sandbox to ensure that the error pattern library is compatible with the preset modeling environment.

[0174] It should be noted that, those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working processes of the intelligent quality detection device and each module used in the parametric modeling and design process of the hyperbolic curtain wall described above can refer to the corresponding processes in the embodiments of the intelligent quality detection method used in the parametric modeling and design process of the hyperbolic curtain wall described in the above embodiments, and will not be repeated here.

[0175] The above-mentioned intelligent quality detection method for the parametric modeling design process of the hyperbolic curtain wall can be implemented in the form of a computer program. The computer program can be used in Figure 2 Run on the device shown.

[0176] See also Figure 3 , Figure 3 1 is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device includes a processor, a memory and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0177] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any intelligent quality detection method used in the parametric modeling design process of the hyperbolic curtain wall.

[0178] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0179] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any intelligent quality detection method used in the parametric modeling design process of the hyperbolic curtain wall.

[0180] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the terminal to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0181] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0182] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0183] When modeling a hyperbolic curtain wall model in a preset modeling environment, obtaining modeling parameter data corresponding to the hyperbolic curtain wall model, and preprocessing the modeling parameter data; the preprocessing at least includes cleaning, formatting and standardizing the data;

[0184] Acquire historical error data corresponding to the hyperbolic curtain wall model and preset expert knowledge to construct an error pattern library; the error pattern library includes error features, and the error features at least include structural errors, size errors, material matching errors, and node closing errors;

[0185] During the modeling process of the hyperbolic curtain wall model, the modeling process is monitored in real time according to the error pattern library;

[0186] If it is determined according to the error pattern library that there is at least one error feature in the modeling process, an error warning message is generated, the error warning message is displayed on the interface corresponding to the preset modeling environment, and an error location visualization report is generated to complete the intelligent quality detection in the parametric modeling design process of the hyperbolic curtain wall.

[0187] In some embodiments, the error warning information is displayed on an interface corresponding to the preset modeling environment, including: highlighting the erroneous component outline corresponding to the hyperbolic curtain wall model in the preset modeling environment; generating an error propagation link diagram with topological relationship annotations in the preset modeling environment; and displaying error correction suggestions according to a preset voice interaction form.

[0188] In some embodiments, generating the error location visualization report includes: generating a hierarchical error index directory, an interactive error impact domain stress cloud map, and a clause reference comparison table of associated design specifications corresponding to the hyperbolic curtain wall model according to the error warning information; generating the error location visualization report according to the error index directory, the interactive error impact domain stress cloud map, and the clause reference comparison table of associated design specifications.

[0189] In some embodiments, before the generating of the error warning information, it also includes: performing a stress compliance check on the hyperbolic curtain wall model based on finite element analysis; generating a predicted error propagation probability corresponding to the hyperbolic curtain wall model and the error feature according to Monte Carlo; performing a virtual installation rehearsal according to a preset digital twin model based on the predicted error propagation probability and the compliance check result corresponding to the stress compliance check to complete a secondary verification of the error feature, and if the secondary verification passes, generating the error warning information.

[0190] In some embodiments, after completing the intelligent quality inspection in the hyperbolic curtain wall parametric modeling design process, it also includes: obtaining the error correction record corresponding to the error location visualization report; performing feature extraction based on the error correction record to generate an error feature vector; and updating the error pattern library based on the error feature vector.

[0191] Exemplarily, the extracting features according to the error correction record to generate an error feature vector includes: extracting features from the error correction record according to a preset convolutional neural network and outputting the error feature vector; the expression of the error feature vector includes:

[0192] ;in, Indicates that the convolutional neural network is layer The error feature vector of the position output, is the convolution kernel size corresponding to the convolutional neural network, The convolutional neural network is described in The paranoid term of the layer, is the ReLU activation function, It is The relative position of the convolution kernel of the layer ( , ) is a weight parameter used to capture the spatial correlation of local error features, For the Layer at offset position The input feature value reflects the error features transmitted by the previous network layer.

[0193] Exemplarily, the updating of the error pattern library according to the error feature vector includes: dynamically optimizing a weight coefficient of the error pattern library to complete the updating of the error pattern library.

[0194] It should be noted that, in some embodiments, the dynamic optimization equation corresponding to the weight coefficient of the error mode library includes:

[0195] ;in, Represents the time step The weight coefficient corresponding to the error pattern library when , the range of weight coefficient is (0,1), is an attenuation adjustment factor, the attenuation adjustment factor is greater than 0, is the current time step counter, The base time offset is used to set the starting reference point of the pattern library update cycle. is the loss function In the parameters The gradient vector at reflects the optimization direction of the current model training state. It is a 2-norm operator that calculates the Euclidean length of the gradient vector and quantifies the magnitude of the update of the model parameters.

[0196] In some embodiments, before the real-time monitoring of the modeling process according to the error pattern library, it also includes: obtaining version information corresponding to the preset modeling environment; obtaining compatibility information corresponding to the error pattern library and the version information; if it is confirmed according to the compatibility information that the error pattern library is compatible with the preset modeling environment, the modeling process is monitored in real time according to the error pattern library.

[0197] Exemplarily, if it is confirmed according to the compatibility information that the error pattern library is incompatible with the preset modeling environment, the method includes: parsing the API calling protocol of the preset modeling environment based on reverse engineering; performing version-compatible packaging on the open graphical interface of the preset modeling environment; and constructing an independent operating environment sandbox corresponding to the error pattern library based on containerization technology to run the error pattern library in the independent operating environment sandbox to ensure that the error pattern library is compatible with the preset modeling environment.

[0198] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the computer equipment and each module described above can refer to the corresponding process in the embodiment of the intelligent quality detection method for the parametric modeling design process of the hyperbolic curtain wall described in the above embodiments, and will not be repeated here.

[0199] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the steps of the intelligent quality detection method for the parametric modeling design process of a hyperbolic curtain wall as provided in any embodiment of the present application.

[0200] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0201] Exemplarily, the medium is used to implement the following steps:

[0202] When modeling a hyperbolic curtain wall model in a preset modeling environment, obtaining modeling parameter data corresponding to the hyperbolic curtain wall model, and preprocessing the modeling parameter data; the preprocessing at least includes cleaning, formatting and standardizing the data;

[0203] Acquire historical error data corresponding to the hyperbolic curtain wall model and preset expert knowledge to construct an error pattern library; the error pattern library includes error features, and the error features at least include structural errors, size errors, material matching errors, and node closing errors;

[0204] During the modeling process of the hyperbolic curtain wall model, the modeling process is monitored in real time according to the error pattern library;

[0205] If it is determined according to the error pattern library that there is at least one error feature in the modeling process, an error warning message is generated, the error warning message is displayed on the interface corresponding to the preset modeling environment, and an error location visualization report is generated to complete the intelligent quality detection in the parametric modeling design process of the hyperbolic curtain wall.

[0206] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the storage medium and each module described above can refer to the corresponding process in the embodiment of the intelligent quality detection method for the parametric modeling design process of the hyperbolic curtain wall described in the above embodiments, and will not be repeated here.

[0207] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An intelligent quality detection method for parametric modeling design of hyperbolic curtain walls, characterized in that: include: When modeling a hyperbolic curtain wall model in a preset modeling environment, obtaining modeling parameter data corresponding to the hyperbolic curtain wall model, and preprocessing the modeling parameter data; the preprocessing at least includes cleaning, formatting and standardizing the data; Acquire historical error data corresponding to the hyperbolic curtain wall model and preset expert knowledge to construct an error pattern library; The error pattern library includes error features, and the error features at least include structural errors, size errors, material matching errors, and node closing errors; During the modeling process of the hyperbolic curtain wall model, the modeling process is monitored in real time according to the error pattern library; If it is determined according to the error pattern library that there is at least one error feature in the modeling process, an error warning message is generated, the error warning message is displayed on the interface corresponding to the preset modeling environment, and an error location visualization report is generated to complete the intelligent quality detection in the parametric modeling design process of the hyperbolic curtain wall.

2. The method according to claim 1, characterized in that The displaying of the error warning information on the interface corresponding to the preset modeling environment includes: Highlighting the erroneous component contour corresponding to the hyperbolic curtain wall model in the preset modeling environment; Generating an error propagation link graph with topological relationship annotations in the preset modeling environment; Displays error correction suggestions based on the preset voice interaction form.

3. The method according to claim 1, characterized in that The generating of the error location visualization report includes: Generating a hierarchical error index catalog, an interactive error impact domain stress cloud diagram, and a clause reference comparison table of associated design specifications corresponding to the hyperbolic curtain wall model according to the error warning information; The error location visualization report is generated according to the error index directory, the interactive error impact domain stress cloud diagram and the clause reference comparison table of the associated design specification.

4. The method according to claim 1, characterized in that: Before generating the error warning information, the method further includes: Performing stress compliance verification on the hyperbolic curtain wall model based on finite element analysis; Generate the predicted error propagation probability corresponding to the hyperbolic curtain wall model and the error feature according to Monte Carlo; According to the preset digital twin model, a virtual installation rehearsal is performed according to the compliance verification results corresponding to the predicted error propagation probability and the stress compliance verification to complete the secondary verification of the error characteristics. If the secondary verification passes, the error warning information is generated.

5. The method according to claim 1, characterized in that After completing the intelligent quality inspection in the hyperbolic curtain wall parametric modeling design process, it also includes: Obtaining an error correction record corresponding to the error location visualization report; Perform feature extraction according to the error correction record to generate an error feature vector; The error pattern library is updated according to the error feature vector.

6. The method according to claim 5, characterized in that The step of extracting features according to the error correction record to generate an error feature vector includes: The error correction record is subjected to feature extraction according to a preset convolutional neural network, and the error feature vector is output; the expression of the error feature vector includes: ; in, Indicates that the convolutional neural network is layer The error feature vector of the position output, is the convolution kernel size corresponding to the convolutional neural network, The convolutional neural network is described in The paranoid term of the layer, is the ReLU activation function, It is The relative position of the convolution kernel of the layer ( , ) is a weight parameter used to capture the spatial correlation of local error features, For the Layer at offset position The input feature value reflects the error features transmitted by the previous network layer.

7. The method according to claim 5, characterized in that The updating of the error pattern library according to the error feature vector comprises: The weight coefficient of the error pattern library is dynamically optimized to complete the update of the error pattern library.

8. The method according to claim 7, characterized in that The dynamic optimization equation corresponding to the weight coefficient of the error mode library includes: ; in, Represents the time step The weight coefficient corresponding to the error pattern library when , the range of weight coefficient is (0,1), is an attenuation adjustment factor, the attenuation adjustment factor is greater than 0, is the current time step counter, The base time offset is used to set the starting reference point of the pattern library update cycle. is the loss function In the parameters The gradient vector at reflects the optimization direction of the current model training state. It is a 2-norm operator that calculates the Euclidean length of the gradient vector and quantifies the magnitude of the update of the model parameters.

9. The method according to claim 1, characterized in that: Before real-time monitoring of the modeling process according to the error pattern library, the method further includes: Obtaining version information corresponding to the preset modeling environment; Obtaining compatibility information between the error pattern library and the version information; If it is confirmed according to the compatibility information that the error pattern library is compatible with the preset modeling environment, the modeling process is monitored in real time according to the error pattern library.

10. The method according to claim 9, characterized in that If it is confirmed according to the compatibility information that the error mode library is incompatible with the preset modeling environment, the method includes: Analyzing the API calling protocol of the preset modeling environment based on reverse engineering; Provide version-compatible packaging for the open graphical interface of the preset modeling environment; An independent operating environment sandbox corresponding to the error pattern library is constructed based on containerization technology to run the error pattern library in the independent operating environment sandbox, thereby ensuring that the error pattern library is compatible with the preset modeling environment.

Images