MBSE-based industrial host machine digital prototype collaborative design method and device

Abstract

The application discloses an industrial host machine digital prototype collaborative design method and device based on MBSE, and belongs to the technical field of industrial host machine modeling. The method comprises the following steps: S1, a design model library of an industrial host machine digital prototype is constructed; the design model library comprises a plurality of different types of requirement models and a plurality of large models for requirements of each aspect of the digital prototype; S2, according to a target and requirements, a plurality of suitable requirement models are selected from the design model library, and the large models matched are called by using artificial intelligence technology to construct an industrial host machine structure digital prototype model, an industrial host machine electrical digital prototype model, an industrial host machine hydraulic digital prototype model and / or an industrial host machine process digital prototype model; and S3, the digital prototype model is adjusted and optimized to obtain an industrial host machine digital prototype model meeting accuracy requirements. The application can perform digital prototype design from four dimensions, multi-model fusion, and improve the design efficiency and accuracy of the industrial host machine.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of industrial mother machine modeling, and particularly relates to an industrial mother machine digital prototype collaborative design method and device based on MBSE. BACKGROUND

[0002] The application of model-based system engineering (MBSE) in industrial mother machine digital prototype modeling is a complex process that combines system engineering methods and advanced modeling techniques. By using standard system modeling languages (such as SysML) to build requirement models, functional models and architecture models, the decomposition and allocation from requirements to functions are realized. This methodology emphasizes model-centric system analysis and design to ensure that the entire system can achieve the predetermined engineering objectives.

[0003] Industrial mother machines are the core equipment of manufacturing industry, and their design and manufacturing process requires high precision and reliability. Digital prototype modeling technology provides strong support for the design and optimization of industrial mother machines. Through digital prototype, the product can be simulated and analyzed in a virtual environment, so that potential problems can be found and improved in advance, greatly reducing the cost and risk of physical trial production.

[0004] Currently, the implementation scheme of modeling industrial mother machine digital prototype through MBSE is mainly designed by experience, without forming a modular model construction, and generally involves multiple design tools and simulation tools. The discrete use of tools is difficult to collaborate, which limits the modeling. And the existing digital prototype scheme is mainly for aerospace, without a systematic digital prototype design method for industrial mother machines. SUMMARY

[0005] The present application aims to at least partially solve one of the above-mentioned technical problems in the related art.

[0006] To this end, the present application aims to provide an industrial mother machine digital prototype collaborative design method and device based on MBSE, which can perform collaborative design of digital prototype from four dimensions, multi-model fusion, and improve the design efficiency and precision of industrial mother machines.

[0007] In order to solve the above technical problems, the present application is implemented as follows:

[0008] The embodiment of the present application provides an industrial mother machine digital prototype collaborative design method based on MBSE, which comprises:

[0009] S1, a design model library of industrial mother machine digital prototype is constructed; the design model library contains a plurality of different types of requirement models and a plurality of large models for each aspect of the digital prototype requirement;

[0010] S2, according to the target and requirement, selecting several suitable requirement models from the design model library, matching to a suitable large model according to the matching principle, constructing an industrial mother machine structure digital prototype model, an industrial mother machine electrical digital prototype model, an industrial mother machine hydraulic digital prototype model and / or an industrial mother machine process digital prototype model;

[0011] S3, adjusting and optimizing the constructed digital prototype model in combination with the experience of engineers, to obtain an industrial mother machine digital prototype model meeting the requirements.

[0012] The requirement model in the application is a model constructed for the target requirement.

[0013] In addition, the MBSE-based industrial mother machine digital prototype collaborative design method according to the application can also have the following additional technical features:

[0014] In some embodiments, the step of constructing a design model library of an industrial mother machine digital prototype in step S1 comprises:

[0015] Determining the target and requirement: clearly defining the specific target and requirement of different kinds of industrial mother machine digital prototype design, including the function, precision and applicable range of the model;

[0016] Data collection and cleaning: collecting relevant historical data from multiple sources, and cleaning the collected data to remove invalid, erroneous or redundant information;

[0017] Feature engineering: extracting useful feature data for model establishment from the cleaned data, and preprocessing the feature data to improve the training efficiency and performance of the model;

[0018] Model selection and training: selecting a suitable model architecture according to the specific requirement, training each model using the processed feature data, and obtaining each type of model by continuously adjusting the parameters and structure of the model;

[0019] Model verification and optimization: using a preset verification data set to evaluate the trained model, and then optimizing the model according to the evaluation result to obtain an optimized model of each type;

[0020] Modular construction: modularizing the optimized models of each type to form a model library containing different types of industrial mother machine digital prototype design models.

[0021] In some embodiments, the industrial mother machine structure digital prototype model comprises a multi-level part model, a mechanism model, an assembly model, a contact model and a multi-body dynamics model.

[0022] In some embodiments, when the part model is constructed, according to the existing design parameters and target indicators, a suitable large model is matched according to the matching principle to generate an initial part model, and the initial part model is optimized and adjusted in combination with the experience of engineers to obtain a part model meeting the requirements.

[0023] When the mechanism model is constructed, according to the connection and motion relationship of the industrial mother machine, a suitable large model is matched according to the matching principle to generate an initial mechanism model; the initial mechanism model is optimized and adjusted in combination with the experience of engineers to obtain a mechanism model meeting the requirements.

[0024] When the assembly model is constructed, according to the constructed part model and mechanism model, a suitable large model is matched according to the matching principle to obtain an initial assembly model, and the initial assembly model is adjusted and optimized in combination with the experience of engineers to obtain a final assembly model.

[0025] When the contact model is constructed, according to the constructed part model and assembly model, and based on the geometric features of the parts and the collision detection algorithm, a suitable large model is matched according to the matching principle to generate an initial contact model, and the initial contact model is adjusted and optimized in combination with the experience of engineers to obtain a contact model capable of reflecting the contact relationship between the parts.

[0026] When the multi-body dynamics model is constructed, according to the constructed part model, mechanism model and assembly model, a suitable large model is matched according to the matching principle to obtain an initial multi-body dynamics model; the initial multi-body dynamics model is adjusted and optimized according to the motion characteristics and force conditions to obtain a final multi-body dynamics model.

[0027] In some embodiments, the electrical digital prototype model of the industrial mother machine includes a control model, a detection model and / or a fault prediction model.

[0028] In some embodiments, when the control model is constructed, a suitable large model is matched according to the matching principle in combination with the demand parameters and targets related to electrical control to generate an initial control model; and the initial control model is adjusted and optimized in combination with the experience of engineers to obtain the required control model.

[0029] When the detection model is constructed, a suitable large model is matched according to the detection requirements and the matching principle to generate an initial detection model; and the initial detection model is further optimized and adjusted in combination with the experience of engineers to obtain the required detection model.

[0030] Fault prediction model: according to the constructed control model and detection model, a suitable large model is matched according to the matching principle to generate an initial fault prediction model, and the initial fault prediction model is further optimized and adjusted in combination with the experience of engineers to obtain the required fault prediction model.

[0031] In some embodiments, the construction of the industrial mother machine hydraulic digital mockup model includes:

[0032] According to the hydraulic control requirements described in the demand model, an initial hydraulic control model is generated by matching appropriate large models according to the matching principle, and the initial hydraulic control model is further optimized and adjusted in combination with the experience of engineers to ensure that the hydraulic control model meets the requirements in the demand model, and the final hydraulic control model is obtained.

[0033] In some embodiments, the construction of the industrial mother machine process digital mockup model includes:

[0034] According to the obtained process demand model, an initial industrial mother machine process digital mockup model is generated by matching appropriate large models according to the matching principle, and the initial industrial mother machine process digital mockup model is further adjusted and optimized in combination with the experience of engineers to obtain the final industrial mother machine process digital mockup model.

[0035] In some embodiments, the relevant historical data includes design drawings, performance parameters and use records of the industrial mother machine;

[0036] The feature data includes the geometry, material properties and assembly relationship of the parts;

[0037] The preprocessing of the feature data includes normalization processing and standardization processing;

[0038] According to the evaluation results, the model is optimized, including adjusting the model parameters and / or improving the model structure.

[0039] The embodiment of the application also provides an industrial mother machine digital mockup collaborative design device based on MBSE, including a processor and a memory, the memory stores a software program, and the processor can realize the content of the industrial mother machine digital mockup collaborative design method based on MBSE as described in any one of the above when running the software program.

[0040] Additional aspects and advantages of the application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 The MBSE-based industrial mother machine digital mockup collaborative design method block diagram disclosed for an embodiment of the application. DETAILED DESCRIPTION

[0042] With reference to the drawings and in connection with the embodiments of the application, the technical solutions in the embodiments of the application will be described clearly and completely. Obviously, the described embodiments are some of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the application.

[0043] The embodiments of the application will be described in detail below with reference to the drawings and specific embodiments and application scenarios.

[0044] Please refer to Figure 1 As shown in the drawings, in some embodiments of the application, an MBSE-based industrial mother machine digital prototype collaborative design method is provided. First, according to the industrial mother machine design requirements classification, the classification includes additive manufacturing, equal material manufacturing and subtractive manufacturing, and each type of manufacturing corresponds to a number of requirement models.

[0045] According to the requirement model, the modular construction of the industrial mother machine structure digital prototype is carried out, including multi-level part models, mechanism models, assembly models, contact models and multi-body dynamics models.

[0046] According to the requirement model, the modular construction of the industrial mother machine electrical digital prototype is carried out, including control models, detection models and fault prediction models.

[0047] According to the requirement model, the modular construction of the industrial mother machine hydraulic digital prototype is carried out.

[0048] According to the requirement model, the modular construction of the industrial mother machine process digital prototype is carried out. The modular construction of the industrial mother machine process digital prototype is carried out by using the typical process model library data to match the requirement model, including the same type of industrial mother machine process parameter model.

[0049] The establishment process of the requirement model includes:

[0050] First, the model target and function definition are clarified.

[0051] Second step, data collection and preparation. Collect design-related data: Collect a large number of demand description samples from different customers about sand mold 3D printing equipment, covering various size ranges, precision requirements, structural characteristics, and processing time requirements. At the same time, manually annotate these demand descriptions to clearly identify the various design parameters they contain for training the demand analysis module. Design model data: Organize various design models related to sand mold 3D printing equipment, record the function, applicable scenario, input parameter and output result of each design model, and build a design model library. Digital prototype data: Collect existing sand mold 3D printing equipment digital prototype cases and complete data for learning and reference in the automatic design and modeling process. Data preprocessing, including demand data cleaning and design model data organization.

[0052] Third step, model architecture design. Pre-training language model fine-tuning: Based on pre-trained language models such as BERT and GPT, fine-tune the collected demand sample data. Through the design of appropriate downstream tasks such as named entity recognition (NER), identify key entities such as size, precision, structure, and time in demand descriptions; use existing text classification techniques to classify demand types to better match design models. Post-processing and parameter extraction: Post-process the results output by the pre-trained language model, and convert the recognized entities into the accurate design parameter format required by the design model. For example, convert the size values described in the text into specific length, width, and height values with units. Model matching and parameter determination module: Build a design model knowledge base: Organize the design model data into a knowledge base, which can be stored in the form of a knowledge graph for quick query and retrieval. The nodes in the knowledge graph represent design models and their related attributes, and the edges represent the relationships and applicable conditions between models. Matching algorithm design: Design a matching algorithm based on rules and machine learning. According to the design parameters extracted by the demand analysis module, first use rule matching to filter out design models that meet the basic conditions. Then, through machine learning algorithms (such as decision trees, support vector machines, etc.), further sort and select the filtered models to determine the most matched design model. At the same time, extract the input parameters required by each matching model from the knowledge base.

[0053] Fourth step, model training and optimization. Including dividing data sets, setting training targets and optimization algorithms, model evaluation and improvement.

[0054] Step 5: Model deployment and maintenance. Deploy the trained requirement model to the actual business system, develop corresponding interfaces and user interfaces to facilitate user input of requirement information, and obtain the model output design scheme and digital mockup model. With the development of technology and changes in customer needs, new requirement sample data, design model data, and digital mockup data are continuously collected. Regularly retrain and optimize the model to ensure that the model can adapt to new requirements and design requirements in a timely manner. At the same time, establish a model monitoring mechanism to monitor the running state and performance indicators of the model in real time, and timely discover and solve problems that occur during model operation.

[0055] The model construction process is as follows:

[0056] I. Establishing an industrial mother machine digital mockup design model library:

[0057] Determine the specific goals and requirements of different types of industrial mother machine digital mockup design model libraries, including model functions, precision, and applicable scope.

[0058] Data collection and cleaning: Collect relevant historical data from multiple sources, such as industrial mother machine design drawings, performance parameters, and usage records. Clean the collected data to remove invalid, erroneous, or redundant information, ensuring data accuracy and consistency.

[0059] Feature engineering: Extract useful feature data from cleaned data, such as part geometry, material properties, and assembly relationships. Preprocess feature data, such as normalization and standardization, to improve model training efficiency and performance.

[0060] Model selection and training: Select an appropriate model architecture based on specific requirements. Train the model using historical data, and continuously adjust model parameters and structures to accurately describe and predict industrial mother machine performance and behavior.

[0061] Model verification and optimization: Evaluate the trained model using a validation dataset to check its accuracy and reliability. Optimize the model based on evaluation results, such as adjusting parameters and improving model structure, to improve model performance.

[0062] Modular construction: Modularize the trained model to form different types of industrial mother machine digital mockup design model libraries. The model library includes all Figure 1 The model library contains different types of industrial mother machine digital mockup design models.

[0063] The industrial machine digital prototype design can be customized by using the industrial machine digital prototype design model library, combining and configuring the modules in the model library according to the requirements, and further optimizing and adjusting the responsible modules by professional engineers to generate a customized model, and finally generating the required industrial machine digital prototype.

[0064] II. Description and introduction of each model construction process:

[0065] 1. The modular construction process of the foregoing industrial machine structure digital prototype is as follows:

[0066] Multi-level part model: according to the matching principle, it is matched to the appropriate large model and called, and according to the existing design parameters and target indicators, a new part design scheme is generated. The designer can optimize and adjust the generated design scheme to finally obtain a part model that meets the requirements. Since there are many types of industrial parts and components, the matching principles of each part and component are different, and the present application does not make specific limitations, and the matching principles of specific parts and components can refer to existing technologies. When matching according to the matching principle, existing matching models that incorporate the matching principle can be used to achieve it, such as matching models based on artificial intelligence technology, which are not limited by the present application.

[0067] The digital prototype design of the industrial machine is related to the safety and reliability of the product in actual use, and any design defects may cause serious consequences. Designers or engineers need to review the generated design scheme from the ethical and safety perspectives. And although the matching model can handle a large amount of data, it is not as good as the professional knowledge and experience accumulated by human engineers in long-term practice in the early stage of design model use and self-learning, or even for a long time. For example, in the design of a sand 3D printing device, for the strength requirements of the sand mold under different casting processes, the demolding feasibility of complex structures, etc., engineers can intuitively judge the rationality of the matching model generated scheme based on past project experience. For example, for high-precision castings such as aircraft engine blades, engineers know that additional support structure design is needed at certain key points to ensure that the sand mold does not deform due to high temperature and metal liquid impact during the casting process, which is difficult for the matching model to automatically generate based on data alone. Adjustment and optimization based on engineer experience can be done from several angles such as functional integrity, safety, compatibility, performance, cost, and simulation verification. The following several other modular construction processes of industrial machine digital prototypes also have similar adjustments and optimizations.

[0068] The following is an example of a commonly used structure-transmission system of an industrial machine, which introduces the process of multi-level part model construction. The transmission system is the core component of the industrial machine, responsible for transmitting power from the motor to the machining system to achieve workpiece machining. The design steps of the present application include:

[0069] Step 1: Define the requirements of the transmission system

[0070] Firstly, a requirement model of the transmission system needs to be established, including parameters such as transmission efficiency, power, speed, and working environment. These requirements will directly affect the design parameters and material selection of the part model.

[0071] Step 2: Large model selection and application

[0072] Select large models: According to the requirements of the transmission system, select large models with strong computing power and high precision, such as deep learning models. These models should have the ability to handle complex geometric shapes, physical properties, and interaction relationships.

[0073] Data preparation: Collect data related to the transmission system, including the size, shape, material properties, and working conditions of the parts. These data will be used to train the large model and generate the part model.

[0074] Model training and optimization: Use the collected data to train the large model, and evaluate and optimize the model through cross-validation, performance index evaluation, and other methods. Ensure that the model can accurately reflect the characteristics and behavior of the transmission system. Store the trained model in the digital prototype model library

[0075] Step 3: Multi-level part model construction

[0076] Part level division: According to the requirement model, divide the parts into different levels. For example, it can be divided into base, transmission rod, transmission rod, gear, motor, etc.

[0077] Part model generation: Use the large model to generate the part model of each level. For complex parts, it can be further divided into smaller sub-parts and generate models respectively.

[0078] Model integration and optimization: Integrate the generated part models to form a complete transmission system model. During the integration process, attention should be paid to the coordination between parts, dimensional accuracy, and consistency of physical properties. Designers can choose the optimal model based on experience, and then use the optimization capabilities of the large model to optimize the overall model parameters and perform simulation tests to improve the performance and reliability of the transmission system.

[0079] Mechanism model: According to the connection and motion relationship of the industrial mother machine, use artificial intelligence matching model to generate the initial design of the mechanism model. Engineers can further optimize and adjust the design scheme generated by the model to ensure that the mechanism model meets the requirements of the requirement model.

[0080] Assembly model: Based on the part model and mechanism model generated by the artificial intelligence matching model, automatically generate an initial assembly model. Engineers can further adjust and optimize the assembly model to ensure the correct assembly of each part.

[0081] Contact model: Generate the contact relationship model between parts automatically according to the part model and assembly model generated by the artificial intelligence matching model. This can be achieved by learning the geometric features of the parts and the collision detection algorithm to ensure the correctness of the contact between the parts during the movement process.

[0082] Multi-body dynamics model: Use the existing part model, mechanism model and assembly model to generate the initial multi-body dynamics model. Engineers can further adjust and optimize the motion characteristics and force conditions generated by the model to ensure the accuracy and reliability of the model. Multi-body dynamics model realizes the virtual assembly of parts, which can be used to analyze the characteristics, state and specific parameter values of each part during the force process and movement process, to design the actual prototype.

[0083] 2、The modular construction process of the aforementioned industrial mother machine electrical digital prototype is as follows:

[0084] Control model: Use the corresponding artificial intelligence matching model to generate the initial control model design scheme according to the demand parameters and targets related to electrical control. Engineers can adjust and optimize the design scheme generated by the model to ensure that the control requirements in the demand model are met. Taking the sand type 3D printing equipment as an example, briefly introduce how engineers adjust and optimize, engineers can optimize and adjust from six aspects:

[0085] 1) Functional integrity: On the one hand, carefully check the demand model, if the requirements such as the nozzle moving speed needs to be adjusted in real time according to the sand mold part, etc. The scheme lacks the corresponding control logic, which needs to be supplemented and improved. On the other hand, remove redundant functions such as special fault alarms that rarely occur and do not affect the main function. 2) Performance optimization: In terms of response speed, investigate signal transmission paths, controller operation speed, etc. Bottlenecks such as upgrading low-bandwidth data transmission buses or optimizing protocols. In terms of stability, evaluate electrical component selection, circuit layout, such as replacing unstable power supply modules, adding voltage filtering circuits, and proper cable layout and shielding to enhance anti-interference capability. 3) Compatibility: In terms of hardware compatibility, ensure that the electrical control scheme matches the mechanical structure, sensor, etc. Hardware interface and electrical parameters, design signal conversion circuit. At the same time, consider future expansion requirements such as adding nozzle types or improving precision, and reserve interfaces and control resources. 4) Cost control: Perform cost-benefit analysis on electrical component selection, replace expensive models with functionally similar and reasonably priced controllers, and simplify complex circuit design to reduce unnecessary use of relays and contactors. 5) Safety optimization: In terms of electrical safety protection, improve leakage, overcurrent, and short-circuit protection, such as adding a leakage protection switch. In terms of operation safety design, properly position and set the emergency stop button, and set up warnings and confirmation links for dangerous operations. 6) Simulation verification: First, simulate the device running under different working conditions using simulation software to check the control logic and performance indicators. Then test on the actual device, collect current, voltage, etc. Data, adjust the scheme according to the results to ensure that the control requirements are met.

[0086] Detection model: According to the detection requirements of the industrial mother machine described in the demand model, use the corresponding artificial intelligence matching model to generate the initial design of the detection model. Engineers can further optimize and adjust the design scheme generated by the model to ensure that the detection model meets the requirements in the demand model.

[0087] The construction process of the detection model includes:

[0088] Step 1, detection requirements

[0089] Industrial mother machines are core equipment in intelligent manufacturing, and their performance and quality have a significant impact on production efficiency and product quality. Therefore, the detection requirements for industrial mother machines mainly include the following aspects:

[0090] Accuracy detection: Ensure that the machining accuracy of the industrial mother machine meets the design requirements, including positioning accuracy, repeat positioning accuracy, geometric accuracy, etc.

[0091] Performance detection: Evaluate the overall performance of the industrial mother machine, such as cutting speed, feed speed, spindle power, etc., to ensure that it can meet production requirements.

[0092] Fault Diagnosis: By detecting the operating status of the industrial mother machine, potential faults can be discovered and diagnosed in a timely manner to avoid production interruptions and equipment damage.

[0093] Safety Detection: Ensure that the safety protection devices of the industrial mother machine are intact and effective to prevent operators from being injured during production.

[0094] Step 2, Detect relevant parameters

[0095] To meet the detection needs, a series of parameters need to be set to evaluate the performance and quality of the industrial mother machine. Here are some key parameters:

[0096] Precision parameters:

[0097] Positioning accuracy: Measures the accuracy of positioning during the machining process of the industrial mother machine.

[0098] Repeat positioning accuracy: Evaluates the consistency of the industrial mother machine in multiple positioning.

[0099] Geometric accuracy: Reflects the relative position and shape accuracy between the components of the industrial mother machine.

[0100] Performance parameters:

[0101] Cutting speed: The speed of the industrial mother machine during cutting.

[0102] Feed speed: The speed of the industrial mother machine during machining.

[0103] Spindle power: The output power of the spindle motor, reflecting the cutting ability of the industrial mother machine.

[0104] Fault diagnosis parameters:

[0105] Vibration signal: By detecting the vibration signal of the industrial mother machine, analyze the running state of the equipment.

[0106] Temperature signal: Monitor the temperature changes of the components of the industrial mother machine, and discover abnormal situations in a timely manner.

[0107] Noise signal: Analyze the noise during the operation of the industrial mother machine to determine whether the equipment has faults.

[0108] Safety parameters:

[0109] Integrity of safety protection devices: Check whether the safety protection devices are complete and effective.

[0110] Reliability of emergency stop button: Ensure that the emergency stop button can quickly stop the operation of the equipment in emergency situations.

[0111] Step 3, Large model application

[0112] Based on the above detection requirements and parameters, a detection model for the industrial mother machine can be constructed. The model construction process is as follows:

[0113] Data collection and preprocessing:

[0114] Collect historical data of the industrial mother machine, including precision detection data, performance detection data, fault diagnosis data, and safety detection data, etc. Preprocess the data, including data cleaning, data conversion, and data standardization, etc., to improve the quality and usability of the data.

[0115] Feature extraction and selection:

[0116] Extract features related to detection requirements from raw data, such as precision features, performance features, fault diagnosis features, and safety features, etc. Use feature selection algorithms to filter out key features that have a greater impact on detection results, to improve the accuracy and efficiency of the model.

[0117] Model training and optimization:

[0118] Select appropriate artificial intelligence algorithms, such as deep learning, machine learning, etc., use preprocessed data and key features for model training, adjust model parameters to optimize performance. Use cross-validation, performance index evaluation, etc. to evaluate and optimize the model, to ensure that the model can accurately reflect the characteristics and behavior of the industrial mother machine.

[0119] Write the trained model into the industrial mother machine digital prototype model library.

[0120] Step 4, detection model construction

[0121] Generate an initial design of the detection model that meets the requirements based on the demand model and model library. Engineers can further optimize and adjust the design scheme generated by the model. For example:

[0122] Adjust feature weights: adjust the weights of each feature according to actual requirements to improve the accuracy and sensitivity of the model;

[0123] Optimize algorithm parameters: adjust algorithm parameters such as learning rate, iteration times, etc. to further optimize the performance of the model;

[0124] Introduce new features: introduce new features according to new detection requirements and technological development to expand the application range and detection capability of the model.

[0125] Fault prediction model: use the built control model and detection model to generate an initial fault prediction model. Engineers can further optimize and adjust the fault prediction algorithm generated by the model based on their experience to improve the accuracy and reliability of fault prediction.

[0126] 3. The modular construction process of the aforementioned industrial machine hydraulic digital prototype is as follows:

[0127] According to the hydraulic control requirements described in the demand model, the appropriate large model is matched by using the corresponding artificial intelligence matching model to generate the initial design of the hydraulic control model. Engineers can further optimize and adjust the design scheme generated by the model according to previous experience to ensure that the hydraulic control model meets the requirements in the demand model.

[0128] 4. The modular construction process of the aforementioned industrial machine process digital prototype is as follows:

[0129] According to the process parameters and process characteristics, select the appropriate process type demand model from the model library, and further adjust and optimize the model according to the experience of engineers to obtain the final process demand model; according to the obtained process demand model, use the corresponding artificial intelligence matching model to match the appropriate large model to generate the initial industrial machine process digital prototype model, and further adjust and optimize the initial industrial machine process digital prototype model according to the experience of engineers to obtain the final process demand model.

[0130] After completing the model construction, the industrial machine digital prototype can be simulated, including the simulation of the industrial machine structure digital prototype, the industrial machine electrical digital prototype, the industrial machine hydraulic digital prototype, and the industrial machine process digital prototype. Among them, when simulating the industrial machine structure digital prototype, the industrial machine structure digital prototype is solved for statics, kinematics and dynamics, kinematics and dynamics analysis is performed, and according to specific requirements, modal analysis, fatigue analysis, thermodynamic analysis and other mechanical analysis can also be performed. These analyses together constitute the basis for comprehensive evaluation and optimal design of the performance of the industrial machine structure. Virtual assembly and analysis of the industrial machine structure digital prototype, including assembly modeling, tolerance analysis, mechanism motion analysis, to find problems in assembly design.

[0131] In some embodiments of the present application, physical field analysis and visualization of the working process of the industrial machine can also be performed, including analysis object visualization, temperature field numerical simulation, and defect prediction of processed products. The physical model in the application process of the industrial machine is described and analyzed in a visual manner, and the relationship between various parameters of the industrial machine and its physical properties and physical properties is dynamically displayed. Analysis of these physical fields can help to deeply understand the working principle and performance characteristics of the industrial machine, help engineers to understand the changes of product characteristics in the actual working process, increase the controllability and predictability of the product manufacturing and use process, and understand and optimize the performance of the industrial machine.

[0132] In some embodiments of the present application, during the simulation of the industrial mother machine electrical digital prototype, including electrical comprehensive system simulation, power supply system simulation; through the digital prototype-based electrical system design simulation integration technology, the effectiveness of the electrical system design scheme is verified, the industrial mother machine development cycle is shortened, the cost is reduced, and the design accuracy and reliability of the industrial mother machine are improved.

[0133] The content of the industrial mother machine electrical digital prototype collaborative design includes: digital prototype model modular design, using multi-field parallel and collaborative design, and collaborative simulation, joint simulation analysis of different personnel / tools on the same product at the system level. According to the characteristics and process of industrial mother machine design, each tool module is customized and developed.

[0134] During the digital prototype design process of the industrial mother machine, engineers from different fields need to work closely together to complete the task. Through the sharing function provided by the platform, engineers from different fields can easily access, modify and generate models. This allows them to design and simulate on the same basis, avoiding duplication of effort and waste of resources. That is, collaboration is reflected in the fact that multi-field personnel can collaborate on the unified platform to complete the entire industrial mother machine digital prototype design. The platform can centralize multiple simulation tools, and engineers from different fields can perform collaborative design and simulation. They can communicate and discuss in real time through the communication tools provided by the platform, and work together to solve problems encountered during the design process. At the same time, the platform also supports multi-field parallel simulation analysis, allowing engineers to more comprehensively understand the performance and behavior characteristics of the industrial mother machine digital prototype.

[0135] After the digital prototype design of the industrial mother machine is completed, the digital prototype of the industrial mother machine can be optimized and adjusted: during the design and simulation process, engineers from different fields need to adjust and optimize the model according to the simulation results and optimization suggestions, and can perform parameter adjustment, model modification, etc. through the optimization tools provided by the platform to improve the performance and reliability of the digital prototype.

[0136] After optimization and adjustment are completed, the digital prototype of the industrial mother machine can also be regularly reviewed and feedback: in order to ensure the smooth progress of the design process and the quality of the design results, regular review and feedback are needed. Engineers from different fields can jointly participate in the review meeting, evaluate and discuss the design results, and put forward improvement suggestions and recommendations. This ensures that problems in the design process are discovered and solved in a timely manner.

[0137] The platform and the digital prototype design model library of the industrial mother machine are closely related and interact with each other. The platform provides storage, management, integration, collaboration, optimization and sharing functions to support the model library; and engineers from different fields work closely together through the platform to complete the digital prototype design task of the industrial mother machine.

[0138] The parts of the present application not described in detail can refer to the prior art or be known to those skilled in the art, and the present application will not be described in more detail.

[0139] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the specific embodiments described above, which are merely illustrative rather than restrictive, and those of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, which all belong to the protection of the present application.

Claims

1. A collaborative design method for digital prototype of industrial mother machine based on MBSE, characterized by: The method comprises: S1. Build a design model library for the digital prototype of an industrial machine; the design model library contains several different types of demand models and several large models for various aspects of the digital prototype; S2. Based on the objectives and requirements, select several appropriate demand models from the design model library, use artificial intelligence technology to call the corresponding matched large models, and build a digital prototype model of the industrial mother machine structure, an industrial mother machine electrical digital prototype model, an industrial mother machine hydraulic digital prototype model, and an industrial mother machine process digital prototype model; S3. Adjust and optimize the constructed digital prototype model. Designers or engineers review the generated design plan from the perspective of ethics and safety. Based on the engineers' experience, adjustments and optimizations are made from the perspectives of functional integrity, safety, compatibility, performance, cost, and simulation verification to obtain a digital prototype model of the industrial mother machine that meets the accuracy requirements. The industrial machine structure digital prototype model includes a multi-level parts model, a mechanism model, an assembly model, a contact model and a multi-body dynamics model; When constructing the part model, according to the existing design parameters and target indicators, artificial intelligence technology is used to match the appropriate large model to generate an initial part model. The initial part model is optimized and adjusted based on the engineer's experience to obtain a part model that meets the requirements; When constructing the mechanism model, artificial intelligence technology is used to match a suitable large model based on the connection and motion relationship of the industrial mother machine to generate an initial mechanism model; the initial mechanism model is optimized and adjusted based on the experience of engineers to obtain a mechanism model that meets the requirements; When constructing the assembly model, artificial intelligence technology is used to match the appropriate large model based on the constructed part model and mechanism model to obtain an initial assembly model, and the initial assembly model is adjusted and optimized based on the experience of engineers to obtain the final assembly model; When constructing the contact model, based on the constructed part model and assembly model, and based on the part geometric features and collision detection algorithm, artificial intelligence technology is used to match the appropriate large model to generate an initial contact model. The initial contact model is adjusted and optimized based on the engineer's experience to obtain a contact model that can reflect the contact relationship between the parts; When constructing the multi-body dynamics model, an initial multi-body dynamics model is obtained by matching a suitable large model with the constructed part model, mechanism model, and assembly model using artificial intelligence technology; the initial multi-body dynamics model is adjusted and optimized according to the motion characteristics and force conditions to obtain the final multi-body dynamics model; The electrical digital prototype model of the industrial mother machine includes a control model, a detection model and / or a fault prediction model; When constructing the control model, artificial intelligence technology is used, combined with the required parameters and goals related to electrical control, to match the appropriate large model to generate an initial control model; then, based on the engineer's experience, the initial control model is adjusted and optimized to obtain the desired control model; When constructing the detection model, artificial intelligence technology is used to match a suitable large model according to the detection requirements to generate an initial detection model; the initial detection model is further optimized and adjusted based on the experience of engineers to obtain the required detection model; Fault prediction model: Based on the established control model and detection model, AI technology is used to match the appropriate large model to generate an initial fault prediction model. This model is then further optimized and adjusted based on the engineers' experience to obtain the desired fault prediction model. The construction content of the industrial machine hydraulic digital prototype model includes: According to the hydraulic control requirements described in the demand model, artificial intelligence technology is used to match the appropriate large model to generate an initial hydraulic control model. The initial hydraulic control model is then further optimized and adjusted based on the engineers' experience to ensure that the hydraulic control model meets the requirements of the demand model and obtain the final hydraulic control model. The construction content of the industrial mother machine process digital prototype model includes: According to the process parameters and process characteristics, select the appropriate process type demand model from the model library, and then further adjust and optimize the model based on the engineer's experience to obtain the final process demand model; Based on the obtained process requirement model, artificial intelligence technology is used to match the appropriate large model to generate the initial industrial mother machine process digital prototype model. Then, combined with the engineer's experience, the initial industrial mother machine process digital prototype model is further adjusted and optimized to obtain the final process requirement model.

2. The MBSE-based collaborative design method for industrial machine tool digital prototypes according to claim 1 is characterized in that: The steps of constructing the design model library of the industrial mother machine digital prototype in step S1 include: Determine goals and requirements: Identify specific goals and requirements for digital prototype design of different types of industrial machine tools, including the model's function, accuracy, and scope of application; Data collection and cleaning: Collect relevant historical data from multiple sources and clean the collected data to remove invalid, erroneous or redundant information; Feature engineering: Extracting useful feature data for model building from cleaned data and preprocessing the feature data to improve model training efficiency and performance; Model selection and training: Select the appropriate model architecture based on specific needs, use the processed feature data to train the respective models, and obtain various types of models by continuously adjusting the model parameters and structure; Model validation and optimization: Use the preset validation data set to evaluate the trained model, and then optimize the model based on the evaluation results to obtain optimized models of various types; Modular construction: The optimized models of various types are modularly constructed to form a model library containing digital prototype design models of different types of industrial mother machines.

3. The MBSE-based collaborative design method for industrial machine tool digital prototypes according to claim 1 is characterized in that: Relevant historical data includes the design drawings, performance parameters and usage records of industrial mother machines; The characteristic data includes the geometric shape, material properties and assembly relationship of the parts; The preprocessing of feature data includes normalization and standardization; Optimizing the model based on the evaluation results includes adjusting model parameters and / or improving the model structure.

4. A collaborative design device for digital prototypes of industrial mother machines based on MBSE, comprising a processor and a memory, wherein a software program is stored in the memory, characterized in that: When the processor runs the software program, it can implement the content of the MBSE-based industrial mother machine digital prototype collaborative design method as described in any one of claims 1 to 3.

Images