Intelligent generation method and system for mold surface of glass mold

Abstract

The invention relates to the technical field of mold surface generation, in particular to an intelligent mold surface generation method and system for a glass mold. The method comprises the following steps: acquiring three-dimensional scanning data of a glass mold, and carrying out geometric digitalization on the three-dimensional mold to obtain a three-dimensional structure model of the glass mold; historical manufacturing data of the glass mold are obtained, mold design demand analysis is carried out, and a mold design demand parameter set is obtained; performing mold physical working condition simulation on the glass mold three-dimensional structure model according to the mold design demand parameter set to obtain glass mold physical simulation data; performing three-dimensional mold surface conversion on the optimized glass mold three-dimensional structure model based on the glass mold physical simulation data so as to obtain mold surface data of the to-be-manufactured glass mold; and obtaining glass mold manufacturing multi-dimensional data, and carrying out process scheduling optimization according to the glass mold manufacturing multi-dimensional data so as to obtain mold manufacturing process optimization scheduling data. The efficiency and accuracy of the mold manufacturing process can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mold surface generation, and in particular to a mold surface intelligent generation method and system for a glass mold. Background Art

[0002] In modern manufacturing, glass molds, as key manufacturing tools, are widely used in the field of glass deep processing, especially in the molding process of glass products. With the development of technology, the types and complexity of glass products are constantly increasing, and traditional mold design methods can no longer meet the growing manufacturing needs. The traditional glass mold surface design method mainly relies on manual experience and traditional CAD (computer-aided design) technology. Usually, mold designers manually draw two-dimensional drawings of molds according to manufacturing requirements and historical data, and then make molds through CNC processing and other means. Although this method met the manufacturing requirements of simple glass products in the early stage, as the complexity of products increased, the defects of traditional design methods gradually emerged. Traditional design methods usually require a lot of manual intervention, which not only has a long design cycle, but also the experience of designers directly affects the accuracy and quality of the final mold. Especially when designing glass molds with complex shapes or requiring extremely high precision, manual operation is very likely to produce errors, resulting in the mold being unable to meet actual manufacturing needs after it is manufactured. This error may cause quality problems in batch manufacturing, and even lead to product abandonment or manufacturing stagnation. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for intelligently generating a mold surface for a glass mold to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above object, a method for intelligently generating a mold surface for a glass mold comprises the following steps:

[0005] Step S1: Acquire three-dimensional scanning data of a glass mold, and perform glass surface microstructure recognition on the three-dimensional scanning data of the glass mold, thereby obtaining microstructure data of the glass mold; perform three-dimensional mold geometry digitization based on the microstructure data of the glass mold, thereby obtaining a three-dimensional structural model of the glass mold;

[0006] Step S2: acquiring historical manufacturing data of glass molds, and performing mold performance requirement identification on the historical manufacturing data of glass molds, thereby obtaining historical mold performance requirement data; performing mold design requirement analysis on the historical mold performance requirement data, thereby obtaining a mold design requirement parameter set;

[0007] Step S3: optimizing the shape structure of the glass mold three-dimensional structure model according to the mold design requirement parameter set, thereby obtaining an optimized glass mold three-dimensional structure model; simulating the physical working condition of the optimized glass mold three-dimensional structure model according to the historical mold performance requirement data, thereby obtaining glass mold physical simulation data;

[0008] Step S4: Based on the physical simulation data of the glass mold, the optimized three-dimensional structure model of the glass mold is optimized for high-temperature molding dynamic mold structure, so as to obtain a high-temperature structure optimized glass mold model; the high-temperature structure optimized glass mold model is converted into a three-dimensional mold surface, so as to obtain mold surface data of the glass mold to be manufactured, and the mold surface data is uploaded to the glass mold manufacturing management platform to execute the mold manufacturing task;

[0009] Step S5: Acquire glass mold manufacturing multidimensional data, and perform manufacturing mold process adaptability evaluation based on the glass mold manufacturing multidimensional data, so as to obtain manufacturing mold process adaptability data; perform process scheduling optimization based on the manufacturing mold process adaptability data, so as to obtain manufacturing mold process optimization scheduling data, and upload it to the glass mold manufacturing management platform to execute the process scheduling task.

[0010] The present invention can accurately restore the surface details of the mold by acquiring the three-dimensional scanning data of the glass mold and performing microstructure identification, eliminating the errors caused by manual drawing in the traditional design method. The acquisition of this microstructure data provides a basis for the subsequent mold geometry digitization, making the mold design more accurate, and can reflect the microscopic characteristics of the glass mold in practical applications, thereby providing data support for mold optimization. Then, the construction of the three-dimensional structure model based on these data can more realistically reflect the geometric shape of the mold, and is not limited by manual operation and experience, thereby avoiding the common geometric errors in the traditional method. Through the integration of historical manufacturing data, it can help identify the performance requirements of the mold and provide a clear direction for further design. Combining historical performance requirements with design requirements analysis, the key parameters of the mold design can be accurately extracted to ensure that the mold design not only meets the production requirements, but also meets the high-precision requirements in actual manufacturing. Using these design requirement parameters to optimize the three-dimensional structure model can further improve the shape and function of the mold, making it more adaptable to complex manufacturing requirements. At the same time, the introduction of physical simulation data, especially the simulation on the three-dimensional structure model after the mold is optimized, can accurately simulate the performance of the mold in the high-temperature molding process, and provide a theoretical basis for the adjustment and improvement of the mold design. Through the optimization of dynamic mold structure of high temperature molding, the stability and durability of the mold under extreme working conditions can be improved, the failure rate in the production process can be reduced, and the service life of the mold can be ensured. The mold surface data generated by the three-dimensional mold surface conversion after the high temperature structure optimization can directly provide accurate processing data for the mold manufacturing, avoiding the error of manual adjustment and improving the processing accuracy. After uploading these mold surface data to the manufacturing management platform, the smooth execution of mold manufacturing tasks and the real-time update of data are ensured, which further improves the automation level of production management and avoids the uncertainty caused by human intervention. Finally, by obtaining multi-dimensional data of glass mold manufacturing and conducting process adaptability evaluation, we can better understand the adaptation of mold performance and process in the actual manufacturing process and identify possible process problems in advance. This evaluation provides data support for process scheduling optimization, making the mold manufacturing process more efficient and accurate, and can timely adjust the production plan according to the evaluation data, optimize resource allocation, thereby improving production efficiency and reducing production costs. The process scheduling optimization data uploaded to the manufacturing management platform provides precise guidance for the execution of subsequent production tasks, further enhancing the controllability and traceability of the manufacturing process.

[0011] Optionally, step S1 specifically includes:

[0012] Step S11: acquiring three-dimensional scanning data of the glass mold, and performing scanning point cloud data preprocessing on the three-dimensional scanning data of the glass mold, so as to obtain scanning point cloud data of the glass mold to be analyzed;

[0013] Step S12: performing mold surface texture analysis on the scanned point cloud data of the glass mold to be analyzed, thereby obtaining mold surface texture data;

[0014] Step S13: quantifying the microstructure characteristics of the mold surface according to the mold surface texture data, thereby obtaining the glass mold microstructure data;

[0015] Step S14: performing three-dimensional geometric modeling of the mold based on the microstructure data of the glass mold, thereby obtaining a three-dimensional geometric model of the glass mold;

[0016] Step S15: Correcting the accuracy of the three-dimensional geometric model of the glass mold to obtain a three-dimensional structural model of the glass mold.

[0017] The present invention can obtain high-precision geometric data from the actual mold and eliminate the error of artificial modeling by obtaining three-dimensional scanning data of the glass mold and performing point cloud data preprocessing. This process can ensure that the obtained data accurately reflects the actual physical shape of the mold, providing a reliable basis for subsequent analysis and modeling. By performing mold surface texture analysis on the scanned point cloud data to be analyzed, the subtle texture features of the mold surface can be extracted, which provides data support for further analysis of the mold surface performance. Surface texture analysis helps to identify possible microscopic defects or irregularities on the mold surface, providing a basis for subsequent design optimization. By quantifying the microstructure features of these texture data, the microstructure of the mold surface can be accurately described, further revealing the actual surface characteristics of the mold. By quantifying the surface texture features, quantitative data support can be provided for subsequent mold optimization and material selection, avoiding relying solely on empirical judgment, thereby improving the scientificity and accuracy of the design. The beneficial effect of this process is that the surface details and microstructure of the mold can be accurately identified and quantified, thereby promoting more accurate mold design. The three-dimensional geometric modeling based on the obtained microstructure data can digitize the physical features of the mold, so that the geometric shape of the mold can be accurately reproduced in a virtual environment. This 3D geometric model provides an important basis for subsequent structural optimization, simulation analysis and actual manufacturing. By correcting the accuracy of the 3D geometric model of the glass mold, errors that may occur during scanning or modeling can be eliminated to ensure that the final 3D structural model accurately meets actual manufacturing requirements. The corrected 3D structural model with higher accuracy can better support subsequent mold design optimization, functional simulation and actual production and processing, and improve the quality and accuracy of mold design.

[0018] Optionally, step S13 is specifically:

[0019] Step S131: extracting surface texture direction features from the mold surface texture data, thereby obtaining the mold surface texture direction data;

[0020] Step S132: performing surface texture frequency analysis according to the mold surface texture direction data, thereby obtaining surface texture periodic feature data;

[0021] Step S133: Calculating the local surface roughness of the mold surface texture data, thereby obtaining the mold surface roughness data;

[0022] Step S134: performing microscopic feature recognition of a local area of ​​the mold based on the surface texture periodic feature data and the mold surface roughness data, thereby obtaining local microscopic structure data of the mold surface;

[0023] Step S135: matching the local microstructure data of the mold surface with the local microstructure material properties of the mold surface through a preset glass material property database, thereby obtaining the local microstructure material property data of the mold surface;

[0024] Step S136: integrating the microstructure features of the glass mold surface according to the local microstructure data of the mold surface and the local microstructure material property data of the mold surface, so as to obtain the microstructure data of the glass mold.

[0025] The present invention can accurately identify the main directional features of the mold surface texture by extracting the directional features of the mold surface texture, thereby providing a clear directional basis for subsequent texture analysis and optimization. This process helps to understand the spatial layout of the mold surface texture and its possible impact on the glass molding process, ensuring that the mold has stable performance during use. The frequency analysis of the surface texture directional data can reveal the periodic characteristics of the mold surface texture, quantify the regularity of the texture, and provide support for the compatibility analysis of the mold surface and glass products. Through the identification of periodic features, it is possible to provide a quantitative basis for the optimization design of the mold surface microstructure and reduce the poor molding phenomenon caused by texture mismatch. The local roughness calculation of the mold surface texture can further quantify the roughness characteristics of the mold surface. This process helps to accurately describe the microscopic morphology of the mold surface and provide decision support for subsequent mold surface treatment. Roughness data not only helps to analyze the friction and wear resistance of the mold, but also affects the surface quality of the glass product, thereby improving the service life and molding efficiency of the mold. Local microscopic feature recognition based on periodic features and roughness data helps to identify the microstructure of the local area of ​​the mold surface and accurately grasp the performance differences of the mold in various areas. This identification process can reveal the physical properties of the mold surface in different areas, help identify possible surface defects or unevenness, and thus optimize the overall design of the mold. By matching with the preset glass material property database, it is possible to further accurately find the most suitable material properties for the local microstructure of the mold surface. The matching process of material property data provides a theoretical basis for the selection and optimization of the mold surface microstructure, ensuring that the selected material can fully meet the actual production requirements and improve the functionality and durability of the mold. By integrating the local microstructure data of the mold surface with the material property data, more comprehensive glass mold microstructure data can be obtained. This integration process not only improves the comprehensive evaluation of mold performance, but also provides a scientific basis for the optimal design and manufacturing of the mold, thereby effectively improving the quality and use of glass molds.

[0026] Optionally, step S135 is specifically:

[0027] Identify local grain structure features based on local microstructure data of the mold surface, thereby obtaining local grain structure data of the mold surface;

[0028] The thermal energy characteristics of glass raw materials are extracted through a preset glass material characteristic database, thereby obtaining thermal energy characteristic data of glass raw materials;

[0029] According to the thermal energy characteristic data of the glass raw materials, the local grain structure data on the mold surface is matched with the glass mold material characteristics, so as to obtain the glass mold matching material data;

[0030] Estimating the raw material ratio of the glass mold based on the local grain structure data of the mold surface based on the glass mold matching material data, thereby obtaining the estimated raw material ratio data of the glass mold;

[0031] The local microstructure material characteristics of the mold surface are extracted from the glass material characteristics database according to the glass mold matching material data and the glass mold raw material ratio estimation data, so as to obtain the local microstructure material characteristics data of the mold surface.

[0032] The present invention can deeply understand the grain structure of the local area of ​​the mold surface during the identification process of local grain structure characteristics, and provide strong support for optimizing the selection and processing of mold materials. Through the acquisition of grain structure data, the microscopic changes on the mold surface can be accurately revealed, and the areas that may affect the performance and service life of the mold can be identified, so as to make adjustments and improvements in the design stage. In addition, by extracting the thermal energy characteristics of glass raw materials, the characteristics of glass raw materials can be analyzed from the perspective of thermal energy, and more accurate heat treatment data can be obtained, which helps to better understand the thermal behavior of glass during the molding process, thereby providing a more comprehensive basis for mold design. Combining these thermal energy characteristics with the local grain structure data on the mold surface for material property matching, the raw materials that are compatible with the microstructure of the mold surface can be effectively selected, thereby improving the thermal stability and molding accuracy of the mold, reducing the errors generated during thermal expansion or cooling, and ensuring the quality of glass products. By estimating the raw material ratio of the matched glass mold material, a scientific and reasonable ratio can be made according to the characteristics of different raw materials, thereby optimizing the physical properties of the mold, improving the durability and adaptability of the mold, and meeting the manufacturing needs of different glass products. Ultimately, by extracting the material properties of the local microstructure of the mold surface, not only can the required materials be accurately matched, but the overall performance of the mold can also be further improved, ensuring the stability and efficiency of the mold during the production process.

[0033] Optionally, step S2 specifically includes:

[0034] Step S21: acquiring historical manufacturing data of glass molds, and performing data preprocessing on the historical manufacturing data of glass molds, thereby obtaining historical manufacturing data of glass molds to be analyzed;

[0035] Step S22: extracting mold manufacturing features from the historical manufacturing data of the glass mold to be analyzed, thereby obtaining mold manufacturing process data and mold historical performance detection data;

[0036] Step S23: performing mold historical detection performance pattern recognition on the mold historical performance detection data, thereby obtaining mold detection performance pattern data;

[0037] Step S24: performing mold performance requirement identification based on the mold detection performance mode data, thereby obtaining historical mold performance requirement data;

[0038] Step S25: Perform mold design requirement analysis based on historical mold performance requirement data and mold manufacturing process data to obtain a mold design requirement parameter set.

[0039] By acquiring and preprocessing the historical manufacturing data of glass molds, the present invention can effectively remove noise and inconsistencies in the data, thereby ensuring that subsequent analysis and decision-making are based on high-quality data. Mold manufacturing feature extraction can extract key process parameters and performance indicators from historical data, providing a scientific basis for understanding the production process and performance of the mold. By identifying the performance patterns of historical mold detection, we can have an in-depth understanding of the performance evolution process of the mold and provide a reliable reference for future mold design. Mold performance requirement identification can accurately extract the performance requirement patterns reflected in historical data, help determine the performance requirements of the mold under different working conditions, and provide clear goals for the design of a new generation of molds. Through mold design demand analysis, we can start from historical needs and combine actual process and performance requirements to form a more accurate and optimized mold design parameter set.

[0040] Optionally, step S24 is specifically:

[0041] Step S241: classifying the performance patterns according to the mold detection performance pattern data, thereby obtaining the performance pattern data of the molds that passed the detection and the performance pattern data of the molds that failed the detection;

[0042] Step S242: quantifying the performance mode errors of the qualified mold performance mode data and the unqualified mold performance mode data, thereby obtaining mold performance mode error data;

[0043] Step S243: removing the mold detection performance mode data from the mold detection performance mode data according to the mold performance mode error data, thereby obtaining the mold detection performance mode correction data;

[0044] Step S244: quantifying the performance mode error according to the mold detection performance mode correction data, thereby obtaining the mold performance mode error correction data;

[0045] Step S245: performing performance detection threshold statistics according to the mold performance mode error correction data, thereby obtaining mold performance detection threshold data;

[0046] Step S246: Identify mold performance requirements based on the mold performance detection threshold data, thereby obtaining historical mold performance requirement data.

[0047] The present invention not only improves the accuracy of mold quality detection by finely processing mold detection performance data, but also lays the foundation for subsequent mold optimization and performance requirement identification. Performance pattern classification realizes a clear distinction between qualified and unqualified molds, so that subsequent analysis can be focused on molds that meet the standards, effectively eliminating the interference of unqualified molds, thereby improving the accuracy of the analysis results. The operation of quantifying performance pattern errors helps to discover potential performance problems by accurately evaluating the performance deviations of each mold, providing data support for optimization. The elimination of extreme values ​​in the deviation distribution effectively reduces the impact of abnormal data on the analysis, ensuring that the mold performance pattern data is more reliable. Further error correction makes the mold detection data more accurate by correcting potential measurement errors or noise, thereby reducing design deviations caused by inaccurate data. The statistics of performance detection thresholds provide a clearer quantitative basis for the judgment criteria of mold performance, provide a scientific performance threshold for subsequent production, and ensure that the mold can operate within a certain performance range. Through the identification of mold performance requirements, historical data can be systematically extracted and analyzed to clarify the actual requirements of mold performance, helping designers to adjust design parameters more accurately, thereby improving mold manufacturing accuracy and production efficiency, reducing resource waste and reducing the production of defective products.

[0048] Optionally, step S25 is specifically:

[0049] Step S251: extracting mold performance characteristics from historical mold performance demand data, thereby obtaining mold performance characteristic data;

[0050] Step S252: Modeling the manufacturing process-related features based on the mold performance feature data and the mold manufacturing process data, thereby obtaining a performance requirement-manufacturing process-related model;

[0051] Step S253: acquiring real-time mold manufacturing process data, and performing manufacturing process deviation calculation on the real-time mold manufacturing process data and the mold manufacturing process data, thereby obtaining manufacturing process deviation data;

[0052] Step S254: Adaptively adjust the performance requirement-manufacturing process association model according to the manufacturing process deviation data, so as to obtain an updated performance requirement-manufacturing process association model;

[0053] Step S255: Estimating mold design requirement parameters by updating the performance requirement-manufacturing process association model, thereby obtaining an unclassified mold design requirement parameter set;

[0054] Step S256: classifying the glass mold historical manufacturing data to be analyzed by mold type to obtain manufacturing mold type data, and associating the manufacturing mold type data and the unclassified mold design requirement parameter set by mold type to obtain the mold design requirement parameter set.

[0055] The present invention optimizes the entire mold design and manufacturing process by deeply analyzing the relationship between mold performance requirements and manufacturing processes. After the mold performance characteristics are extracted, the mold performance characteristic data obtained can help to deeply understand the working performance and requirements of the mold, and provide clear guidance for subsequent design. On this basis, an association model between performance requirements and manufacturing processes is established, and accurate mapping from design requirements to process adjustments is achieved, so that the mold design is more in line with actual manufacturing requirements. Through the calculation of manufacturing process deviations, the deviations in the process can be discovered in time, and data support can be provided for updating the model, which ensures the consistency and accuracy in the design and manufacturing process. The adaptive adjustment of the model is optimized according to the real-time process deviation, ensuring the continuous effectiveness of the model, avoiding design deviations caused by process changes, and improving the flexibility of the manufacturing process. By estimating the mold design requirement parameters through the updated association model, an accurate unclassified design requirement parameter set can be generated, which provides strong data support for the next step of mold classification. Through the association of mold type classification and design requirement parameter set, it is ensured that the design requirements of each type of mold can be met in a targeted manner, thereby improving the efficiency and accuracy of the design, while reducing the probability of erroneous design.

[0056] Optionally, step S3 specifically includes:

[0057] Step S31: performing mold structure-design requirement association on the mold design requirement parameter set and the glass mold three-dimensional structure model, thereby obtaining a mold structure-design requirement association matrix;

[0058] Step S32: Based on the mold design requirement parameter set, and using the mold structure-design requirement association matrix, mold shape structure parameters are selected for the glass mold three-dimensional structure model, thereby obtaining a mold shape structure parameter set;

[0059] Step S33: performing multi-objective structural parameter optimization on the mold shape structural parameter set, thereby obtaining optimized mold shape structural parameters;

[0060] Step S34: adjusting the three-dimensional structure of the glass mold three-dimensional structure model according to the optimized mold shape structure parameters, thereby obtaining the optimized glass mold three-dimensional structure model;

[0061] Step S35: estimating the working condition of the glass mold based on the historical mold performance requirement data and the real-time mold manufacturing process data, thereby obtaining the working condition data of the glass mold;

[0062] Step S36: performing mold physical working condition simulation on the optimized glass mold three-dimensional structure model according to the glass mold working condition data, thereby obtaining glass mold physical simulation data.

[0063] The present invention provides systematic data support and precise calculation for the design and optimization of glass molds by closely combining mold design requirements with actual manufacturing processes. The construction of the mold structure-design requirement association matrix enables the mold design requirements to be directly associated with its three-dimensional structure, providing an accurate basis for the subsequent shape parameter selection. Through this matrix, it is possible to clearly identify which design requirements correspond to the specific characteristics of the mold structure, thereby achieving accurate design requirement conversion. Multi-objective structural optimization using the mold shape structure parameter set can effectively improve the performance of the mold design, such as strength, durability and other key indicators, so that the final mold design can not only meet the basic functional requirements, but also show higher stability and efficiency in the production process. The optimized mold shape structure parameters will adjust the three-dimensional structure model to ensure that the optimized design can be applied in actual operation and is highly consistent with production requirements. By combining historical mold performance requirement data and real-time process data, the working conditions of the glass mold can be accurately estimated, providing a data basis for subsequent physical simulations, and ensuring that the simulation results are true and reliable. Physical simulation of the optimized mold 3D structural model based on these working conditions can predict the performance of the mold in actual use, discover potential problems in advance, and reduce risks that may occur in the production process, thereby improving the reliability of mold design and the safety of the production process.

[0064] Optionally, step S4 is specifically:

[0065] Step S41: extracting high temperature simulation features from the physical simulation data of the glass mold, thereby obtaining high temperature simulation data of the glass mold;

[0066] Step S42: performing time series statistics of mold high temperature stress distribution on the glass mold high temperature simulation data, thereby obtaining mold dynamic high temperature stress distribution data;

[0067] Step S43: performing high-temperature forming dynamic structure thermal-mechanical coupling analysis according to the dynamic high-temperature force distribution data of the mold, thereby obtaining mold structure temperature field distribution data and mold structure stress distribution data;

[0068] Step S44: identifying the mold thermal fatigue area based on the mold structure temperature field distribution data, thereby obtaining the mold thermal fatigue area data; identifying the mold thermal stress concentration point based on the mold structure stress distribution data, thereby obtaining the mold thermal stress concentration point data;

[0069] Step S45: performing mold structure deformation risk assessment according to the mold thermal fatigue area data and the mold thermal stress concentration point data, thereby obtaining mold structure deformation risk data;

[0070] Step S46: performing high deformation risk mold structure optimization on the optimized glass mold three-dimensional structure model based on the mold structure deformation risk data, thereby obtaining a high temperature structure optimized glass mold model;

[0071] Step S47: converting the high-temperature structure optimized glass mold model into a mold surface, thereby obtaining mold surface data of the glass mold to be manufactured, and uploading the data to the glass mold manufacturing management platform to execute the mold manufacturing task.

[0072] The present invention provides a comprehensive thermal-mechanical coupling analysis by performing a detailed analysis of the high-temperature simulation data of the glass mold, and can accurately evaluate the performance of the mold under a high-temperature environment. Through high-temperature simulation feature extraction and dynamic high-temperature force distribution statistics, the force and temperature changes of the mold during use can be accurately understood, providing key data for subsequent analysis. These data are further used for the thermal-mechanical coupling analysis of the mold structure during high-temperature molding, and the temperature field and stress field distribution of the mold under the working state are obtained, and the existing thermal fatigue area and thermal stress concentration point are clarified. This analysis can identify the vulnerable points of the mold at high temperatures in advance, providing a basis for subsequent optimization. By identifying the thermal fatigue area and thermal stress concentration point of the mold, the deformation risk of the mold under a high-temperature environment can be evaluated, and the design can be further optimized to reduce possible damage or failure. The high deformation risk mold structure optimization can adjust the weaknesses of the mold under high temperature conditions, so that the structure of the mold is more adapted to the high-temperature environment and the service life of the mold is extended. The optimized mold model is converted into a mold surface and uploaded to the manufacturing management platform to ensure that the optimized mold design can be smoothly executed and applied in practice during the manufacturing process. This series of steps significantly improves the durability and reliability of the mold in actual production by comprehensively analyzing and optimizing the high-temperature performance of the mold, reduces the risk of production interruptions and equipment failures caused by high temperature, and ensures the stability and efficiency of the glass mold manufacturing process.

[0073] Optionally, the present specification also provides a mold surface intelligent generation system for a glass mold, which is used to execute the mold surface intelligent generation method for a glass mold as described above, and the mold surface intelligent generation system for a glass mold includes:

[0074] The mold microstructure recognition module is used to obtain the three-dimensional scanning data of the glass mold, and perform glass surface microstructure recognition on the three-dimensional scanning data of the glass mold, so as to obtain the microstructure data of the glass mold; the three-dimensional mold geometry is digitized based on the microstructure data of the glass mold, so as to obtain the three-dimensional structure model of the glass mold;

[0075] The mold design requirement analysis module is used to obtain the historical manufacturing data of glass molds, and identify the mold performance requirements of the historical manufacturing data of glass molds, so as to obtain the historical mold performance requirement data; perform mold design requirement analysis on the historical mold performance requirement data, so as to obtain the mold design requirement parameter set;

[0076] The mold shape structure optimization module is used to optimize the mold shape structure of the glass mold three-dimensional structure model according to the mold design requirement parameter set, so as to obtain the optimized glass mold three-dimensional structure model; the mold physical working condition simulation is performed on the optimized glass mold three-dimensional structure model according to the historical mold performance requirement data, so as to obtain the glass mold physical simulation data;

[0077] The high-temperature mold structure optimization module is used to optimize the dynamic mold structure of the high-temperature molding of the optimized glass mold three-dimensional structure model based on the physical simulation data of the glass mold, so as to obtain the high-temperature structure optimized glass mold model; perform three-dimensional mold surface conversion on the high-temperature structure optimized glass mold model, so as to obtain the mold surface data of the glass mold to be manufactured, and upload it to the glass mold manufacturing management platform to execute the mold manufacturing task;

[0078] The process adaptability evaluation module is used to obtain multi-dimensional data of glass mold manufacturing, and to evaluate the process adaptability of the manufacturing mold based on the multi-dimensional data of glass mold manufacturing, so as to obtain the process adaptability data of the manufacturing mold; to optimize the process scheduling based on the process adaptability data of the manufacturing mold, so as to obtain the manufacturing mold process optimization scheduling data, and upload it to the glass mold manufacturing management platform to execute the process scheduling task.

[0079] The intelligent mold surface generation system for glass molds of the present invention can implement any one of the intelligent mold surface generation methods for glass molds of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the intelligent mold surface generation method for glass molds. The internal modules of the system cooperate with each other to improve the efficiency and accuracy of the mold manufacturing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0081] Figure 1 It is a schematic diagram of the steps of the method for intelligently generating a mold surface for a glass mold according to the present invention;

[0082] Figure 2 Detailed step flow diagram of step S1 in the present invention;

[0083] Figure 3 Detailed step flow diagram of step S2 in the present invention;

[0084] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0085] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0086] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0087] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0088] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for intelligently generating a mold surface for a glass mold, the method comprising the following steps:

[0089] Step S1: Acquire three-dimensional scanning data of a glass mold, and perform glass surface microstructure recognition on the three-dimensional scanning data of the glass mold, thereby obtaining microstructure data of the glass mold; perform three-dimensional mold geometry digitization based on the microstructure data of the glass mold, thereby obtaining a three-dimensional structural model of the glass mold;

[0090] In this embodiment, a high-precision laser scanner is used to obtain the three-dimensional scanning data of the glass mold. During the scanning process, a high-resolution sensor is used to ensure that the acquired data details fully reflect the microscopic surface features of the glass mold. Afterwards, computer vision technology is used to identify the surface microstructure of the scanned data, and edge detection and image segmentation algorithms are used to extract details such as grain distribution and microcracks on the mold surface, thereby obtaining the microstructure data of the glass mold. These microstructure data will be input into the three-dimensional modeling software for geometric digitization processing, and the three-dimensional structure model of the glass mold will be obtained through parametric modeling technology to ensure that the model can accurately express the detailed features of the mold surface and interior, and provide data support for subsequent optimization.

[0091] Step S2: acquiring historical manufacturing data of glass molds, and performing mold performance requirement identification on the historical manufacturing data of glass molds, thereby obtaining historical mold performance requirement data; performing mold design requirement analysis on the historical mold performance requirement data, thereby obtaining a mold design requirement parameter set;

[0092] In this embodiment, the glass mold manufacturing management platform is used to obtain the historical manufacturing data of the glass mold, and the manufacturing data of the glass mold in the historical production process is collected, including manufacturing time, temperature, material and other information. Combined with the performance requirements of the mold, the performance requirement data of the mold under different working conditions are identified through data analysis and machine learning algorithms, such as the mold's high temperature resistance, compressive strength and other characteristics. These performance requirement data are further analyzed and converted into a mold design requirement parameter set, including material selection, mold thickness, dimensional tolerance and other parameters, to provide a basis for subsequent design optimization.

[0093] Step S3: optimizing the shape structure of the glass mold three-dimensional structure model according to the mold design requirement parameter set, thereby obtaining an optimized glass mold three-dimensional structure model; simulating the physical working condition of the optimized glass mold three-dimensional structure model according to the historical mold performance requirement data, thereby obtaining glass mold physical simulation data;

[0094] In this embodiment, the shape and structure of the three-dimensional structural model of the glass mold is optimized using the obtained mold design requirement parameter set. During the optimization process, finite element analysis is used to simulate the stress conditions of the mold, and the geometric shape of the mold is adjusted to meet performance requirements, such as improving the thermal stability of the mold or enhancing the wear resistance of the mold. The optimized three-dimensional structural model is used as the basis for the next physical simulation data for simulation analysis. The optimized three-dimensional structural model is physically simulated under high temperature conditions, and the temperature field and stress field distribution of the mold in actual production are analyzed using thermodynamics and fluid mechanics simulation, thereby obtaining physical simulation data of the glass mold during high temperature molding.

[0095] Step S4: Based on the physical simulation data of the glass mold, the optimized three-dimensional structure model of the glass mold is optimized for high-temperature molding dynamic mold structure, so as to obtain a high-temperature structure optimized glass mold model; the high-temperature structure optimized glass mold model is converted into a three-dimensional mold surface, so as to obtain mold surface data of the glass mold to be manufactured, and the mold surface data is uploaded to the glass mold manufacturing management platform to execute the mold manufacturing task;

[0096] In this embodiment, based on the obtained physical simulation data, the optimized three-dimensional structure model of the glass mold is further optimized for high-temperature forming dynamic mold structure, with special attention paid to the deformation and thermal stress distribution of the mold under high temperature. By comparing with the high-temperature forming experimental data, the mold structure is adjusted using the thermal-mechanical coupling analysis method to reduce deformation and material fatigue under high temperature environment, thereby obtaining a glass mold model after high-temperature structure optimization. Then, the model is converted into a three-dimensional mold surface, and the optimized three-dimensional structure is converted into mold surface data suitable for manufacturing. These data will be uploaded to the glass mold manufacturing management platform for subsequent mold production and scheduling.

[0097] Step S5: Acquire glass mold manufacturing multidimensional data, and perform manufacturing mold process adaptability evaluation based on the glass mold manufacturing multidimensional data, so as to obtain manufacturing mold process adaptability data; perform process scheduling optimization based on the manufacturing mold process adaptability data, so as to obtain manufacturing mold process optimization scheduling data, and upload it to the glass mold manufacturing management platform to execute the process scheduling task.

[0098] In this embodiment, the glass mold manufacturing management platform collects multidimensional data related to the glass mold manufacturing process through a sensor system, including but not limited to the temperature, humidity, pressure, vibration, processing speed, mold material temperature, production load, and energy consumption of the equipment during operation. The frequency of data collection can reach once per minute to ensure real-time monitoring of the production environment. These data are uploaded to the manufacturing control system through the Internet of Things technology to facilitate real-time data analysis. Next, the multidimensional data from different sources are integrated using data fusion technology to build a unified process adaptability evaluation model. The adaptability relationship between different process parameters is comprehensively evaluated by data fusion technology and machine learning algorithms. The model can analyze and evaluate the adaptability relationship between various parameters and target product requirements in the production process, such as the impact of temperature fluctuations on mold hardness, the impact of humidity changes on material thermal expansion, etc. By adopting machine learning algorithms (such as support vector machines, decision trees, etc.), the stability and process adaptability of the production process are evaluated. According to the adaptability evaluation results, the process bottlenecks and risks that may cause mold production quality problems are identified. For example, if the evaluation model finds that the temperature fluctuation range of a certain device is large, which will affect the surface quality of the mold, or in certain specific production stages, the excessive load of the equipment may cause delays in production progress or damage to the mold, it will automatically alarm and provide improvement suggestions, such as adjusting temperature control settings, optimizing equipment scheduling, or changing production task allocation. After the evaluation, a specific process scheduling optimization plan will be generated based on the adaptability data to further improve process efficiency and reduce resource waste. For example, it is recommended to arrange low-load tasks for equipment during high-load periods, or optimize the production batches of molds to reduce the frequent start and stop of equipment. The optimized process scheduling plan will be automatically uploaded to the glass mold manufacturing management platform through the interface with the production management platform. The platform can schedule production tasks in real time, adjust production plans and equipment loads, and realize the automation and efficiency of the production process. The upload of process scheduling optimization data can ensure that production management personnel can monitor changes in the entire manufacturing process in a timely manner and make corresponding adjustments, further ensuring the production quality and stability of the production progress of glass molds.

[0099] Optionally, step S1 specifically includes:

[0100] Step S11: acquiring three-dimensional scanning data of the glass mold, and performing scanning point cloud data preprocessing on the three-dimensional scanning data of the glass mold, so as to obtain scanning point cloud data of the glass mold to be analyzed;

[0101] In this embodiment, when obtaining the three-dimensional scanning data of the glass mold, a high-precision laser scanner is used to scan the glass mold to obtain surface point cloud data. Since there may be noise, missing data or overlapping points during the scanning process, point cloud data preprocessing is required, including noise removal, point cloud sparseness, and overlapping point elimination. A downsampling algorithm based on the voxel grid method is used to reduce the amount of data, and the RANSAC algorithm is used for plane fitting to eliminate irrelevant points, and finally generate the glass mold scanning point cloud data to be analyzed. In this way, the efficiency and accuracy of subsequent data processing can be improved.

[0102] Step S12: performing mold surface texture analysis on the scanned point cloud data of the glass mold to be analyzed, thereby obtaining mold surface texture data;

[0103] In this embodiment, the point cloud is filtered on the scanned point cloud data of the glass mold to be analyzed to smooth the data and reduce noise. Then, the point cloud data is layered using a multi-scale analysis method to extract different texture features on the mold surface. The texture feature areas in the point cloud, such as surface roughness, cracks, scratches, etc., are identified through an adaptive threshold segmentation algorithm. In order to improve the analysis accuracy, the principal component analysis (PCA) method is also combined to further enhance the ability to extract texture features, thereby obtaining mold surface texture data, which can provide a reliable basis for subsequent microstructure feature analysis.

[0104] Step S13: quantifying the microstructure characteristics of the mold surface according to the mold surface texture data, thereby obtaining the glass mold microstructure data;

[0105] In this embodiment, image processing technology is used to quantify the microstructure characteristics of the mold surface based on the mold surface texture data. The distribution characteristics of the surface texture, such as surface fluctuation amplitude, texture periodicity, roughness index, etc., are extracted by statistical analysis methods. Then, the gray level co-occurrence matrix (GLCM) is used to calculate the characteristic values ​​of the texture, such as contrast, energy, uniformity, etc. Through a series of feature quantification techniques, the microstructure feature data of the mold surface, such as surface roughness, microcrack density, local changes, etc., are calculated, providing an in-depth analysis of the mold surface quality.

[0106] Step S14: performing three-dimensional geometric modeling of the mold based on the microstructure data of the glass mold, thereby obtaining a three-dimensional geometric model of the glass mold;

[0107] In this embodiment, based on the microstructure data of the glass mold, data standardization is performed to ensure the accuracy and consistency of the data. Computer-aided design (CAD) software and three-dimensional modeling technology are used to model the microstructure features and reconstruct the three-dimensional geometric structure model of the glass mold. In this process, the finite element method (FEM) is used to simulate the mechanical properties of the surface microstructure, and the details of the three-dimensional model are further optimized to ensure its feasibility and reliability in practical applications.

[0108] Step S15: Correcting the accuracy of the three-dimensional geometric model of the glass mold to obtain a three-dimensional structural model of the glass mold.

[0109] In this embodiment, after obtaining a preliminary three-dimensional geometric model, an error correction algorithm is used to correct the accuracy of the model. By comparing with the actual scanning data, the difference analysis method is used to identify the deviation between the geometric model and the actual surface, and the least square method and other optimization algorithms are applied to correct it. In addition, the model is redesigned using reverse engineering technology to ensure that all details meet the manufacturing requirements. Through multiple iterative optimizations, a high-precision three-dimensional structural model of the glass mold is obtained to meet the needs of subsequent design and manufacturing.

[0110] Optionally, step S13 is specifically:

[0111] Step S131: extracting surface texture direction features from the mold surface texture data, thereby obtaining the mold surface texture direction data;

[0112] In this embodiment, when extracting the surface texture direction feature of the mold surface texture data, a gradient-based direction calculation method (such as the Canny edge detection algorithm) is used to identify the main texture direction of the mold surface by calculating the local direction of each point in the point cloud data. The statistical analysis method of the directional gradient is used to extract the texture direction data of the mold surface in different areas based on the angular relationship between the texture points. For example, for the surface of a glass mold, its main scratch direction, wear direction, etc. can be extracted through local area analysis, and then the main direction information of the mold surface texture can be obtained. This provides a directional basis for subsequent texture periodicity analysis and roughness calculation.

[0113] Step S132: performing surface texture frequency analysis according to the mold surface texture direction data, thereby obtaining surface texture periodic feature data;

[0114] In this embodiment, when performing surface texture frequency analysis based on the texture direction data of the mold surface, the texture data of the mold surface is converted into the frequency domain using the fast Fourier transform (FFT). By analyzing the frequency distribution in the texture direction of the mold surface, its periodic characteristics can be obtained. For example, if there are periodic scratches or lines on the mold surface, the FFT analysis can reveal the periodic frequency of the texture, and then obtain the periodic characteristic data of the texture. By setting an appropriate frequency threshold, the texture pattern with a more obvious frequency can be extracted to assist in the subsequent microstructure identification and material property analysis.

[0115] Step S133: Calculating the local surface roughness of the mold surface texture data, thereby obtaining the mold surface roughness data;

[0116] In this embodiment, when calculating the local surface roughness of the mold surface texture data, common surface roughness calculation standards such as Ra, Rq, etc. are used. A computer vision algorithm is used to perform statistical analysis of the mold surface point cloud data in local areas to calculate the surface roughness of each small area. Specifically, the scanned point cloud of the mold is first meshed, and indicators such as the height difference, average roughness, and root mean square roughness of the point cloud are calculated in each grid. For example, on the surface of a glass mold, it may be found that the surface roughness of a local area increases due to improper use or manufacturing defects. Through this calculation, detailed mold surface roughness data can be obtained, providing a basis for subsequent microstructure analysis.

[0117] Step S134: performing microscopic feature recognition of a local area of ​​the mold based on the surface texture periodic feature data and the mold surface roughness data, thereby obtaining local microscopic structure data of the mold surface;

[0118] In this embodiment, when the microscopic features of the local area of ​​the mold are identified based on the surface texture periodic feature data and the mold surface roughness data, the classification algorithm based on machine learning is used to divide the mold surface into regions. The different texture and roughness features of the mold surface are grouped using a clustering algorithm (such as K-means clustering method) to identify the microscopic features of different local areas of the mold surface. For example, in the manufacturing process of a glass mold, different degrees of heat treatment areas may appear, and their surface roughness and texture features are significantly different. By integrating the texture and roughness feature data of these areas, the local microstructure data of the mold surface is finally obtained, which can provide support for subsequent material property matching.

[0119] Step S135: matching the local microstructure data of the mold surface with the local microstructure material properties of the mold surface through a preset glass material property database, thereby obtaining the local microstructure material property data of the mold surface;

[0120] In this embodiment, when matching the local microstructure data of the mold surface with the local microstructure material properties of the mold surface through the preset glass material property database, an information library containing multi-dimensional properties such as mechanical properties, thermal properties, and chemical stability of the glass material is first established. Then, the local microstructure data of the mold surface is compared with the database, and the material properties similar to the current mold surface microstructure are identified through a feature matching algorithm (such as nearest neighbor search). For example, if a local area of ​​the mold surface shows high roughness and large surface cracks, a glass material with strong heat resistance and wear resistance may be recommended in the database. This matching process ensures that suitable materials are selected for surface repair or improvement based on the microstructure characteristics of the mold.

[0121] Step S136: integrating the microstructure features of the glass mold surface according to the local microstructure data of the mold surface and the local microstructure material property data of the mold surface, so as to obtain the microstructure data of the glass mold.

[0122] In this embodiment, when integrating the microstructure characteristics of the glass mold surface according to the local microstructure data of the mold surface and the local microstructure material property data of the mold surface, the microstructure data of each local area is first weighted and fused. Based on a weighted average or weighted regression model, the surface texture, roughness and material property data of each local area are integrated to form global glass mold surface microstructure data. For example, combining the characteristics of the thermal stress area and the wear area of ​​the glass mold, the design and manufacturing process of the mold can be optimized to ensure the stability of the mold under high temperature and high pressure environments. By integrating these data, a more accurate description of the microstructure characteristics of the mold surface can be obtained, thereby providing an important reference basis for the optimal design of the mold and material selection.

[0123] Optionally, step S135 is specifically:

[0124] Identify local grain structure features based on local microstructure data of the mold surface, thereby obtaining local grain structure data of the mold surface;

[0125] In this embodiment, a clustering algorithm is used to extract the grain morphology, size and distribution information of the local area of ​​the mold surface from the local microstructure data of the mold surface. Then, a regional segmentation algorithm is applied to identify different grain blocks, and the grain size and grain spacing of these blocks are used as local grain structure data. Then, based on this data, the relationship between the grain structure characteristics and the changes in the mold surface temperature and pressure is established in the model, providing a basis for the subsequent selection of glass materials.

[0126] The thermal energy characteristics of glass raw materials are extracted through a preset glass material characteristic database, thereby obtaining thermal energy characteristic data of glass raw materials;

[0127] In this embodiment, when extracting the thermal energy characteristics of glass raw materials through a preset glass material characteristic database, first select a suitable glass raw material type, such as silica-based, aluminosilicate-based, etc., and use the thermal conductivity, specific heat capacity, thermal expansion coefficient and other parameters of the glass stored in the database to extract the thermal energy characteristic data of different glass raw materials at a specific working temperature. These data are usually obtained through literature search or experimental testing, and can be fine-tuned according to the actual application scenario. For example, for glass materials with high thermal expansion characteristics, the database will show their thermal stability and thermal stress distribution at high temperatures, thereby providing an important basis for matching suitable mold materials.

[0128] According to the thermal energy characteristic data of the glass raw materials, the local grain structure data on the mold surface is matched with the glass mold material characteristics, so as to obtain the glass mold matching material data;

[0129] In this embodiment, when matching the glass mold material characteristics with the local grain structure data on the mold surface according to the thermal energy characteristic data of the glass raw material, the local grain structure characteristics on the mold surface are compared and analyzed with the thermal energy data of the glass raw material. For example, for the mold surface area with large thermal expansion, a glass material with a high thermal expansion coefficient is selected to ensure that the thermal stress distribution of the mold surface and the glass can be balanced under high temperature conditions. The machine learning algorithm is used to compare the thermal response characteristics of different materials with the mold grain structure data, and the glass material that best matches the mold surface characteristics is automatically selected.

[0130] Estimating the raw material ratio of the glass mold based on the local grain structure data of the mold surface based on the glass mold matching material data, thereby obtaining the estimated raw material ratio data of the glass mold;

[0131] In this embodiment, when estimating the raw material ratio of the glass mold based on the local grain structure data of the mold surface based on the glass mold matching material data, the raw material ratio of the glass mold is estimated by using a calculation model in combination with the existing glass material characteristic data and the local grain structure characteristics of the mold surface. Specifically, an optimization algorithm (such as a genetic algorithm or a particle swarm optimization) can be used to calculate the glass raw material ratio by considering multiple factors such as grain structure, thermal expansion, and high temperature resistance. For example, increasing the ratio of silicon and sodium can improve the thermal expansion and thermal conductivity of the glass, while adding aluminum and calcium can improve the heat resistance and aging resistance of the glass, thereby calculating the material ratio suitable for the specific grain structure of the mold surface.

[0132] The local microstructure material characteristics of the mold surface are extracted from the glass material characteristics database according to the glass mold matching material data and the glass mold raw material ratio estimation data, so as to obtain the local microstructure material characteristics data of the mold surface.

[0133] In this embodiment, when extracting the material properties of the local microstructure of the mold surface from the glass material property database based on the glass mold matching material data and the estimated data of the glass mold raw material ratio, the estimated ratio data is first compared with the thermal and mechanical properties in the material database to extract the most matching material property data. For example, for the estimated ratio results, the database will provide data such as the thermal conductivity, thermal fatigue resistance, and thermal expansion coefficient of the glass to further refine the microstructure properties of the mold. The extraction of these data can be completed by calling the material property model in the database in the computer-aided design (CAD) software to complete the specific matching of material properties in practical applications, and provide a basis for the selection of raw materials and performance evaluation in the subsequent mold manufacturing process.

[0134] Optionally, step S2 specifically includes:

[0135] Step S21: acquiring historical manufacturing data of glass molds, and performing data preprocessing on the historical manufacturing data of glass molds, thereby obtaining historical manufacturing data of glass molds to be analyzed;

[0136] In this embodiment, when the glass mold manufacturing management platform is used to obtain the historical manufacturing data of the glass mold, it includes information such as historical production records, raw material batches, processing parameters, and process flow. Then, these data are preprocessed to make the data neater and easier to analyze by removing duplicate records, filling missing values, and standardizing values. Specifically, if there are missing values ​​such as mold size and processing temperature in the original data, mean filling or interpolation algorithms can be used to obtain the historical manufacturing data of the glass mold to be analyzed that is suitable for further analysis.

[0137] Step S22: extracting mold manufacturing features from the historical manufacturing data of the glass mold to be analyzed, thereby obtaining mold manufacturing process data and mold historical performance detection data;

[0138] In this embodiment, when extracting mold manufacturing features from the historical manufacturing data of the glass mold to be analyzed, the process parameters such as temperature, pressure, speed, etc. recorded during the processing are analyzed, and key manufacturing features are extracted using data mining methods. For example, the characteristic variables closely related to mold performance, such as mold surface roughness, wear resistance, thermal expansion coefficient, etc., are identified through the principal component analysis (PCA) method. At the same time, the historical performance test data of the mold is screened to extract key performance test indicators, such as mold hardness, surface finish, etc., and finally the mold manufacturing process data and historical performance test data are obtained to provide basic data for subsequent performance analysis.

[0139] Step S23: performing mold historical detection performance pattern recognition on the mold historical performance detection data, thereby obtaining mold detection performance pattern data;

[0140] In this embodiment, when performing mold historical detection performance pattern recognition on mold historical performance detection data, the performance patterns of molds in different manufacturing batches are identified through machine learning algorithms, such as K-means clustering or support vector machine (SVM). For example, molds in a certain batch have higher surface roughness or lower high temperature resistance, while other batches show better performance. Through the recognition of these data patterns, a quantitative basis can be provided for the performance differences of different molds, and data support can be provided for the subsequent identification of mold performance requirements.

[0141] Step S24: performing mold performance requirement identification based on the mold detection performance mode data, thereby obtaining historical mold performance requirement data;

[0142] In this embodiment, when the mold performance requirements are identified based on the mold detection performance pattern data, the mold performance requirements are identified by matching the mold detection performance pattern data with the historical mold usage environment. For example, if a mold is used under high temperature and high pressure conditions for a long time, its performance requirements include strong heat resistance and pressure resistance; while molds used in low temperature environments require strong frost resistance and low thermal expansion coefficient. Through data mining methods, combined with the mold usage environment and historical performance detection data, the performance requirement data of historical molds are obtained to guide the formulation of subsequent mold design requirements.

[0143] Step S25: Perform mold design requirement analysis based on historical mold performance requirement data and mold manufacturing process data to obtain a mold design requirement parameter set.

[0144] In this embodiment, when performing mold design demand analysis based on historical mold performance demand data and mold manufacturing process data, the performance requirements of the mold are analyzed in detail and the performance requirements are converted into design parameters. For example, if the performance requirements of the mold require higher heat resistance, then it is necessary to determine the appropriate material type and design specifications based on the material properties, temperature changes, thermal expansion and other requirements of the mold. Combined with the mold manufacturing process data, analyze the impact of process changes on mold design, such as the impact of different processing technologies on mold hardness and wear resistance. Based on these analysis results, a mold design requirement parameter set is obtained, including size requirements, material type, performance indicators, etc., to provide detailed technical parameters for the design of the mold.

[0145] Optionally, step S24 is specifically:

[0146] Step S241: classifying the performance patterns according to the mold detection performance pattern data, thereby obtaining the performance pattern data of the molds that passed the detection and the performance pattern data of the molds that failed the detection;

[0147] In this embodiment, when classifying the performance patterns according to the mold detection performance pattern data, a machine learning algorithm, such as K-means clustering or a decision tree model, is used to classify the performance data of the historical molds. The mold performance data obtained includes parameters such as surface finish, hardness, and high temperature resistance. The mold performance is divided into two categories of "qualified" and "unqualified" according to the test result items in these data, and the performance patterns of qualified and unqualified molds are identified. For example, a certain type of mold is classified as a qualified mold due to its high hardness and good surface finish, while another type of mold is classified as an unqualified mold due to poor heat resistance and surface defects, and finally the performance pattern data of the two types of molds are obtained.

[0148] Step S242: quantifying the performance mode errors of the qualified mold performance mode data and the unqualified mold performance mode data, thereby obtaining mold performance mode error data;

[0149] In this embodiment, when the performance mode error is quantified for the performance mode data of the qualified mold and the performance mode data of the unqualified mold, the error range is calculated by using a statistical analysis method. For example, for a qualified mold, the error amount of each performance indicator, such as mold hardness, surface roughness, etc., is calculated by comparing the difference between the actual measured performance data and the standard performance requirements. At the same time, for an unqualified mold, a similar method is used to calculate its performance error, and its deviation is quantitatively analyzed. Through error quantification, the error range of each mold performance mode can be clearly identified, providing a basis for subsequent deviation elimination and correction.

[0150] Step S243: removing the mold detection performance mode data from the mold detection performance mode data according to the mold performance mode error data, thereby obtaining the mold detection performance mode correction data;

[0151] In this embodiment, when the mold detection performance mode data is subjected to deviation distribution extreme value detection data elimination based on the mold performance mode error data, an outlier detection method, such as a box plot or a Z-score method, is used to identify extreme values ​​in the performance mode error. By calculating the deviation distribution of the mold performance error data, it is determined which data points are beyond the normal range, and these extreme values ​​are eliminated. For example, if the hardness test data of a batch of molds has obvious deviations, it may be due to measurement errors or equipment failures. After eliminating these abnormal data, the remaining data can more accurately reflect the mold performance, thereby obtaining the correction data of the mold detection performance mode.

[0152] Step S244: quantifying the performance mode error according to the mold detection performance mode correction data, thereby obtaining the mold performance mode error correction data;

[0153] In this embodiment, when the performance mode error is quantified based on the mold detection performance mode correction data, the performance error is recalculated using the correction data after the extreme values ​​are previously eliminated. Specifically, the corrected data can be quantified using the mean square error (MSE) or the mean absolute error (MAE) to obtain a more accurate error range. For example, after correction, the surface roughness error of a mold is reduced from the original ±0.05 to ±0.01, and the hardness error is also significantly reduced. The quantified error data is more accurate, which helps to better identify the true situation of the mold performance.

[0154] Step S245: performing performance detection threshold statistics according to the mold performance mode error correction data, thereby obtaining mold performance detection threshold data;

[0155] In this embodiment, when the performance detection threshold is statistically calculated based on the error correction data of the mold performance model, a performance detection standard is set, and the allowable error range of each performance indicator (such as surface finish, hardness, high temperature resistance, etc.) is calculated. Through statistical analysis, such as using a normal distribution or other suitable statistical distribution model, the qualified threshold of each performance indicator is obtained. For example, the qualified threshold of surface roughness is set to Ra≤0.01μm, and the qualified range of hardness is set to HRC 48-52. Through the statistically corrected error data, an overall mold performance detection threshold is obtained to ensure the accuracy of subsequent mold detection.

[0156] Step S246: Identify mold performance requirements based on the mold performance detection threshold data, thereby obtaining historical mold performance requirement data.

[0157] In this embodiment, when the mold performance requirements are identified based on the mold performance detection threshold data, the performance requirements of the mold are identified and optimized in combination with the environment and conditions in which the mold is actually used during the production process. For example, molds used in high temperature and high pressure environments require special attention to their heat resistance and pressure resistance, so they need to be matched according to the performance detection threshold data to ensure that the mold can meet these requirements. Based on historical mold performance requirement data, the specific performance requirements of the mold in different working environments are identified to provide guidance for subsequent design and manufacturing.

[0158] Optionally, step S25 is specifically:

[0159] Step S251: extracting mold performance characteristics from historical mold performance demand data, thereby obtaining mold performance characteristic data;

[0160] In this embodiment, when extracting mold performance characteristics from historical mold performance demand data, characteristic parameters closely related to mold performance, such as high temperature resistance, pressure resistance, corrosion resistance, surface roughness, etc., are extracted through data analysis methods. These data come from the results obtained from performance tests on molds during multiple productions. For example, for the extraction of high temperature resistance, based on the test data of historical molds under different temperature conditions, the thermal stability and deformation resistance of the mold in a high temperature environment are identified, and the thermal deformation coefficient, heat resistance and other characteristics of the mold are calculated through this series of data. This process can be automated using statistical regression analysis or machine learning methods to extract mold performance characteristic data and provide a basis for subsequent modeling.

[0161] Step S252: Modeling the manufacturing process-related features based on the mold performance feature data and the mold manufacturing process data, thereby obtaining a performance requirement-manufacturing process-related model;

[0162] In this embodiment, when modeling the manufacturing process-related features based on the mold performance feature data and the mold manufacturing process data, the intrinsic relationship between the performance features and the manufacturing process is identified by performing deep learning analysis on the historical data. For example, the surface finish of the mold is closely related to the polishing process in the manufacturing process, and the hardness is directly related to the heat treatment process (such as quenching and tempering). By establishing an association model, the performance characteristics and the corresponding manufacturing process data are mapped, and the association relationship between the performance requirements and the manufacturing process is constructed using modeling methods such as multivariate linear regression or neural networks, thereby obtaining a performance requirement-manufacturing process association model. This model can effectively predict the most suitable manufacturing process conditions required under a specific mold performance requirement.

[0163] Step S253: acquiring real-time mold manufacturing process data, and performing manufacturing process deviation calculation on the real-time mold manufacturing process data and the mold manufacturing process data, thereby obtaining manufacturing process deviation data;

[0164] In this embodiment, after obtaining real-time mold manufacturing process data through the glass mold manufacturing management platform, when calculating the manufacturing process deviation of the real-time mold manufacturing process data and the historical mold manufacturing process data, real-time monitoring technology is used to obtain data of each manufacturing process link, such as key manufacturing parameters such as temperature, time, pressure, and equipment speed. By comparing with historical process data, the deviation value of the process parameter is calculated using a difference analysis method (such as deviation analysis, chi-square test). For example, if the heat treatment temperature of a batch of molds is too high, it may cause the hardness to exceed the standard, and the deviation data can reveal this problem. By calculating the manufacturing process deviation data, a numerical basis is provided for the subsequent adjustment model.

[0165] Step S254: Adaptively adjust the performance requirement-manufacturing process association model according to the manufacturing process deviation data, so as to obtain an updated performance requirement-manufacturing process association model;

[0166] In this embodiment, when the performance requirement-manufacturing process association model is adaptively adjusted according to the manufacturing process deviation data, the calculated deviation data is used to correct the model. For example, if it is found that the temperature deviation in the manufacturing process causes the hardness to be too high, the process parameters can be adjusted to compensate for this error by dynamically updating the original association model. Using weighted regression or Bayesian optimization methods, the real-time process deviation is incorporated into the model, and the model parameters are corrected to obtain a more accurate relationship between performance requirements and processes. This adjustment enables the model to adapt to real-time changing manufacturing conditions and ensure that the mold performance meets the expected requirements.

[0167] Step S255: Estimating mold design requirement parameters by updating the performance requirement-manufacturing process association model, thereby obtaining an unclassified mold design requirement parameter set;

[0168] In this embodiment, when estimating the mold design requirement parameters through the performance requirement-manufacturing process update association model, first input the new performance requirement data (such as new hardness requirements, heat resistance requirements, etc.), and combine it with the updated manufacturing process data, and estimate it through the updated association model. For example, if the customer's demand changes require the mold to have a higher compressive strength, the model can be used to quickly estimate the design requirements such as the need for higher hardness materials, changes in heat treatment processes, or changes in cooling speed. Through algorithms such as regression analysis and neural networks, the mold design parameter set that best meets the performance requirements can be automatically estimated.

[0169] Step S256: classifying the glass mold historical manufacturing data to be analyzed by mold type to obtain manufacturing mold type data, and associating the manufacturing mold type data and the unclassified mold design requirement parameter set by mold type to obtain the mold design requirement parameter set.

[0170] In this embodiment, when the historical manufacturing data of the glass mold to be analyzed is classified into mold types, a classification algorithm (such as K-means clustering, support vector machine, etc.) is used to classify the molds into different types, such as injection molds, die-casting molds, etc., according to the historical manufacturing data. These mold type data can be classified based on the shape, structure, and application field of the mold. Subsequently, based on the mold type data and the unclassified mold design requirement parameter set, an association analysis method (such as the Apriori algorithm) is used to associate the mold type with the design requirements. For example, a certain type of mold is more suitable for high-pressure casting process. According to this association feature, a corresponding design requirement parameter set is generated for this type of mold, and finally a specific mold design requirement parameter set is obtained, which provides a basis for subsequent production and design.

[0171] Optionally, step S3 specifically includes:

[0172] Step S31: performing mold structure-design requirement association on the mold design requirement parameter set and the glass mold three-dimensional structure model, thereby obtaining a mold structure-design requirement association matrix;

[0173] In this embodiment, when the mold design requirement parameter set and the three-dimensional structural model of the glass mold are associated with the mold structure-design requirement, the design requirements of the glass mold are determined, including the heat resistance, compressive strength, dimensional accuracy, etc. of the mold. Then, relevant geometric parameters (such as the wall thickness, material type, cooling channel distribution, etc. of the mold) are extracted from the existing three-dimensional structural model, and these structural parameters are linked to the design requirements through data analysis methods (such as correlation analysis, regression model). For example, the thermal expansion performance requirements of the mold are associated with the wall thickness and thermal conductivity of the material. Therefore, a matrix is ​​established to quantify the relationship between the mold design requirements and the structure. Through this process, the influence relationship between different design requirements and structural parameters can be clearly seen, providing a basis for subsequent design adjustments.

[0174] Step S32: Based on the mold design requirement parameter set, and using the mold structure-design requirement association matrix, mold shape structure parameters are selected for the glass mold three-dimensional structure model, thereby obtaining a mold shape structure parameter set;

[0175] In this embodiment, based on the mold design requirement parameter set, when selecting the mold shape structure parameters for the glass mold three-dimensional structure model using the mold structure-design requirement association matrix, the structural parameters most closely related to the mold design requirements are selected according to the data in the association matrix. For example, if the thermal stability of the mold is the primary design requirement, parameters that affect the thermal conductivity performance, such as material thermal conductivity, mold wall thickness, etc., can be selected from the three-dimensional model. These parameters will be input into an optimization algorithm to help select the most appropriate shape structure parameter set. If the thermal stability of the mold needs to be improved, the design requirements can be met by selecting a material with a higher thermal conductivity and an appropriate wall thickness, thereby forming a new set of mold shape structure parameter sets.

[0176] Step S33: performing multi-objective structural parameter optimization on the mold shape structural parameter set, thereby obtaining optimized mold shape structural parameters;

[0177] In this embodiment, when performing multi-objective structural parameter optimization on the mold shape structure parameter set, a multi-objective optimization method (such as genetic algorithm, particle swarm optimization, etc.) is used to weigh multiple design goals (such as mold strength, heat resistance, wear resistance, etc.). Specifically, assuming that the design requirements of the mold include high strength and good thermal stability, the optimization algorithm will simultaneously consider the trade-off between the two. For example, increasing the wall thickness can increase the strength, but will result in a decrease in thermal conductivity. Through multi-objective optimization, a balance point can be found between different goals, and ultimately an optimized mold shape structure parameter set that meets both strength requirements and ensures thermal stability is selected. The optimization process takes into account the priorities and constraints between different goals to ensure that each design goal is fully met.

[0178] Step S34: adjusting the three-dimensional structure of the glass mold three-dimensional structure model according to the optimized mold shape structure parameters, thereby obtaining the optimized glass mold three-dimensional structure model;

[0179] In this embodiment, when the three-dimensional structure of the glass mold three-dimensional structure model is adjusted according to the optimized mold shape structure parameters, the optimized parameters are applied to the three-dimensional design model. These parameters include the wall thickness, angle, distribution of cooling channels, etc. of the mold. CAD software (such as SolidWorks or AutoCAD) is used to make modifications in the three-dimensional model, such as adjusting the wall thickness of the mold to meet the thermal stability requirements, or optimizing the cooling channel layout to improve the cooling efficiency. Through these structural adjustments, a new optimized three-dimensional structure model of the glass mold is obtained to ensure that it can meet the design requirements and have good performance in actual use. This model will be used for subsequent physical simulation and actual manufacturing.

[0180] Step S35: estimating the working condition of the glass mold based on the historical mold performance requirement data and the real-time mold manufacturing process data, thereby obtaining the working condition data of the glass mold;

[0181] In this embodiment, when estimating the working conditions of the glass mold based on the historical mold performance requirement data and the real-time mold manufacturing process data, the historical mold usage data is collected, such as the performance, loss, deformation and other information of the mold at different temperatures and pressures. Real-time manufacturing data such as temperature, pressure and cooling rate are obtained. Using these data, the working conditions of the mold are estimated through thermodynamic models or finite element analysis (FEA). For example, if historical data shows that a certain type of mold is prone to thermal expansion at high temperatures, real-time data can help confirm whether the mold is in a similar working environment under the current working conditions. Through these calculations, accurate mold working condition data can be obtained, which provides a scientific basis for subsequent simulation and adjustment.

[0182] Step S36: performing mold physical working condition simulation on the optimized glass mold three-dimensional structure model according to the glass mold working condition data, thereby obtaining glass mold physical simulation data.

[0183] In this embodiment, when the physical working condition simulation of the optimized glass mold three-dimensional structure model is performed according to the glass mold working condition data, the optimized three-dimensional structure model is simulated in detail using physical simulation software (such as ANSYS or COMSOL). The obtained working conditions (such as temperature distribution, pressure field, etc.) are input into the simulation software to simulate the performance of the mold in the actual working environment. Specifically, the thermal stress distribution, thermal expansion effect and possible deformation of the mold under high temperature working conditions can be calculated during the simulation process. For example, if the working temperature of the glass mold is 1300°C, the simulation will calculate the thermal stress of the mold at this temperature and check whether there is deformation or cracks caused by thermal expansion. These simulation data provide detailed physical performance predictions for subsequent mold performance improvements and production, ensuring that the mold can meet the expected performance requirements in actual production.

[0184] Optionally, step S4 is specifically:

[0185] Step S41: extracting high temperature simulation features from the physical simulation data of the glass mold, thereby obtaining high temperature simulation data of the glass mold;

[0186] In this embodiment, when high-temperature simulation feature extraction is performed on the physical simulation data of the glass mold, high-temperature simulation data obtained by finite element analysis (FEA) software (such as ANSYS or COMSOL) is obtained. These data include information such as the temperature field, stress field, thermal expansion, etc. of the mold at different working temperatures. Then, using data analysis methods such as principal component analysis (PCA) or Fourier transform, feature extraction is performed on the temperature field data to analyze the temperature change law, heat conduction efficiency and physical response characteristics of the mold under a high temperature environment. Through in-depth analysis of the thermal properties and deformation response of the mold material, representative high-temperature simulation data is obtained, laying the foundation for further analysis of the performance of the mold at high temperatures. This step can extract key feature data of the mold under high-temperature working conditions, such as changes in the thermal expansion coefficient within a certain temperature range.

[0187] Step S42: performing time series statistics of mold high temperature stress distribution on the glass mold high temperature simulation data, thereby obtaining mold dynamic high temperature stress distribution data;

[0188] In this embodiment, when the high-temperature simulation data of the glass mold is subjected to time-series statistics of the high-temperature stress distribution of the mold, dynamic data such as mold stress and temperature under high temperature conditions are collected. These data are obtained by simulating the actual working environment of the mold at high temperature, which includes the distribution of mold stress at different time points and temperatures. These data are analyzed using time-series statistical methods (such as weighted average, time-series regression analysis, etc.) to calculate the distribution trend of mold stress changes over time. For example, the stress changes of the mold in a heating-cooling cycle are analyzed, and the stress peak or minimum point in a specific time period is identified to obtain the dynamic high-temperature stress distribution data of the mold. These data help to reveal the uneven stress problem encountered by the mold under long-term high-temperature working conditions, and provide a basis for subsequent analysis and optimization.

[0189] Step S43: performing high-temperature forming dynamic structure thermal-mechanical coupling analysis according to the dynamic high-temperature force distribution data of the mold, thereby obtaining mold structure temperature field distribution data and mold structure stress distribution data;

[0190] In this embodiment, when performing high-temperature molding dynamic structural thermal-mechanical coupling analysis based on the dynamic high-temperature force distribution data of the mold, the temperature field and stress field data of the mold are combined, and the thermal-mechanical coupling analysis method is used to further study the behavior of the mold under dynamic high temperature. Through finite element software, the interaction between thermal expansion, heat conduction and mechanical stress is considered to simulate how the mold withstands the stress caused by heat changes during the actual molding process, and how it responds to these thermal-mechanical effects through material deformation or contraction. The analysis results will provide the structural temperature field distribution data of the mold, indicating the temperature distribution on the surface and inside of the mold, and at the same time calculate the stress distribution data of the mold to identify possible stress concentration areas or vulnerable parts. This analysis can help predict the risk of deformation or damage of the mold due to thermal-mechanical coupling during the production process.

[0191] Step S44: identifying the mold thermal fatigue area based on the mold structure temperature field distribution data, thereby obtaining the mold thermal fatigue area data; identifying the mold thermal stress concentration point based on the mold structure stress distribution data, thereby obtaining the mold thermal stress concentration point data;

[0192] In this embodiment, when the thermal fatigue area of ​​the mold is identified based on the temperature field distribution data of the mold structure, an analysis tool (such as a thermal fatigue assessment model) is used to determine the temperature fluctuation amplitude of the mold in different areas according to the temperature field distribution data, and identify areas with drastic temperature changes and frequent cycles. These areas are prone to thermal fatigue. For example, if the temperature fluctuation of a certain part of the mold is large, it will cause thermal expansion and contraction of the material, resulting in the generation of microcracks. When the thermal stress concentration point of the mold is identified based on the stress distribution data of the mold structure, the areas with the most intensive stress distribution on the surface or inside of the mold are identified. These places become thermal stress concentration points and are prone to cracks or deformation. Through these two analyses, the thermal fatigue areas and thermal stress concentration points in the mold can be accurately identified, providing data support for subsequent optimization.

[0193] Step S45: performing mold structure deformation risk assessment according to the mold thermal fatigue area data and the mold thermal stress concentration point data, thereby obtaining mold structure deformation risk data;

[0194] In this embodiment, when the mold structural deformation risk assessment is performed based on the mold thermal fatigue area data and the mold thermal stress concentration point data, the risk assessment model (such as finite element risk analysis or reliability analysis) is used in combination with the above-identified thermal fatigue area and stress concentration point to comprehensively assess the mold structural deformation risk. For example, if a certain thermal fatigue area also has a large thermal stress concentration point, the deformation risk of this area will increase significantly. The assessment process will also consider factors such as the working environment, material properties, and fatigue life of the mold, and ultimately generate mold structural deformation risk data. These data will provide a basis for mold design improvements to ensure that the occurrence of structural deformation is reduced during the actual manufacturing process.

[0195] Step S46: performing high deformation risk mold structure optimization on the optimized glass mold three-dimensional structure model based on the mold structure deformation risk data, thereby obtaining a high temperature structure optimized glass mold model;

[0196] In this embodiment, when optimizing the high deformation risk mold structure of the optimized glass mold three-dimensional structure model based on the mold structure deformation risk data, first use the deformation risk data obtained in the previous step to identify the mold areas with higher risks. Then, use the optimization algorithm (such as topology optimization or shape optimization) to optimize the structure of these high-risk areas. For example, the deformation risk of these areas can be reduced by changing the geometry of these areas, adding cooling channels, optimizing material layout, etc. During the optimization process, the system will combine the thermal stress distribution and thermal fatigue area data of the mold to ensure that the adjusted mold structure can effectively withstand high temperatures and stress changes, and reduce potential deformation or failure. Finally, a glass mold model with optimized high-temperature structure is obtained.

[0197] Step S47: converting the high-temperature structure optimized glass mold model into a mold surface, thereby obtaining mold surface data of the glass mold to be manufactured, and uploading the data to the glass mold manufacturing management platform to execute the mold manufacturing task.

[0198] In this embodiment, when the high-temperature structure optimized glass mold model is converted into a mold surface, computer-aided design (CAD) software is used to convert the optimized three-dimensional mold structure into mold surface data suitable for actual manufacturing. The mold surface conversion process will take into account the actual requirements of the manufacturing process, such as processing accuracy, surface finish, etc., to ensure that the converted data can accurately guide the production of the mold. The converted mold surface data will be uploaded to the glass mold manufacturing management platform, which will arrange and manage the manufacturing tasks of the mold based on these data. For example, the platform will arrange appropriate production processes and equipment according to the complexity of the mold and the production schedule to ensure that the mold is manufactured on time and according to quality requirements.

[0199] Optionally, the present specification also provides a mold surface intelligent generation system for a glass mold, which is used to execute the mold surface intelligent generation method for a glass mold as described above, and the mold surface intelligent generation system for a glass mold includes:

[0200] The mold microstructure recognition module is used to obtain the three-dimensional scanning data of the glass mold, and perform glass surface microstructure recognition on the three-dimensional scanning data of the glass mold, so as to obtain the microstructure data of the glass mold; the three-dimensional mold geometry is digitized based on the microstructure data of the glass mold, so as to obtain the three-dimensional structure model of the glass mold;

[0201] The mold design requirement analysis module is used to obtain the historical manufacturing data of glass molds, and identify the mold performance requirements of the historical manufacturing data of glass molds, so as to obtain the historical mold performance requirement data; perform mold design requirement analysis on the historical mold performance requirement data, so as to obtain the mold design requirement parameter set;

[0202] The mold shape structure optimization module is used to optimize the mold shape structure of the glass mold three-dimensional structure model according to the mold design requirement parameter set, so as to obtain the optimized glass mold three-dimensional structure model; the mold physical working condition simulation is performed on the optimized glass mold three-dimensional structure model according to the historical mold performance requirement data, so as to obtain the glass mold physical simulation data;

[0203] The high-temperature mold structure optimization module is used to optimize the dynamic mold structure of the high-temperature molding of the optimized glass mold three-dimensional structure model based on the physical simulation data of the glass mold, so as to obtain the high-temperature structure optimized glass mold model; perform three-dimensional mold surface conversion on the high-temperature structure optimized glass mold model, so as to obtain the mold surface data of the glass mold to be manufactured, and upload it to the glass mold manufacturing management platform to execute the mold manufacturing task;

[0204] The process adaptability evaluation module is used to obtain multi-dimensional data of glass mold manufacturing, and to evaluate the process adaptability of the manufacturing mold based on the multi-dimensional data of glass mold manufacturing, so as to obtain the process adaptability data of the manufacturing mold; to optimize the process scheduling based on the process adaptability data of the manufacturing mold, so as to obtain the manufacturing mold process optimization scheduling data, and upload it to the glass mold manufacturing management platform to execute the process scheduling task.

[0205] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0206] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for intelligently generating a mold surface for a glass mold, characterized in that: The following steps are involved: Step S1: Acquire three-dimensional scanning data of a glass mold, and perform glass surface microstructure recognition on the three-dimensional scanning data of the glass mold, thereby obtaining microstructure data of the glass mold; perform three-dimensional mold geometry digitization based on the microstructure data of the glass mold, thereby obtaining a three-dimensional structural model of the glass mold; Step S2: acquiring historical manufacturing data of glass molds, and performing mold performance requirement identification on the historical manufacturing data of glass molds, thereby obtaining historical mold performance requirement data; performing mold design requirement analysis on the historical mold performance requirement data, thereby obtaining a mold design requirement parameter set; Step S3: optimizing the shape structure of the glass mold three-dimensional structure model according to the mold design requirement parameter set, thereby obtaining an optimized glass mold three-dimensional structure model; simulating the physical working condition of the optimized glass mold three-dimensional structure model according to the historical mold performance requirement data, thereby obtaining glass mold physical simulation data; Step S4: Based on the physical simulation data of the glass mold, the optimized three-dimensional structure model of the glass mold is optimized for high-temperature molding dynamic mold structure, so as to obtain a high-temperature structure optimized glass mold model; the high-temperature structure optimized glass mold model is converted into a three-dimensional mold surface, so as to obtain mold surface data of the glass mold to be manufactured, and the mold surface data is uploaded to the glass mold manufacturing management platform to execute the mold manufacturing task; Step S5: acquiring glass mold manufacturing multidimensional data, and performing manufacturing mold process adaptability evaluation based on the glass mold manufacturing multidimensional data, thereby obtaining manufacturing mold process adaptability data; The process scheduling is optimized based on the manufacturing mold process adaptability data to obtain the manufacturing mold process optimization scheduling data, and uploaded to the glass mold manufacturing management platform to execute the process scheduling task.

2. The method for intelligently generating mold surface for glass mold according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: acquiring three-dimensional scanning data of the glass mold, and performing scanning point cloud data preprocessing on the three-dimensional scanning data of the glass mold, so as to obtain scanning point cloud data of the glass mold to be analyzed; Step S12: performing mold surface texture analysis on the scanned point cloud data of the glass mold to be analyzed, thereby obtaining mold surface texture data; Step S13: quantifying the microstructure characteristics of the mold surface according to the mold surface texture data, thereby obtaining the glass mold microstructure data; Step S14: performing three-dimensional geometric modeling of the mold based on the microstructure data of the glass mold, thereby obtaining a three-dimensional geometric model of the glass mold; Step S15: Correcting the accuracy of the three-dimensional geometric model of the glass mold to obtain a three-dimensional structural model of the glass mold.

3. The method for intelligently generating mold surface for glass mold according to claim 2, characterized in that: Step S13 is specifically as follows: Step S131: extracting surface texture direction features from the mold surface texture data, thereby obtaining the mold surface texture direction data; Step S132: performing surface texture frequency analysis according to the mold surface texture direction data, thereby obtaining surface texture periodic feature data; Step S133: Calculating the local surface roughness of the mold surface texture data, thereby obtaining the mold surface roughness data; Step S134: performing microscopic feature recognition of a local area of ​​the mold based on the surface texture periodic feature data and the mold surface roughness data, thereby obtaining local microscopic structure data of the mold surface; Step S135: matching the local microstructure data of the mold surface with the local microstructure material properties of the mold surface through a preset glass material property database, thereby obtaining the local microstructure material property data of the mold surface; Step S136: integrating the microstructure features of the glass mold surface according to the local microstructure data of the mold surface and the local microstructure material property data of the mold surface, so as to obtain the microstructure data of the glass mold.

4. The method for intelligently generating mold surface for glass mold according to claim 3, characterized in that: Step S135 is specifically as follows: Identify local grain structure features based on local microstructure data of the mold surface, thereby obtaining local grain structure data of the mold surface; The thermal energy characteristics of glass raw materials are extracted through a preset glass material characteristic database, thereby obtaining thermal energy characteristic data of glass raw materials; Matching the glass mold material characteristics with the local grain structure data on the mold surface according to the thermal energy characteristic data of the glass raw materials, thereby obtaining the glass mold matching material data; Estimating the raw material ratio of the glass mold based on the local grain structure data of the mold surface based on the glass mold matching material data, thereby obtaining the estimated raw material ratio data of the glass mold; The local microstructure material characteristics of the mold surface are extracted from the glass material characteristics database according to the glass mold matching material data and the glass mold raw material ratio estimation data, so as to obtain the local microstructure material characteristics data of the mold surface.

5. The method for intelligently generating mold surface for glass mold according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: acquiring historical manufacturing data of glass molds, and performing data preprocessing on the historical manufacturing data of glass molds, thereby obtaining historical manufacturing data of glass molds to be analyzed; Step S22: extracting mold manufacturing features from the historical manufacturing data of the glass mold to be analyzed, thereby obtaining mold manufacturing process data and mold historical performance detection data; Step S23: performing mold historical detection performance pattern recognition on the mold historical performance detection data, thereby obtaining mold detection performance pattern data; Step S24: performing mold performance requirement identification based on the mold detection performance mode data, thereby obtaining historical mold performance requirement data; Step S25: Perform mold design requirement analysis based on historical mold performance requirement data and mold manufacturing process data to obtain a mold design requirement parameter set.

6. The method for intelligently generating mold surface for glass mold according to claim 5, characterized in that: Step S24 is specifically as follows: Step S241: classifying the performance patterns according to the mold detection performance pattern data, thereby obtaining the performance pattern data of the molds that passed the detection and the performance pattern data of the molds that failed the detection; Step S242: quantifying the performance mode errors of the qualified mold performance mode data and the unqualified mold performance mode data, thereby obtaining mold performance mode error data; Step S243: removing the mold detection performance mode data from the mold detection performance mode data according to the mold performance mode error data, thereby obtaining the mold detection performance mode correction data; Step S244: quantifying the performance mode error according to the mold detection performance mode correction data, thereby obtaining the mold performance mode error correction data; Step S245: performing performance detection threshold statistics according to the mold performance mode error correction data, thereby obtaining mold performance detection threshold data; Step S246: Identify mold performance requirements based on the mold performance detection threshold data, thereby obtaining historical mold performance requirement data.

7. The method for intelligently generating mold surface for glass mold according to claim 5, characterized in that: Step S25 is specifically as follows: Step S251: extracting mold performance characteristics from historical mold performance demand data, thereby obtaining mold performance characteristic data; Step S252: Modeling the manufacturing process-related features based on the mold performance feature data and the mold manufacturing process data, thereby obtaining a performance requirement-manufacturing process-related model; Step S253: acquiring real-time mold manufacturing process data, and performing manufacturing process deviation calculation on the real-time mold manufacturing process data and the mold manufacturing process data, thereby obtaining manufacturing process deviation data; Step S254: Adaptively adjust the performance requirement-manufacturing process association model according to the manufacturing process deviation data, so as to obtain an updated performance requirement-manufacturing process association model; Step S255: Estimating mold design requirement parameters by updating the performance requirement-manufacturing process association model, thereby obtaining an unclassified mold design requirement parameter set; Step S256: classifying the glass mold historical manufacturing data to be analyzed by mold type to obtain manufacturing mold type data, and associating the manufacturing mold type data and the unclassified mold design requirement parameter set by mold type to obtain the mold design requirement parameter set.

8. The method for intelligently generating mold surface for glass mold according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: performing mold structure-design requirement association on the mold design requirement parameter set and the glass mold three-dimensional structure model, thereby obtaining a mold structure-design requirement association matrix; Step S32: Based on the mold design requirement parameter set, and using the mold structure-design requirement association matrix, mold shape structure parameters are selected for the glass mold three-dimensional structure model, thereby obtaining a mold shape structure parameter set; Step S33: performing multi-objective structural parameter optimization on the mold shape structural parameter set, thereby obtaining optimized mold shape structural parameters; Step S34: adjusting the three-dimensional structure of the glass mold three-dimensional structure model according to the optimized mold shape structure parameters, thereby obtaining the optimized glass mold three-dimensional structure model; Step S35: estimating the working condition of the glass mold based on the historical mold performance requirement data and the real-time mold manufacturing process data, thereby obtaining the working condition data of the glass mold; Step S36: performing mold physical working condition simulation on the optimized glass mold three-dimensional structure model according to the glass mold working condition data, thereby obtaining glass mold physical simulation data.

9. The method for intelligently generating mold surface for glass mold according to claim 1, characterized in that: Step S4 is specifically as follows: Step S41: extracting high temperature simulation features from the physical simulation data of the glass mold, thereby obtaining high temperature simulation data of the glass mold; Step S42: performing time series statistics of mold high temperature stress distribution on the glass mold high temperature simulation data, thereby obtaining mold dynamic high temperature stress distribution data; Step S43: performing high-temperature forming dynamic structure thermal-mechanical coupling analysis according to the dynamic high-temperature force distribution data of the mold, thereby obtaining mold structure temperature field distribution data and mold structure stress distribution data; Step S44: Identifying the thermal fatigue region of the mold based on the temperature field distribution data of the mold structure, thereby obtaining the thermal fatigue region data of the mold; Identify the mold thermal stress concentration point based on the mold structure stress distribution data, so as to obtain the mold thermal stress concentration point data; Step S45: performing mold structure deformation risk assessment according to the mold thermal fatigue area data and the mold thermal stress concentration point data, thereby obtaining mold structure deformation risk data; Step S46: performing high deformation risk mold structure optimization on the optimized glass mold three-dimensional structure model based on the mold structure deformation risk data, thereby obtaining a high temperature structure optimized glass mold model; Step S47: converting the high-temperature structure optimized glass mold model into a mold surface, thereby obtaining mold surface data of the glass mold to be manufactured, and uploading the data to the glass mold manufacturing management platform to execute the mold manufacturing task.

10. A mold surface intelligent generation system for glass molds, characterized in that: Used to execute the mold surface intelligent generation method for glass molds according to claim 1, the mold surface intelligent generation system for glass molds comprises: The mold microstructure recognition module is used to obtain the three-dimensional scanning data of the glass mold, and perform glass surface microstructure recognition on the three-dimensional scanning data of the glass mold, so as to obtain the microstructure data of the glass mold; the three-dimensional mold geometry is digitized based on the microstructure data of the glass mold, so as to obtain the three-dimensional structure model of the glass mold; The mold design requirement analysis module is used to obtain the historical manufacturing data of glass molds, and identify the mold performance requirements of the historical manufacturing data of glass molds, so as to obtain the historical mold performance requirement data; perform mold design requirement analysis on the historical mold performance requirement data, so as to obtain the mold design requirement parameter set; The mold shape structure optimization module is used to optimize the mold shape structure of the glass mold three-dimensional structure model according to the mold design requirement parameter set, so as to obtain the optimized glass mold three-dimensional structure model; the mold physical working condition simulation is performed on the optimized glass mold three-dimensional structure model according to the historical mold performance requirement data, so as to obtain the glass mold physical simulation data; The high-temperature mold structure optimization module is used to optimize the dynamic mold structure of the high-temperature molding of the optimized glass mold three-dimensional structure model based on the physical simulation data of the glass mold, so as to obtain the high-temperature structure optimized glass mold model; perform three-dimensional mold surface conversion on the high-temperature structure optimized glass mold model, so as to obtain the mold surface data of the glass mold to be manufactured, and upload it to the glass mold manufacturing management platform to execute the mold manufacturing task; The process adaptability evaluation module is used to obtain multi-dimensional data of glass mold manufacturing, and to evaluate the process adaptability of the manufacturing mold based on the multi-dimensional data of glass mold manufacturing, so as to obtain the process adaptability data of the manufacturing mold; to optimize the process scheduling based on the process adaptability data of the manufacturing mold, so as to obtain the manufacturing mold process optimization scheduling data, and upload it to the glass mold manufacturing management platform to execute the process scheduling task.

Images