Production parameter optimization method and system for lightweight glass bottle and medium

Abstract

The invention relates to the technical field of glass product manufacturing, in particular to a production parameter optimization method and system for a lightweight glass bottle and a medium. The method comprises the following steps: acquiring a glass bottle structure drawing, and identifying a bottle body structure and a bottle bottom structure; constructing a lightweight glass bottle model according to the bottle body structure and the bottle bottom structure; performing impact load simulation according to the lightweight glass bottle model to obtain impact load data; identifying a structure weak point based on the impact load data; performing fatigue crack evolution according to the structure weak points to generate glass crack data; identifying a crack shape based on the glass crack data to obtain zigzag glass crack data and radial glass crack data; and performing grain interface detection based on the zigzag glass crack data to obtain grain interface data. Based on a glass product manufacturing technology, the strength retention rate and the parameter adjustment precision rate in the glass bottle lightweight production process are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of glass product manufacturing, in particular to a production parameter optimization method and system for lightweight glass bottles and a medium. BACKGROUND

[0002] Traditional lightweight glass bottle production fails to combine glass bottle structure characteristics for systematic lightweight modeling analysis, often relying on experience to adjust the bottle body or bottom design, lacking standardized processing and structure reconstruction process, resulting in limited lightweight effect; in the impact performance evaluation process, only static strength simulation is usually based on, ignoring local stress concentration, crack propagation path and fatigue life evolution caused by impact load, and the structure weak point and crack type cannot be accurately identified; in the crack data identification aspect, the fine identification of crack geometric features (such as jagged undulation, radial path, etc.) is lacking, and different forms of crack structure cannot be effectively distinguished, resulting in subsequent optimization difficult to target; in the grain boundary and bubble impurity analysis aspect, there is a lack of comprehensive identification means for microcrystal structure and glass optical properties, and impurity detection and parameter back calculation cannot be carried out through grain boundary identification and light spot blur characteristics; in the melting and annealing process parameter optimization process, a multi-dimensional data feedback mechanism based on crack morphology, density intersection and impact damage evaluation is not established, resulting in parameter optimization lacking in pertinence, low production process adjustment efficiency and uncontrollable effect, and it is difficult to meet the high-performance production demand of modern glass bottles with both strength and lightweight. SUMMARY

[0003] Therefore, it is necessary to provide a production parameter optimization method, system and medium for lightweight glass bottles to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a production parameter optimization method for lightweight glass bottles comprises the following steps:

[0005] Step S1: Obtain a glass bottle structure drawing and identify the bottle body structure and the bottle bottom structure; construct a lightweight glass bottle model according to the bottle body structure and the bottle bottom structure;

[0006] Step S2: Perform impact load simulation according to the lightweight glass bottle model to obtain impact load data; identify structure weak points based on the impact load data; perform fatigue crack evolution according to the structure weak points to generate glass crack data; identify crack shapes based on the glass crack data to obtain jagged glass crack data and radial glass crack data;

[0007] Step S3: Perform grain boundary detection based on the jagged glass crack data to obtain grain boundary data; perform bubble impurity identification according to the grain boundary data to obtain bubble impurity data; optimize glass bottle melting production parameters according to the bubble impurity data;

[0008] Step S4: determining annealing parameters according to the radial glass crack data; controlling the glass bottle production program according to the glass bottle melting production parameters and the annealing parameters.

[0009] The production of conventional lightweight glass bottles fails to combine the structural characteristics of glass bottles for systematic lightweight modeling analysis, often relying on experience to adjust the bottle body or bottom design, lacking standardized processing and structural reconstruction process, resulting in limited lightweight effect; in the impact performance evaluation process, only static strength simulation is usually based on, ignoring the local stress concentration, crack propagation path and fatigue life evolution caused by impact load, and the structural weak points and crack types cannot be accurately identified; in the crack data identification aspect, the fine identification of crack geometric features (such as dentiform undulation, radial path, etc.) is lacking, and different forms of crack structure cannot be effectively distinguished, resulting in subsequent optimization difficult to target; in the grain boundary and bubble impurity analysis aspect, there is a lack of comprehensive identification means for microcrystal structure and glass optical properties, and impurity detection and parameter backstepping cannot be carried out through grain boundary identification and light spot blur characteristics; in the melting and annealing process parameter optimization process, a multi-dimensional data feedback mechanism based on crack morphology, density intersection and impact damage evaluation is not established, resulting in parameter optimization lacking in pertinence, low production process adjustment efficiency and uncontrollable effect, which is difficult to meet the modern high-performance production demand for glass bottles with both strength and lightweight.

[0010] Preferably, step S1 is specifically:

[0011] Step S11: obtaining a glass bottle structure drawing and performing standardized processing to obtain a standardized glass bottle structure drawing;

[0012] Step S12: identifying a bottle body edge curve according to the standardized glass bottle structure drawing, and constructing a bottle body structure according to the bottle body edge curve;

[0013] Step S13: identifying a bottle bottom structure according to the standardized glass bottle structure drawing;

[0014] Step S14: identifying a high-redundancy material area based on the bottle body structure, and performing wall thickness distribution optimization on the high-redundancy material area to generate bottle body wall thickness optimization data;

[0015] Step S15: identifying a main stress area based on the bottle bottom structure, and performing support rib structure reconstruction on the main stress area to generate a bottle bottom support rib optimization structure;

[0016] Step S16: constructing a lightweight glass bottle model according to the bottle body wall thickness optimization data and the bottle bottom support rib optimization structure.

[0017] The application standardizes the glass bottle structure drawing paper, so that the original design information meets the unified specification in terms of format, size unit, structure annotation, etc., which helps the high-precision operation of subsequent automatic modeling and recognition algorithm, and guarantees the modeling accuracy from the source. The identification of the bottle body edge curve and the structure reconstruction make the glass bottle outer contour features complete and provide accurate geometric basis for wall thickness distribution analysis. The identification of the bottle bottom structure makes the bottom area where the glass bottle is stressed concentrated accurately extracted, which is convenient for identifying key bearing features and optimizing the structure. The identification of the high-redundancy material area combined with the wall thickness distribution optimization can remove excess material in non-key areas without affecting the overall mechanical performance, reduce the bottle body weight, and achieve the goals of raw material saving and lightweight. The identification of the main stress area combined with the support rib structure reconstruction further enhances the stability of the bottle bottom under impact and stacking load, and improves the local strength and crack resistance. The structure optimization data of the bottle body and the bottle bottom together constitute the lightweight glass bottle model, which makes the whole bottle structure maintain the necessary mechanical performance while realizing the minimum material configuration, providing accurate structure input for subsequent strength simulation, impact test, production and manufacturing. The whole process from structure drawing to lightweight modeling is connected, avoiding the local over-strengthening or weakness caused by experience-based design, improving the controllability and data-driven ability of the design, and providing structure basis and model support for subsequent process parameter optimization and high-performance glass bottle production.

[0018] Preferably, step S2 is specifically:

[0019] Step S21: performing impact load simulation according to the lightweight glass bottle model to obtain impact load data;

[0020] Step S22: statistically calculating the stress concentration area of the glass bottle based on the impact load data; calculating the thickness gradient based on the stress concentration area of the glass bottle, and determining the structure weak point according to the thickness gradient;

[0021] Step S23: performing crack propagation simulation according to the structure weak point to obtain crack data;

[0022] Step S24: predicting fatigue life based on the crack data to obtain fatigue life data;

[0023] Step S25: identifying low-life cracks based on the fatigue life data to obtain glass crack data;

[0024] Step S26: identifying crack shapes based on the glass crack data to obtain sawtooth glass crack data and radial glass crack data.

[0025] The present application can accurately reflect the instantaneous stress response of the bottle body under actual falling, collision and other conditions through the impact load simulation of the lightweight glass bottle model, so that the distribution characteristics of the impact force in time sequence and space can be quantified; further, in combination with the stress concentration area information of stress data statistics, the position and distribution trend of the stress extreme value can be identified, thereby providing a scientific basis for subsequent structure risk assessment. The calculation of the weak point by using the thickness gradient can effectively judge the local mechanical disadvantage area caused by uneven wall thickness, and realize the accurate positioning of the structure weak link. Subsequently, by simulating the crack propagation process of these weak areas and combining the crack driving mechanism of glass brittle materials under different stress states, the complete path of the crack from initiation to fracture can be restored, and the crack characteristic data with physical basis can be obtained. On this basis, the fatigue life prediction can be carried out in combination with the crack length, propagation rate and stress intensity factor change, so as to quantify the sustainability life of the crack under the periodic impact action, and provide a quantitative basis for the time sequence prediction of fatigue failure. Further, based on the fatigue life data, the low-life cracks can be identified, which helps to screen out the crack characteristics that are more likely to fail in a short period of time on the surface or structure of the bottle body, and provides data support for strengthening and design correction of the key areas. In the crack shape identification link, through image processing and geometric feature matching technology, the sawtooth crack with periodic sharp corner characteristics and the radial crack with concentrated radiation characteristics can be accurately distinguished in the complex crack shape, so as to realize the classification and labeling of the crack type, effectively support the subsequent directional structure optimization or process adjustment operation for different crack shapes, and build a precise feedback path from microcrack evolution to macrostructure optimization, thereby improving the pertinence and closed-loop capability of the whole production optimization system.

[0026] Preferably, step S23 is specifically:

[0027] Step S231: importing the structure weak point into the crack propagation simulation software;

[0028] Step S232: setting the crack length range as 0.05mm-1mm, the crack angle range as 0°-90° and the crack tip radius range as 0.005mm-0.1mm in the crack propagation simulation software;

[0029] Step S233: setting the cyclic load range as 0.1MPa-2MPa, the impact load range as 10N-200N and the simulation step range as 100-10000 steps in the crack propagation simulation software;

[0030] Step S234: setting the fracture toughness range of the glass material as 0.5MPa·m 0.5 -1.5MPa·m 0.5 and the critical stress intensity factor range as 0.7MPa·m 0.5 -2.0MPa·m0.5 ;

[0031] Step S235: running a crack simulation program, and extracting crack evolution characteristic data according to the crack propagation path and the propagation rate, so as to obtain crack data.

[0032] The present application focuses on the actual stress most sensitive area by introducing the structural weak point into the crack propagation simulation software, ensures that the simulation results correspond closely to the real failure mechanism; sets the crack length, angle and tip radius parameter range, which can comprehensively cover various combinations of the initial state of micro-cracks, enhances the adaptability and reliability of the model under the micro-scale; sets the range of cyclic load and impact load and cooperates with reasonable simulation step control, so that the evolution path of the crack propagation behavior under the alternating action of quasi-static and dynamic load can be fully displayed, so as to capture the dynamic evolution trend of the crack in the high-frequency impact and fatigue process; set the fracture toughness and critical stress intensity factor range of the glass material, combine the material intrinsic property to build the fracture critical criterion, so that the crack can be dynamically judged whether it reaches the propagation or instability condition in the simulation process, and the physical accuracy of the crack driven model is improved; in the process of running the crack simulation program and extracting the crack evolution characteristic data, not only the complete trajectory information of the crack initiation, propagation and termination can be obtained, but also the response curve of the propagation rate changing with the load, angle and material parameter can be output, which provides a strong data basis for subsequent fatigue life prediction, crack morphology classification and high-risk structure adjustment, and then establishes a precise micro-macro failure mechanism chain, and improves the strength control and production process feedback ability of the glass bottle under the premise of lightweight.

[0033] Preferably, step S26 is specifically:

[0034] Step S261: collecting crack coordinate points based on the glass crack data, and reconstructing a curve based on the crack coordinate points to obtain crack boundary data;

[0035] Step S262: identifying a crack inner edge contour according to the crack boundary data; calculating a contour fluctuation frequency based on the crack inner edge contour; and identifying a crack edge fluctuation tooth segment according to the contour fluctuation frequency;

[0036] Step S263: calculating a fluctuation amplitude according to the crack edge fluctuation tooth segment; and collecting a jagged glass crack according to the fluctuation amplitude to obtain jagged glass crack data;

[0037] Step S264: identifying a crack branch intersection point based on the glass crack data; identifying a crack extension path according to the crack branch intersection point; and calculating a crack path initial included angle according to the crack extension path;

[0038] Step S265: calculating a direction angle distribution uniformity based on the crack path initial included angle; identifying the radial glass crack according to the direction angle distribution uniformity to obtain the radial glass crack data.

[0039] The present application significantly improves the accuracy and resolution of crack morphology identification by fine identification and type classification analysis of the geometric characteristics of glass cracks, thereby providing accurate data support for glass bottle structure optimization. Collecting crack coordinate points and performing curve reconstruction can restore the true boundary morphology of the crack, forming a quantifiable and analyzable boundary data basis, which helps subsequent geometric feature extraction and pattern recognition; by identifying the inner edge contour and calculating the number of fluctuations, the fluctuation characteristics of the crack edge can be quantitatively described, and cracks with obvious tooth segment characteristics can be accurately identified, providing a judgment standard for extracting jagged cracks; the calculation of fluctuation amplitude further strengthens the geometric recognition logic of crack types, making the jagged crack data have a clear threshold and a determinable boundary basis; identifying the crack branch intersection point and its extension path can reconstruct the crack multi-branch propagation characteristics and capture the spatial distribution of direction change and path intersection behavior in the crack propagation process; calculating the direction angle distribution uniformity based on the path initial included angle can reveal the radial symmetry or concentration characteristics of crack propagation, enabling accurate identification of radial cracks; finally, fine classification data of two typical crack types is formed, providing structural basis and geometric model support for subsequent targeted reinforcement design, forming die optimization and annealing process adjustment according to crack types, while also laying the foundation for establishing a structure-performance-morphology feedback closed-loop mechanism for glass bottle forming process, improving the identification ability and response efficiency of the production system for different crack types.

[0040] Preferably, the grain boundary detection in step S3 is specifically:

[0041] Identifying a sharp turning region based on the jagged glass crack data;

[0042] Identifying an edge fluctuation mutation region based on the jagged glass crack data;

[0043] Performing grain region intersection operation according to the sharp turning region and the edge fluctuation mutation region to identify a grain region;

[0044] Performing electron backscatter diffraction based on the grain region to obtain electron backscatter diffraction data;

[0045] Constructing a crystal orientation map according to the electron backscatter diffraction data;

[0046] Calculating an adjacent point orientation difference angle based on the crystal orientation map;

[0047] Identifying a grain boundary according to the adjacent point orientation difference angle to obtain grain boundary data.

[0048] The present application helps to extract potential microstructure change clues from the crack morphology by identifying sharp turning regions and edge fluctuation mutation regions based on sawtooth crack data, enhances the spatial positioning accuracy of the crack and the internal grain correlation of the material; through the intersection operation of the grain region, the complex crack characteristics and the actual grain structure are accurately mapped, providing a high confidence reference area for microstructure analysis; based on the above-mentioned area, electron backscatter diffraction testing is implemented, which can effectively collect the internal microcrystal arrangement state of the glass, and provide a data basis for further revealing stress-induced grain rearrangement and crystal orientation change; after constructing the crystal orientation map, the crystal direction distribution visualization of each local point of the material can be realized, providing reliable support for evaluating the anisotropy of the material and the formation mechanism of local microdefects; further calculating the orientation difference angle of adjacent points can quantify the crystal orientation change intensity, which is helpful for fine identification of the grain boundary range and determination of important parameters such as grain size and distribution density; the finally obtained grain interface data not only reveals the internal structure characteristics of the glass material, but also provides targeted parameter support on the microscale for glass composition adjustment, melting temperature control, annealing homogenization and strengthening treatment process optimization, fundamentally makes up for the uncertainty caused by traditional reliance on macroscopic experience judgment, and realizes the multi-objective synergistic improvement of light weight glass bottles in strength, reliability and process adaptability.

[0049] Preferably, the bubble impurity recognition in step S3 is specifically:

[0050] According to the grain interface data, the interface curvature is calculated;

[0051] Based on the interface curvature mutation point is identified;

[0052] According to the interface curvature mutation point, the glass refractive index is calculated;

[0053] According to the glass refractive index, the refractive index discontinuous region is identified, and the spot blur detection is performed on the refractive index discontinuous region to obtain spot blur data; based on the spot blur data, the spot blur boundary is identified;

[0054] According to the spot blur boundary, the cavity structure recognition is performed to obtain cavity structure data;

[0055] Based on the cavity structure data, the bubble impurity detection is performed to obtain bubble impurity data.

[0056] The present application can quantify the geometric deformation degree of the grain boundary by calculating the interface curvature, and reveal the potential structural stress concentration area; the identification of the interface curvature mutation point can further accurately locate the interface distortion area caused by abnormal grain growth or uneven crystallization process, and provide structural source basis for subsequent optical behavior abnormalities; based on the mutation point calculation of the glass refractive index, it is helpful to establish the mapping relationship between the grain structure and the refractive index distribution, and to improve the local analytical ability of optical property evaluation; the identification of the refractive index discontinuous area and the spot blur detection of the area can capture the actual influence of the internal microscopic defects of the glass on the light propagation behavior, thereby establishing the response mechanism between the refractive index anomaly and the visual blur area; through the identification of the spot blur boundary, the distribution profile of the optical anomaly can be clearly outlined, and the spatial range and morphological characteristics of the cavity structure are further positioned, thereby providing boundary constraints for defect accurate detection; the identification of the cavity structure establishes a structural basis for the existence and diffusion mechanism of the bubble impurities, which is helpful to combine the cavity morphology and the bubble behavior to carry out physical model fitting and process source tracing; and finally, the bubble impurity data obtained can effectively support the purity evaluation, composition improvement and melting parameter adjustment of the glass product, thereby making up for the problems of optical anomaly recognition lag, impurity detection system in the traditional process, and realizing the through modeling analysis from the grain structure, interface characteristics to the optical performance and bubble defects, thereby effectively improving the glass bottle quality stability and the controllability of lightweight production.

[0057] Preferably, the optimization of the glass bottle melting production parameters in step S3 is specifically:

[0058] According to the bubble impurity data, the bubble impurity density is counted;

[0059] According to the bubble impurity data, the bubble impurity diameter is calculated;

[0060] Based on the bubble impurity density, the melting temperature is adjusted to obtain melting temperature adjustment data;

[0061] Based on the bubble impurity diameter, the stirring speed of the stirrer is improved to obtain stirring speed optimization data of the stirrer;

[0062] The melting temperature adjustment data and the stirring speed optimization data of the stirrer are integrated to obtain glass liquid dynamic homogenization parameters;

[0063] Based on the glass liquid dynamic homogenization parameters, the raw material ratio is adjusted to obtain the glass bottle melting production parameters.

[0064] The application helps to quantify the overall distribution level of the impurities in the glass by the statistics of the bubble impurity density, thereby evaluating the overall melting homogeneity and judging the systematicness of the impurity source; the calculation of the bubble impurity diameter provides a quantitative basis for the size characteristics of the impurities, which helps to identify the problems such as local melting disturbance or uneven stirring; adjusting the melting temperature based on the bubble density helps to optimize the fluidity of the glass liquid and the bubble precipitation condition, thereby promoting the bubble floating and escaping from the thermodynamic level and enhancing the uniformity of the raw material melting; increasing the stirrer speed based on the bubble diameter can improve the internal mixing effect of the glass liquid in the kinetic dimension, thereby promoting the rapid dispersion of large-size impurities and weakening the defect influence on the final product; integrating the melting temperature and the stirrer speed, which are two kinds of key process data, into the dynamic homogenization parameter can realize the dynamic regulation and real-time evaluation of the glass liquid state, and promote the formation of a multi-factor coordinated control strategy considering the heat supply and flow field disturbance; finally, adjusting the raw material ratio based on the dynamic homogenization parameter can not only adjust the proportion of each component according to the current glass liquid state, but also further improve the impurity containment and optimize the melting balance, thereby effectively avoiding the problems such as lack of basis for raw material adjustment and large fluctuation of melting efficiency in the traditional process, realizing the precise control of the glass bottle melting process and the high consistency of the lightweight quality, and meeting the intelligent manufacturing needs of modern high-performance glass products.

[0065] Preferably, the present specification also provides a production parameter optimization system for lightweight glass bottles for executing the production parameter optimization method for lightweight glass bottles as described above, the production parameter optimization system for lightweight glass bottles comprising:

[0066] A lightweight glass bottle model construction module is configured to acquire a glass bottle structure drawing and identify a bottle body structure and a bottle bottom structure; and construct a lightweight glass bottle model according to the bottle body structure and the bottle bottom structure.

[0067] A crack shape identification module is configured to simulate impact load according to the lightweight glass bottle model to obtain impact load data; identify a structural weak point based on the impact load data; generate glass crack data by performing fatigue crack evolution according to the structural weak point; and identify a crack shape based on the glass crack data to obtain sawtooth glass crack data and radial glass crack data.

[0068] A melting production parameter optimization module is configured to perform grain boundary detection based on the sawtooth glass crack data to obtain grain boundary data; perform bubble impurity identification according to the grain boundary data to obtain bubble impurity data; and optimize glass bottle melting production parameters according to the bubble impurity data.

[0069] An annealing production parameter optimization module is configured to determine annealing parameters according to the radial glass crack data; and control a glass bottle production program according to the glass bottle melting production parameters and the annealing parameters.

[0070] The production parameter optimization system for lightweight glass bottles of the present application can realize any one of the production parameter optimization methods for lightweight glass bottles of the present application, and is used as a medium for joint operation and signal transmission between various modules to complete the production parameter optimization method for lightweight glass bottles.

[0071] Optionally, the present specification also provides a computer readable storage medium storing a computer program, which, when executed by a processor, implements any one of the production parameter optimization methods for lightweight glass bottles. BRIEF DESCRIPTION OF DRAWINGS

[0072] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the attached drawings:

[0073] Fig. 1 A step flow diagram of the production parameter optimization method for lightweight glass bottles of the present application;

[0074] Fig. 2 A detailed step flow diagram of step S1 in the present application;

[0075] The implementation of the present application, functional features and advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0076] The technical method of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0077] In addition, the accompanying drawings are only schematic illustrations of the present application, and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated description thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0078] It should be understood that, although the terms“first,”“second,” etc. can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element without departing from the scope of the example embodiments. The term“and / or” as used herein includes any and all combinations of one or more of the associated associated items.

[0079] To achieve the above object, please refer to Figs. 1-2 The application provides a production parameter optimization method for lightweight glass bottles, comprising the following steps:

[0080] Step S1: Obtain a glass bottle structure drawing and identify the bottle body structure and the bottle bottom structure; construct a lightweight glass bottle model according to the bottle body structure and the bottle bottom structure;

[0081] In this embodiment, the two-dimensional structure drawing of the glass bottle product is imported through the CAD software system to obtain the bottle body geometric contour and the bottle bottom thickness distribution. The boundary feature extraction is performed on the bottle body structure and the bottle bottom structure in the drawing by using a three-dimensional modeling tool such as SolidWorks, including the bottle opening inner diameter (for example, 26 mm), the bottle body maximum outer diameter (for example, 65 mm), the bottle body height (for example, 220 mm), the bottle bottom thickness distribution (for example, gradually changing from 8 mm at the center to 3 mm at the edge), and the like. The three-dimensional solid model is constructed in a stretching and rotating manner. In the modeling process, according to the national lightweight glass bottle standard (such as GB / T 4544-2021), the maximum wall thickness is constrained to be not more than 80% of the original thickness, the bottle bottom structure adopts a center reinforcing ring and a uniform slope structure, and the three-dimensional model is ensured to have lightweight design features, which is convenient for subsequent mechanical simulation and crack tracking calculation.

[0082] Step S2: Simulate the impact load according to the lightweight glass bottle model to obtain impact load data; identify the structural weak point based on the impact load data; perform fatigue crack evolution according to the structural weak point to generate glass crack data; identify the crack shape based on the glass crack data to obtain sawtooth glass crack data and radial glass crack data;

[0083] In this embodiment, on the basis of the built three-dimensional model, static and dynamic impact load simulation modules are introduced through finite element analysis software (such as ANSYS). Before applying the load, the model is divided into high-density tetrahedral mesh with the minimum unit edge length of 0.2 mm to enhance the simulation accuracy of stress concentration area. The load application mode includes free-fall impact test from top to bottom (the weight of the weight is 0.5 kg, the free-fall height is 1 m, and the initial impact speed is 4.43 m / s), which is applied at the widest part of the bottle body and the center area of the bottle bottom. The impact response time, maximum stress position, equivalent stress nephogram and node strain rate are recorded during the simulation process. The stress extreme point is identified by Von Mises criterion, and if the stress exceeds the glass limit strength value (for example, 40 MPa), the position is marked as a weak point of the structure. In the weak point area, the Paris-Erdogan fatigue crack propagation model is applied, the crack propagation coefficient is set to 1.2×10-11, the crack propagation index is set to 3.1, the crack path is tracked according to the stress intensity factor change curve, and the crack development length and direction are derived. The geometric features of the crack image are extracted by using image processing algorithm (such as Canny edge detection combined with Hough transform), and it is judged whether there is periodic tooth-shaped fluctuation (periodic interval <0.8 mm, depth >0.2 mm) to be classified as sawtooth crack, if it is linear radial divergent structure, the center density >6 lines / 100 mm 2 area, then it is classified as radial crack, and the position information and direction vector are recorded.

[0084] Step S3: detecting the grain boundary based on the sawtooth glass crack data to obtain grain boundary data; identifying the bubble impurities according to the grain boundary data to obtain bubble impurity data; and optimizing the glass bottle melting production parameters according to the bubble impurity data;

[0085] In this embodiment, for the identified sawtooth glass crack area, laser confocal microscope is used to scan the crack section, the scanning resolution is 100 nm, and the grain boundary gray scale change map is obtained. The scanning image is input into the boundary detection algorithm based on threshold segmentation (the threshold is set to the average value of the image gray scale plus 1.5 times the standard deviation) to extract the grain boundary interface map. The structure area with grain boundary length exceeding 20 μm and closure degree above 90% is identified as a complete grain area, and the average diameter and distribution density of the grains are counted. In the grain boundary interface map, the local phase mutation area is detected by combining the digital image phase recognition algorithm, and the bubble impurity area is distinguished by abnormal refractive index. The refractive index recognition standard is that the circular or elliptical dark spot area with a size of more than 5 μm and a relative background average refractive index deviation of more than 15% is determined as a bubble impurity, and the bubble position and density data (such as the number of impurities per square millimeter > 5 is a high-density area) are generated. The bubble impurity area and its corresponding coordinate position are mapped to the glass melting process history database to retrieve the temperature control trajectory corresponding to the position, and to identify whether the temperature fluctuation in the temperature control area exceeds the set threshold (for example, ± 15°C). If it exceeds, adjust the temperature control setting value of the main melting zone temperature control point in the melting stage (such as from 1450°C to 1435°C), and adjust the stirring frequency (such as from 20 times per minute to 30 times per minute) to reduce bubble aggregation.

[0086] Step S4: determining annealing parameters according to the radial glass crack data; controlling the glass bottle production program according to the glass bottle melting production parameters and the annealing parameters.

[0087] In this embodiment, the crack center position, length, density and diffusion angle are quantitatively analyzed. In the radial crack area of the bottle body and the bottle bottom, the three-dimensional space coordinates of the cracks are obtained by high-resolution industrial CT scanning, the scanning resolution is set to 50 μm, and the start point coordinates, direction vector and length information of each crack are derived after volume reconstruction. According to the crack length exceeding 10 mm and the crack density exceeding 6 lines / 100 mm 2The annealing temperature control points are set in the high stress concentration area, and the annealing temperature control points are measured by multi-point thermocouples. The temperature at the center of the bottle body is 550°C, the temperature at the shoulder area is 545°C, and the temperature at the center of the bottle bottom is 530°C. The temperature difference is controlled within ±2°C, and the holding time is set to 90 minutes. The annealing slow cooling rate is controlled by adjusting the air duct and radiation cooling. The temperature is reduced by 50°C per hour, and the temperature gradient control is set between the bottle body and the bottle bottom. The cooling rate at the periphery of the bottle bottom is controlled at 45°C per hour, and the main body of the bottle body is controlled at 50°C per hour. The uniform cooling is achieved by controlling the distance between the cooling plate and the bottle body within 15 cm. The air flow in the annealing furnace is monitored in real time by an anemometer, and is maintained between 3.5 m / s and 4.0 m / s to ensure uniform heat transfer. During the annealing process, the temperature curve of six key measurement points is recorded every 15 minutes to adjust the heating tube voltage, so that the local temperature fluctuation is not more than ±2°C. The melting temperature, melting furnace temperature control point, blowing mold closing pressure, blowing speed and annealing parameters are comprehensively formed into an automatic control instruction sequence. In the melting stage, the main melting zone temperature control is set to 1435°C, and the auxiliary melting zone is set to 1420°C. The temperature value is recorded every 5 seconds by monitoring with a platinum rhodium thermocouple, and the control temperature points with a deviation of more than ±3°C are automatically adjusted to 105% or 95% of the rated power to correct the temperature difference. In the forming stage, the mold closing pressure is set to 5.2 MPa, the inner diameter of the bottle mouth is controlled within 26 mm±0.1 mm, the maximum outer diameter of the bottle body is controlled within 65 mm±0.2 mm, the blowing gas flow is set to 12 L / s, the blowing time is 3.5 seconds, and the mold is kept closed for 1.2 seconds after blowing to ensure the stability of the bottle bottom structure. The annealing stage is executed according to the above-mentioned annealing parameters. After annealing, the bottle body is sent to the slow cooling area by the automatic conveying system. The slow cooling air speed is maintained at 3.8 m / s by an adjustable air valve, and the cooling time is controlled for 180 minutes until the bottle body temperature drops to room temperature 25°C. The whole production process is executed by a PLC controller, and the program cycle period is set to 500 bottles per batch. The temperature, pressure, time and flow parameters are recorded in the database in real time to realize accurate parameter control and traceability in batch production process.

[0088] Preferably, step S1 is specifically:

[0089] Step S11: Obtain a glass bottle structure drawing and perform standardization processing to obtain a standardized glass bottle structure drawing;

[0090] In this embodiment, the original glass bottle structure drawing is imported into the CAD standard processing system in DWG format, and the drawing source is the production design drawing provided by the glass container manufacturing enterprise. First, the two-dimensional drawing preprocessing module is used to detect the structural normativity of the drawing, and the boundary lines of the bottle body contour, neck, shoulder, bottom, etc. are identified. Through the boundary topology analysis function, the errors such as heavy lines, broken lines and suspended points in the drawing are excluded, the geometric topology structure is ensured to be complete, all units are unified to millimeters, the default scale is set to 1:1, and the layer attributes are standardized. The bottle body contour is set to "structure contour layer", and the bottom structure is set to "bottom structure layer". If there are multiple view structures (front view, top view, sectional view, etc.) in the drawing, projection alignment algorithm is used for graphic registration to ensure the consistency of three-dimensional information. After standardization processing, a standardized glass bottle structure drawing (output format is STEP or IGES file) containing only standard layers, unified units and topology error-free is output.

[0091] Step S12: identifying the bottle body edge curve according to the standardized glass bottle structure drawing, and constructing the bottle body structure according to the bottle body edge curve;

[0092] In this embodiment, in the standardized glass bottle structure drawing, the bottle body edge curve is identified by a geometric contour extraction algorithm, and the bottle body edge detection path is set to scan from the bottle opening starting point to the bottom direction with a scanning interval of 0.2 mm. In the edge extraction, spline fitting technology is used to reconstruct the discrete edge points extracted into continuous bottle body contour curve through cubic B-spline curve. The main features of the bottle body edge curve include the change rate of the shoulder radius, the taper of the bottle body, and the curvature of the transition section between the bottle opening and the bottom. All curves are converted into parametric curve expressions to support subsequent construction of rotating entities based on contour line rotation axis. According to the edge curve rotating around the center axis (z-axis) by 360°, the complete bottle body structure is constructed by entity rotation modeling technology. The initial definition of the bottle body cross-sectional thickness is 3.5 mm, and the wall thickness attribute tag is embedded in the modeling for subsequent wall thickness optimization calculation.

[0093] Step S13: identifying the bottle bottom structure according to the standardized glass bottle structure drawing;

[0094] In this embodiment, by identifying the layer "bottom structure layer" to which the bottle bottom part belongs in the standardized drawing, all the geometric boundaries of the bottle bottom are extracted. The bottle bottom is divided into three parts: bottom center, support ring, and bottom outer edge by using boundary grouping algorithm. For the bottom center area, it is detected whether the center symmetry meets the design requirements. If the deviation exceeds 1 mm, the center point is refitted. When identifying the geometric features of the support ribs, the boundary contour closure detection method is used, which requires each rib structure to be a closed path and the angle with the bottle bottom center to be equally spaced (for example, six ribs, the angle is 60°). The thickness data of the bottle bottom is extracted, and the thickness extraction probe technology is used to project the section line along the vertical direction to the bottom surface to obtain the thickness data at every 10° angle of the bottom. The thickness measurement accuracy is set to 0.1 mm. Finally, the bottle bottom geometric structure file is output, including the bottom center diameter (such as 12 mm), the support ring width (such as 5 mm), and the rib structure number and distribution information.

[0095] Step S14: identifying the high-redundancy material area based on the bottle body structure, and optimizing the wall thickness distribution of the high-redundancy material area to generate bottle body wall thickness optimization data;

[0096] In this embodiment, finite element mesh partitioning is performed on the constructed bottle body structure, and the entire bottle body area is partitioned with a 0.3 mm grid size to generate a structure with uniform grid density. The volume thickness distribution analysis algorithm is used to calculate the wall thickness data of every 2 mm section along the height direction of the bottle body. Local extreme value analysis is performed on the wall thickness data to identify the area where the wall thickness is greater than the average wall thickness (based on 3.5 mm) + 1.0 mm as the high-redundancy material area. The redundant area is reconstructed in the form of a parameterized surface. Under the premise that the minimum wall thickness is not less than 2.0 mm and the local wall thickness gradient is not greater than 0.2 mm / mm, the wall thickness is gradually optimized by using geometric stretching and contraction operations. Bezier curve control point transformation technology is used to adjust the curvature during wall thickness adjustment to ensure smooth transition of wall thickness contraction. After optimization, a new wall thickness distribution data file is generated, recording the wall thickness value corresponding to each bottle body height position, saved in CSV format for subsequent model calling.

[0097] Step S15: identifying the main stress area based on the bottle bottom structure, and reconstructing the support rib structure of the main stress area to generate an optimized bottle bottom support rib structure;

[0098] In this embodiment, the stress analysis of the support rib area defined in the bottle bottom structure is performed, and the vertical upward internal pressure (e.g. 0.5 MPa) and the vertical downward external force (e.g. 10 N impact force) are loaded for simulation, and the stress concentration area is extracted. The equivalent stress distribution map is used to determine whether the rib structure has uneven stress area. The area with stress greater than 35 MPa is identified as the main stress area. The topology reconstruction method based on vector optimization is used to optimize the rib shape in this area. The original support rib design is changed from a rectangular rib to a circular arc rib structure, with a circular arc radius of half the rib width, and an R0.5 fillet transition between the rib bottom and the bottle bottom. After reconstruction, the number of rib structures remains unchanged, and the cross-sectional shape of the optimized rib is a trapezoidal structure (top width 1.5 mm, bottom width 3.0 mm, height 2.5 mm), which improves the support stability of the rib body to the bottle bottom. The output rib structure optimization file is in IGES format, which is used to merge into the final glass bottle model.

[0099] Step S16: Construct a lightweight glass bottle model according to the bottle wall thickness optimization data and the bottle bottom support rib optimization structure.

[0100] In this embodiment, the bottle wall thickness optimization data and the bottle bottom support rib optimization structure are imported into the modeling module. In the original bottle body rotation structure, the wall thickness value corresponding to each cross-sectional height is replaced with the optimized value through control point coordinate adjustment, and the three-dimensional curved surface offset algorithm is used to realize accurate wall thickness construction. Boolean operation merging operation is performed on the bottle bottom structure, and the optimized rib structure is embedded into the central area of the bottle bottom. During the merging process, the model topology consistency is checked, the overlapping lines in the intersection area are eliminated, and the material properties are unified to sodium calcium glass (density 2500 kg / m 3 , Poisson's ratio 0.23, Young's modulus 70 GPa). Finally, a lightweight glass bottle model is generated, and the model output format is.STEP and.STL, which is used for numerical simulation verification and 3D printing manufacturing verification. The model structure includes an optimized wall thickness attribute tag and a support rib structure description tag.

[0101] Preferably, step S2 specifically comprises:

[0102] Step S21: Simulate the impact load according to the lightweight glass bottle model to obtain impact load data;

[0103] In this embodiment, after obtaining the lightweight glass bottle model, the three-dimensional model is imported into the finite element analysis tool ABAQUS 2023, and the Explicit dynamics solver provided by the software is used to perform impact load simulation. The loading condition is set to vertical impact, and a rigid plate is used to apply a transient impact load to the bottom of the glass bottle. The impact speed is set to 3.5 m / s, corresponding to a bottle drop height of about 0.65 meters in the transportation process. The glass bottle material properties are set to typical sodium calcium glass with a density of 2.5 g / cm 3, the elastic modulus is 70 GPa, the Poisson's ratio is 0.22, and the fracture strength is set to 55 MPa. The mesh is divided by C3D10 element type, and the element size is controlled below 1.5 mm to ensure calculation accuracy. By applying the load and performing dynamic analysis with a time step of 0.001 s, the stress-strain data of each node of the bottle body during the impact process is extracted, and the output format is ODB file, which is converted to CSV format and named "impact_stress_data.csv".

[0104] Step S22: Statistically analyze the stress concentration area of the glass bottle based on the impact load data; calculate the thickness gradient based on the stress concentration area of the glass bottle, and determine the structural weak point according to the thickness gradient;

[0105] In this embodiment, the impact load data obtained in step S21 is imported into MATLAB R2022b for stress analysis and processing. First, the maximum principal stress of the grid nodes of the bottle body is extracted using the user-defined function stress_cluster_region.m, and the spatial clustering algorithm DBSCAN (distance threshold eps = 2.5 mm, minimum neighborhood point number minPts = 10) is used to identify the stress significantly concentrated area. For each stress concentration area identified by clustering, the wall thickness information within a radius of 0.5 cm around it is sampled, and the calculation formula: gradient G = |T_max-T_min| / D is used, where T_max and T_min represent the maximum and minimum wall thickness values within the radius range, respectively, and D is the sampling diameter. Points with a thickness gradient greater than 0.12 mm / cm are defined as structural weak points, and their three-dimensional coordinate positions are recorded to the structural weak point database (named weak_point_set.json) as input parameters for subsequent crack simulation analysis.

[0106] Step S23: Perform crack propagation simulation according to the structural weak point to obtain crack data;

[0107] In this embodiment, the Workbench module in the crack propagation simulation tool ANSYS2022R2 is used to simulate crack propagation. The three-dimensional coordinates of the structural weak points in step S22 are read, and initial crack defects are introduced at these positions in turn. The defect length is set to 0.3 mm, and the crack type is Mode-I open crack. The Smeared Crack model is selected for crack propagation analysis, the material fracture toughness is set to 0.8 MPa·m^0.5, and the mesh is locally encrypted to 0.3 mm unit size. The load mode is consistent with step S21, and the instantaneous impact condition is adopted, and the simulation time is set to 0.005 s. The crack front displacement, propagation length and principal stress direction at each time step during the simulation are extracted, and the crack data file "crack_propagation_results.csv" is exported, recording the crack initiation time, propagation path, crack face angle and final crack length of each weak point.

[0108] Step S24: predicting fatigue life based on crack data, obtaining fatigue life data;

[0109] In this embodiment, the material fatigue analysis standard ASTM E739 is used for fatigue life prediction. The crack data output by step S23 is used as the input parameter, and the Paris law model is used for crack propagation rate calculation, the model expression is: da / dN=C*(ΔK)^m, where C is 1.5×10^-10, m is 3.1, and ΔK is the crack tip stress intensity factor range. According to the stress intensity factor of each crack point in the simulation process, the crack propagation rate is calculated, and then combined with the crack initial length of 0.3 mm and the critical failure length of 5.0 mm, the numerical integration method is used to predict the fatigue load cycle number N_f required for crack propagation to failure. Finally, all the fatigue life values corresponding to the weak points are recorded in the fatigue life data table "fatigue_life_output.csv", and each record in the table contains crack number, position coordinates, fatigue life N_f (unit: cycles) and other fields.

[0110] Step S25: identifying low-life cracks based on fatigue life data, obtaining glass crack data;

[0111] In this embodiment, the fatigue life data in step S24 is imported into the Python environment, and pandas is called for data processing. The life threshold N_thresh is set to 8000 cycles, and the crack data below the threshold is used as the low life crack screening standard. Using the conditional filtering method: df[df['fatigue_life']<8000], all low life cracks are extracted, and their coordinates, initial length and final length and other parameters are counted and output to "glass_low_life_cracks.csv". In addition, the position of the corresponding crack on the three-dimensional glass bottle model is marked in space by the Open3D library, and a PLY format visualization file "low_life_cracks_model.ply" is generated, and the marking color is set to red RGB value (255, 0, 0).

[0112] Step S26: Based on the glass crack data, the crack shape is identified, and the jagged glass crack data and the radial glass crack data are obtained.

[0113] In this embodiment, the crack image data in step S25 is subjected to crack shape recognition, and the microscopic crack image is processed by image morphological analysis method, the image resolution is set to 1200x1200 pixels, and the input format is TIFF. First, the Canny edge detection algorithm (threshold values are 80 and 150) in OpenCV is used to extract the crack boundary, and then Hough transform is applied to identify the linear feature. The crack with linear feature density higher than 40% is determined as a radial crack. Subsequently, Fourier transform is performed on the crack contour to analyze the contour frequency characteristics, and the crack with frequency peak value distribution interval less than 10° is identified as a jagged crack. After identification, the radial cracks are output as "radial_cracks_info.json", and the jagged cracks are output as "ated_cracks_info.json". Each file includes crack number, type, boundary point set, average crack width and direction distribution, and other detailed parameter information, and different colors (blue for radial, green for jagged) are used for layered annotation and display in the three-dimensional model.

[0114] OpenCV in Canny edge detection algorithm (threshold values are 80 and 150) to extract the crack boundary, and then apply Hough transform to identify the linear feature. The crack with linear feature density higher than 40% is determined as a radial crack. Subsequently, Fourier transform is performed on the crack contour to analyze the contour frequency characteristics, and the crack with frequency peak value distribution interval less than 10° is identified as a jagged crack. After identification, the radial cracks are output as "radial_cracks_info.json", and the jagged cracks are output as "ated_cracks_info.json". Each file includes crack number, type, boundary point set, average crack width and direction distribution, and other detailed parameter information, and different colors (blue for radial, green for jagged) are used for layered annotation and display in the three-dimensional model.

[0115] Preferably, step S23 is specifically:

[0116] Step S231: Import the structural weak point into the crack propagation simulation software;

[0117] In this embodiment, after identifying the structural weak points, their three-dimensional coordinate data is exported in TXT format, with each record containing X, Y, Z three-axis coordinate information and the corresponding thickness gradient value. The file is named weak_zone_coords.txt. This coordinate data is imported into the Fracture Toolkit module in the crack propagation simulation platform ANSYS Workbench 2022R2. Through the "Initial Flaw Definition" function of this module, the defect points are inserted into the finite element model of the lightweight glass bottle point by point. The method of inserting the defect points is to manually define the initial position of the defect and use the volume method to cut a small size cavity into the solid structure. The local area corresponding to each structural weak point is extracted as a submodel, each submodel retains a boundary range of 20mmx20mmx5mm, all models use equivalent refined mesh, the element type is SOLID186, and the mesh size is controlled at 0.3mm to meet the crack propagation calculation accuracy requirements. Finally, the local submodel containing the structural weak point defects is saved as an analysis file submodel_with_flaws.wbpj.

[0118] Step S232: Set the crack length range to 0.05mm-1mm, the crack angle range to 0°-90°, and the crack tip radius range to 0.005mm-0.1mm in the crack propagation simulation software;

[0119] In this embodiment, in ANSYS Fracture Toolkit, for each structural weak point in the submodel, the initial crack geometric parameters are set. The crack length is set to the parameter range of 0.05mm to 1mm in the interface "Initial Flaw Geometry", the crack length interval is 0.05mm, and a total of 20 initial defect models of different lengths are generated; the crack angle is set to the rotation angle range of 0° to 90° with the X-axis as the reference axis, and one angle direction is generated every 15° to obtain 7 direction configurations; the crack tip radius is set to 0.005mm, 0.02mm, 0.05mm, 0.08mm, and 0.1mm, a total of 5 levels. Each combination generates a simulation configuration, a total of 700 simulation schemes (20x7x5) need to be run. The crack tip uses virtual crack propagation technology to simulate the open type crack tip, all cracks are set to three-dimensional elliptical shape, and the crack depth is set to 80% of the crack length. Each group of crack geometric configurations is established as an independent case to build an analysis scene, and is saved as an analysis input file named

[0120] "Flaw_L{length}_A{angle}_R{radius}.inp".

[0121] Step S233: In the crack propagation simulation software, the cyclic load range is set to 0.1-2 MPa, the impact load range is set to 10-200 N, and the simulation step range is set to 100-10000 steps;

[0122] In this embodiment, on the basis of the simulation model, the cyclic load and the impact load are defined in the Workbench load definition module. The cyclic load is applied to the boundary nodes of the glass bottle mouth, the load direction is perpendicular to the axis of the bottle body, the load range is 0.1-2 MPa, the load type is sine function, the frequency is set to 20 Hz, and the load amplitude is generated in 20 groups with an increment of 0.1 MPa from 0.1 MPa. The impact load simulates the impact of the bottle bottom contacting the ground, adopts the concentrated force loading mode, the load range is 10-200 N with an increment of 10 N, and 20 groups of impact scenarios are generated. Each cyclic+impact combination scenario is defined with a simulation step range from 100 steps to 10000 steps, the simulation time step is 0.0001 s, and the maximum simulation time is 1 s. The load definition is imported into ANSYS Mechanical in the FORTRAN user subroutine interface mode, the simulation load configuration script "load_sequence_config.f90" is generated, and all load configurations are recorded in the database "load_profile_database.db".

[0123] Step S234: In the crack propagation simulation software, the fracture toughness range of the glass material is set to 0.5-1.5 MPa·m 0.5 -1.5MPa·m 0.5 , the critical stress intensity factor range is set to 0.7-2.0 MPa·m 0.5 -2.0MPa·m 0.5 ;

[0124] In this embodiment, in the crack propagation analysis setting, according to the typical performance range of the glass material, the fracture toughness is set to 0.5 MPa·m 0.5, 0.8 MPa·m 0.5, 1.0 MPa·m 0.5, 1.2 MPa·m 0.5, 1.5 MPa·m 0.5, and a total of 5 groups of parameters are simulated for different material process possibilities. The critical stress intensity factor K IC is set to 0.7 MPa·m 0.5, 1.0 MPa·m 0.5, 1.5 MPa·m 0.5, 2.0 MPa·m 0.5, and a total of 4 groups of parameters. All crack front point calculations use the VCCT crack propagation criterion based on J integral. If the J integral corresponding to the K equivalent value exceeds the set K IC, it is considered as the crack propagation trigger condition. This setting is completed in the “Material Property Table”, and is specified as a nonlinear material behavior mode in the simulation solver control file. All parameter configurations are combined and nested in the previously described crack geometry and load configuration, and the total simulation combination number is 700 (geometry) x 20 (load) x 5 (toughness) x 4 (K IC) = 280,000 groups.

[0125] Step S235: running the crack simulation program, and extracting crack evolution feature data according to the crack propagation path and the crack propagation rate, so as to obtain crack data.

[0126] In this embodiment, after all the above parameter configurations are completed, the batch simulation running platform ANSYS BatchManager is called, and all 280,000 crack propagation simulation tasks are executed by using a 64-core parallel cluster server. After each simulation run, the crack propagation path is exported as a three-dimensional trajectory file (format.vtk), and the crack propagation rate is obtained by dividing the displacement of each step by the step length and stored as a CSV file. The Python program crack_feature_extractor.py is used to read all simulation result files and extract the following feature parameters: maximum crack length L max, average crack propagation rate V avg, crack propagation direction vector Δx, Δy, Δz, crack path deflection angle θ deflect, and crack shape change rate R shape. Finally, all data are summarized and output as a database “crack_growth_features.sqlite”, which includes fields including geometry configuration, load configuration, material parameter configuration, and various crack evolution features, and a total of more than 2 million records are generated. In order to facilitate analysis and visualization, Paraview is used to perform crack path animation generation on the.vtk data set, and output as a video sequence with a frame rate of 30 fps, which is used for subsequent analysis and evaluation.

[0127] Preferably, step S26 is specifically:

[0128] Step S261: Collect crack coordinate points based on the glass crack data, and reconstruct the curve based on the crack coordinate points to obtain crack boundary data;

[0129] In this embodiment, in the analysis process of the lightweight glass bottle crack evolution data, first, based on the crack data obtained in step S235, the coordinate point set of the crack in the three-dimensional space is extracted. The specific operation adopts laser confocal microscopic imaging technology to obtain the crack surface topography, uses 0.1 μm precision Z-axis focusing layer scanning to ensure the continuity of the surface profile, the image resolution is set to 2048x2048 pixels, and the image sampling accuracy is set to 1 μm / pixel. The edge detection method based on Sobel operator is used to extract the crack edge point profile, and the two-dimensional image coordinates are converted into actual coordinate points in the three-dimensional geometric coordinate system. Subsequently, the Catmull-Rom spline interpolation algorithm is used to reconstruct the continuous curve of the crack point set, avoiding the angle mutation between the discrete points, and the curve reconstruction accuracy is controlled to be less than 0.5%. The continuous curved surface profile of the crack boundary is generated from the reconstructed curve data, and the spatial geometric position information of all boundary points is exported as the crack boundary data, with the unit being millimeter (mm).

[0130] Step S262: Identify the crack inner edge profile according to the crack boundary data; calculate the profile fluctuation frequency based on the crack inner edge profile; identify the crack edge fluctuation tooth segment according to the profile fluctuation frequency;

[0131] In this embodiment, after obtaining the crack boundary data, the curvature analysis method is used to further identify the profile line of the crack inner edge. Specifically, the method of combining Gaussian curvature (K) and average curvature (H) is used to distinguish the local shape of the curved surface, and the threshold is set to K>0.05 mm -2 and H>0.1 mm -1 as the fluctuation significant area. By calculating the first derivative and the second derivative of each crack inner edge curve segment by segment, all continuous curvature change positive and negative alternating segments are extracted as the profile fluctuation segments. The minimum angle difference between adjacent fluctuation segments is set to 10°, and the minimum length difference is set to 0.1 mm, and the low frequency or weak disturbance profile is removed. The fluctuation frequency is obtained by numerical integration to obtain the total number of curvature extreme points, so as to count the fluctuation frequency of each profile. Based on the adjacent boundary curvature inversion of the continuous fluctuation segment, the local oscillation mutation segment, i.e. the fluctuation tooth segment, in the crack edge is identified, and the space length, number, density and other parameters of the fluctuation tooth segment are extracted, with the unit being mm.

[0132] Step S263: Calculate the fluctuation amplitude according to the crack edge fluctuation tooth segment; collect the jagged glass crack according to the fluctuation amplitude to obtain the jagged glass crack data;

[0133] In this embodiment, the extracted crack edge fluctuation tooth segments are quantified in terms of geometric characteristics. First, the vertical projection algorithm is used to calculate the maximum and minimum edge height difference in each fluctuation segment, and the value is defined as the fluctuation amplitude of the tooth segment. The fluctuation amplitude calculation accuracy requirement is not less than 0.01 mm, and the edge segment with a fluctuation amplitude greater than 0.08 mm is defined as a serrated feature area. Combined with the number and position of the edge fluctuation segments, the crack area meeting the amplitude standard is collected as the serrated glass crack. The data structure includes the spatial coordinate range of each serrated crack, the maximum amplitude value, the tooth density (unit: pieces / mm), and the average inclination angle of each tooth segment. By establishing a structured data table for such crack data, serrated glass crack data is generated for subsequent correlation analysis with processing parameters, cooling curves, and mold forming temperatures.

[0134] Step S264: identifying crack branch intersection points based on the glass crack data; identifying crack extension paths according to the crack branch intersection points; and calculating the crack path starting angle according to the crack extension paths;

[0135] In this embodiment, in the crack data structure, the crack branches and intersection points are identified based on the spatial curve geometric topology analysis method. First, the spatial trajectory of each crack path is parameterized, the path is reconstructed using a cubic Bezier curve function, and the intersection points are identified based on the criteria that the shortest distance between each path is less than 0.05 mm and the path angle is between 5° and 60°. All intersection points are labeled in the form of a point set, and their spatial position, connection path number, and intersection angle are preserved as structured attributes. Subsequently, based on the intersection points, a multi-path tracking operation is performed, and the tracking logic is based on the consistency principle, extending from the intersection point to the starting direction of each branch path. Each path is tracked to its endpoint where the curvature gradient change is less than 0.01, which is defined as the crack extension path. When calculating the starting angle of the crack path, the vector direction formed by the first 10 coordinate points of the crack from the intersection point is taken as the starting angle, and the calculation accuracy requirement is 0.1°. All angle values are saved in the crack structure data set for path structure analysis.

[0136] Step S265: calculating the uniformity of the direction angle distribution based on the crack path starting angle; and identifying the radial glass crack based on the uniformity of the direction angle distribution to obtain the radial glass crack data.

[0137] In this embodiment, the uniformity of the direction angle distribution is calculated based on the existing crack extension path and initial angle data. First, all crack path initial angle values are mapped to the spatial angle interval of [0°, 180°], and 18 direction intervals are divided with a 10° division unit. The number of cracks in each interval is counted and normalized. The distribution entropy value is calculated using the Shannon information entropy formula H = -∑p(i)log2p(i), and the distribution uniformity U = H / H_max is calculated according to the maximum uniform entropy H_max = log218≈4.17. The crack set with U greater than 0.85 is defined as a direction distribution with high uniformity. In combination with the crack trajectory morphology and starting point centrality in these sets, the direction uniform and outward divergent crack set is identified and marked as a radial glass crack. The center point coordinates, diffusion direction number, minimum and maximum angle range, direction entropy value, and path length average of each radial crack are recorded in the data, and finally a radial glass crack data set is formed for subsequent correlation analysis with the bottle cooling rate and thickness gradient.

[0138] Preferably, the grain boundary detection in step S3 is specifically:

[0139] Based on the jagged glass crack data, the sharp turning region is identified;

[0140] In this embodiment, first, jagged glass crack data is selected as the input data set, and a method based on vector angle analysis is used to identify the sharp turning region in the crack trajectory. Discrete processing is performed on each jagged path, and equidistant crack coordinate points are extracted with a step size of 1 μm. The included angle θ formed by three consecutive points is calculated, and the formula is: θ = arccos[(v1·v2) / (|v1||v2|)], where v1 and v2 are adjacent two vector segments. The included angles of all points are analyzed, and the angle threshold for identifying sharp turning regions is set to θ < 90°. When the length of the coordinate point set that continuously satisfies this condition is greater than 10 μm, it is defined as an effective turning section. To exclude false turning sections, the curvature jump index ΔK is introduced, and the average curvature change rate between consecutive turning points is calculated. The condition ΔK > 0.15 mm -1 is one of the judgment conditions. All regions that satisfy the above two conditions are marked as “sharp turning regions”, and their spatial positions, start and end point indexes, and curvature change sequences are output as data structures, with units of mm and rad (radians).

[0141] Based on the jagged glass crack data, the edge fluctuation mutation region is identified;

[0142] In this embodiment, the same jagged glass crack data is used as the basis to identify edge fluctuation mutation regions using the first derivative change rate method. First, based on each crack boundary curve, a function expression f(x) is constructed, the first derivative f'(x) of the curve is calculated, and then the second derivative f"(x) is calculated to obtain the acceleration of the boundary shape change. The fluctuation mutation judgment standard is set as follows: if the first derivative of the curve changes by more than 0.4 within 1 μm and the value of f"(x) is continuously greater than 0.3, it is considered that there is a mutation edge at this position. In order to identify continuous regions, a sliding window analysis method is introduced, the window length is set to 20 μm, the window step is 1 μm, and the proportion of points in each window that meet the mutation condition is analyzed; if the proportion exceeds 50%, the entire window is marked as an "edge fluctuation mutation region". The output content includes region index, curve slope distribution graph, number of mutation points, maximum mutation rate and spatial position, which are used for subsequent grain region judgment operations.

[0143] Grain region intersection operation is performed according to the sharp turning region and the edge fluctuation mutation region to identify the grain region;

[0144] In this embodiment, the above two region data are imported into a spatial Boolean operation module, and a spatial geometric body intersection algorithm is used to identify the grain region. In specific operation, first, a polygon envelope contour is constructed based on the turning region and the fluctuation mutation region, respectively, and a two-dimensional projection grid model is constructed based on Delaunay triangulation; the intersection operation is performed on the two region grids, and the judgment rule is as follows: if the overlapping area of the two regions is greater than 15 μm 2 , and the overlapping part contains at least 30 consecutive coordinate points, it is determined as a grain region. For each grain region, the output includes its boundary coordinate point set, center point coordinate, area value, perimeter, boundary curvature distribution and other geometric attribute information, with units of μm, μm 2 , forming a standard grain region data table.

[0145] Based on the grain region, electron backscatter diffraction is performed to obtain electron backscatter diffraction data;

[0146] In this embodiment, the EBSD detector equipped with a commercial scanning electron microscope is used to collect high-resolution diffraction data in the grain area. The preparation process includes: ion polishing the crack area sample to ensure that the surface roughness is less than 30 nm to ensure that the EBSD imaging signal is clear. The scanning electron microscope acceleration voltage is set to 20 kV, the sample inclination angle is set to 70°, the scanning step is set to 100 nm, and the EBSD screen sampling frequency is set to 100 Hz. Matrix scanning is performed on each grain area to obtain the Kikuchi pattern of each scanning point, and the image size is 640x480 pixels. The system automatically analyzes the image to extract the crystal orientation angle (Euler angle) and Bravais point position identifier (Miller index) of each point, generates electron backscattering diffraction data, and saves the data in.csv and.tiff formats, which contain spatial coordinates, orientation matrix, crystal structure identifier, and other information, with units of ° and μm.

[0147] Constructing a crystal orientation map according to the electron backscattering diffraction data;

[0148] In this embodiment, the crystal orientation map is constructed using color coding mapping based on the orientation matrix in the electron backscattering diffraction data. The Inverse Pole Figure (IPF) mapping scheme is used for map construction, and RGB color mapping is used for the

[001] direction,

[101] direction, and

[111] direction: R, G, and B value ranges are 0-255, respectively. After mapping the crystal principal axis direction of each measurement point to the RGB color space, a two-dimensional image is drawn, with an image resolution of 300 dpi and a map range equal to the EBSD acquisition area. Each pixel in the map corresponds to a measurement point location and contains color, orientation angle, and spatial coordinate information. In addition to the image, the map data is also output in a data matrix form, recording the RGB value, Euler angle group, and crystal direction index of each point, which is used for subsequent angle difference calculation.

[0149] Calculating the orientation difference angle between adjacent points based on the crystal orientation map;

[0150] In this embodiment, each measurement point in the crystal orientation map is traversed, and its four adjacent points above, below, left, and right are selected to calculate the Euler angle difference. The orientation difference angle calculation method is to use the principal axis difference between the orientation tensors, specifically using the Rodrigues transformation formula Δθ = arccos[(Trace(G1G2 -1 )-1) / 2], where G1 and G2 are the orientation tensors of two measurement points. The lower threshold for distinguishing valid differences is set to Δθ ≥ 5° to exclude small fluctuations within the grain. All points that meet the conditions are marked with coordinates, and a difference angle heat map is constructed. The angle difference size is represented by gray scale in the image, with black being 0° and white being the maximum 90°. The data is also output as a spatial mapping matrix, which is used for grain boundary determination.

[0151] According to the orientation difference angle of adjacent points, the grain boundary is identified, and grain interface data is obtained.

[0152] In this embodiment, according to the difference angle thermal map of adjacent points, the boundary points with continuous orientation difference angle Δθ≥10° are extracted, and are defined as high-angle grain boundaries. The region growing method based on edge connection is used to connect all high-angle difference points to form a closed path, and the grain boundary line is extracted. In order to avoid noise interference, the minimum boundary length threshold is set to 20 μm, and the boundary line less than the threshold is removed. The grain interface data structure includes fields such as boundary line segment start and end coordinates, boundary length, maximum orientation difference, adjacent grain index, and grain boundary average curvature. All interface data are output in table form for subsequent glass bottle stress direction heterogeneity analysis and production forming area backtracking processing.

[0153] Preferably, the bubble impurity recognition in step S3 is specifically:

[0154] According to the grain interface data, the interface curvature is calculated;

[0155] In this embodiment, after obtaining the grain interface data, a curvature reconstruction method based on discrete point set is used to calculate and process the point-by-point curvature of the interface profile. In the specific processing process, each continuous curve segment in the grain interface data is selected, and a least squares circular arc is constructed with 3 points at each center point using the circular arc fitting technology in surface differential geometry. The curvature κ is calculated by the formula κ = 1 / R, wherein R is the radius of the fitted circle. In order to ensure the calculation accuracy, the number of points used for fitting each segment is set to 7 (the first 3 points, the current point, and the last 3 points), and the curvature value of each point is smoothed by weighted moving average to reduce the error influence caused by abnormal fluctuations. For the boundary abnormal area, the curvature change gradient limit is used, and the gradient threshold Δκ = 0.05 mm -1 is set to identify the non-continuous area and remove its interference on the overall curvature field. The above curvature calculation operation is implemented in a two-dimensional interface image based on coordinate space, and the image resolution is 1 μm / pixel.

[0156] The interface curvature mutation point is identified based on the interface curvature;

[0157] In this embodiment, after the obtained curvature value sequence is arranged according to the spatial position, the first-order difference method is used to calculate the curvature change rate, and the formula is Δκi = κi+1- κi. On this basis, by setting the mutation recognition threshold θ_c = 0.15 mm -1, identify all position points satisfying |Δκi|≥θ_c as curvature mutation points. In the mutation identification process, the continuous difference strategy is adopted to screen out isolated wave points, and only the mutation segments satisfying the threshold condition for more than 3 are reserved to avoid misidentification. The above mutation identification process is realized by using the edge curvature mutation detection script written in Python language. The standard NumPy numerical processing library is called in the script for sequence calculation, and the point coordinates are returned to the original image space coordinates for subsequent positioning and labeling.

[0158] According to the interface curvature mutation point, the glass refractive index is calculated;

[0159] In this embodiment, the interface curvature mutation point position is projected to the refractive experiment platform of the glass bottle sample in the glass thickness direction, and the actual refractive angle change of each mutation point under light is measured by a laser interference measurement device. The experimental configuration is: the wavelength of the laser is λ=632.8nm, the incident angle is α=45°, the medium environment used is air, and the refractive index n0=1. According to Snell's law: n=n0·sin(α) / sin(β), wherein β is the refractive angle measured from the high frame rate camera system. The angle is sampled in units of 0.1°, and the measurement error is controlled within ±0.05°. Each mutation point is measured at least 3 times to take the average value to ensure stability, and the obtained refractive index is mapped to the curvature mutation point coordinates to generate a refractive index space distribution matrix.

[0160] According to the glass refractive index, the refractive index discontinuous region is identified, and the light spot blur detection is performed on the refractive index discontinuous region to obtain light spot blur data; and the light spot blur boundary is identified based on the light spot blur data;

[0161] In this embodiment, the refractive index spatial distribution matrix is subjected to two-dimensional difference analysis, and a refractive index mutation threshold η = 0.12 is set. Whether it is a discontinuous region is judged according to the difference |n(i+1, j)-n(i, j)|≥η or |n(i, j+1)-n(i, j)|≥η. In the discontinuous region, a local window size of 11x11 pixels is set, and the gradient distribution of the light spot image is analyzed by using the structure tensor method to judge the edge blur degree of the light spot. The light spot image is collected by a high-frame-rate industrial camera, and the gray value range is [0, 255]. The gradient is calculated by the Sobel operator, and the blur index is compared with the blur threshold γ_g = 25. If σ_g < γ_g, it is judged as a light spot blur area. The spatial position and corresponding gradient value of the blur area are output as light spot blur data. The region growing method is used to extract the boundary contour of the light spot blur data. The specific operation is as follows: select the blur center point with the smallest gray value in the blur area image as the seed point, set the growth condition as the blur degree gradient change less than Δσ_g = 5, expand the blur area pixel by pixel, and stop until all pixels meeting the condition are added to the region. After completion, the boundary line is generated on the edge of the blur area by the Canny edge detection algorithm. In the edge detection process, double threshold processing is adopted, in which the low threshold is T_low = 20 and the high threshold is T_high = 40, so as to reduce the interference of false edges. Finally, the boundary coordinate set constitutes the light spot blur boundary data.

[0162] The cavity structure data is obtained by identifying the cavity structure according to the light spot blur boundary.

[0163] In this embodiment, the light spot blur boundary data is mapped to the three-dimensional coordinate system of the glass bottle structure, and whether a closed region is formed is judged by the boundary closure degree. If there is no identifiable refractive structure in the closed region, and the average gray value inside is lower than the threshold μ = 50 (based on the 0-255 gray scale standard), the closed region is defined as a cavity structure. The three-dimensional reconstruction operation uses a stereo vision matching technology based on a double industrial camera (resolution 2048x2048 pixels, baseline length 100 mm) to perform depth modeling on the blur boundary. All identified cavity structures are output in the form of point cloud data, including information parameters such as three-dimensional geometric center, maximum inscribed circle diameter, and boundary roughness.

[0164] The bubble impurity data is obtained by detecting the bubble impurity based on the cavity structure data.

[0165] In this embodiment, the identified cavity structure is further subjected to internal imaging analysis by using a high-resolution X-ray image. The imaging parameters are set as voltage 60 kV, current 0.5 mA, exposure time 100 ms, and image resolution 5 μm / pixel. Texture analysis is performed on each cavity structure region, and the internal gray variance σ 2and the Energy term in the Gray Level Co-occurrence Matrix. The typical gray level variance of the bubble is between 150-300, and the Energy value below 0.15 is defined as a non-homogeneous structure region, which is determined as a bubble. All identified impurity bubble structures are marked with their positions, gray values, equivalent diameters, and shape factors (circularity), and output as a standardized structured data table.

[0166] Preferably, the optimization of the glass bottle melting production parameters in step S3 is specifically as follows:

[0167] According to the bubble impurity data, the bubble impurity density is calculated.

[0168] In this embodiment, the spatial coordinates and volume data marked as bubble impurities in the acquired cavity structure data are used to divide the glass bottle sample space into multiple cubic units with an edge length of 1 mm using a three-dimensional space grid division method. An industrial image recognition system (such as a FLIR high-definition infrared industrial camera combined with a structured light scanner) is used to obtain the spatial distribution position and size of the bubbles at the glass bottle wall or bottle center through multi-angle scanning. The number and total volume of bubbles contained in each cubic unit are counted, and the density calculation formula is ρ = N / V, where N is the total number of bubbles per unit volume, and V is the unit volume (i.e. 1 mm 3 ). After the calculation of multiple units is completed, the average bubble density of all units is taken as the bubble impurity density value of the current glass bottle, and the density value is recorded in the original structure database. The entire process uses a CNC motion platform and a precision positioning module to perform partition sampling and coordinate positioning, avoiding repeated calculation and missed detection.

[0169] According to the bubble impurity data, the bubble impurity diameter is calculated.

[0170] In this embodiment, based on each identified bubble structure region, a laser interference profiler is used for high-precision contour mapping, and a micro-focus microscopic image is used for edge extraction processing. The edge curve of each bubble is processed using a circle fitting algorithm for least squares fitting to obtain the diameter value d of the fitted circle, and all d values are stored in an array. The diameter data of the bubble is the maximum edge span of the bubble, which is obtained by taking the maximum value of the distance between the boundary points and the center point of each bubble contour and multiplying it by 2. The edge extraction threshold used in the measurement is set to a gray difference ΔI ≥ 15, and the bubble boundary accuracy is controlled within ±0.01 mm. The collected sample is not less than 1000 bubble data, and the mean, maximum, and standard deviation of the calculated bubble diameter are saved together as reference indicators for subsequent process adjustment.

[0171] Based on the bubble impurity density, the melting temperature is adjusted to obtain melting temperature adjustment data.

[0172] In this embodiment, the obtained bubble density p is judged, if p is greater than the set process critical density threshold p0 (p0 is set to 10 bubbles / mm 3 ), the melting temperature needs to be adjusted downward; if p is less than p0, the current temperature is maintained. The specific temperature adjustment method is as follows: assuming the current temperature T1 is 1450℃, when p> p0, the temperature is adjusted downward by AT = k·(p-p0), where k is the temperature sensitivity coefficient, which is set to 2℃·mm 3 / bubble. Example: if p = 14 / mm 3 , then AT = 2×(14-10) = 8℃, the adjusted melting temperature is T2 = 1442℃. The temperature adjustment process is performed by the automatic temperature control system, which connects the PLC system with the high-temperature zone electric heating module to realize degree-by-degree adjustment, with no more than 2℃ adjustment per minute, and continuously sampling the bubble density until it is lower than p0 for 30 consecutive minutes to stop adjustment. The adjustment result is stored as the melting temperature adjustment data T2, and is associated with the current batch production parameter record.

[0173] Based on the diameter of the bubble impurities, the stirring speed of the stirrer is increased to obtain stirring speed optimization data;

[0174] In this embodiment, the average bubble diameter D - obtained in the foregoing steps is compared with the target bubble diameter threshold D0, if D - > D0 (D0 is set to 0.6mm), the stirring speed of the stirrer in the glass melt needs to be increased. The adjustment coefficient a of the increased speed is An = a·(D - -D0), where a is set to 50rpm / mm. For example, if D - = 0.75mm, then An = 50×(0.75-0.6) = 7.5rpm, and the increased speed is 8rpm after rounding up. Assuming the current stirring speed of the stirrer is n1 = 60rpm, the new stirring speed n2 = 68rpm. The stirring speed of the stirrer is adjusted in real time by the central drive controller, and the new frequency value (such as 0.95Hz corresponding to 60rpm, and 1.08Hz corresponding to 68rpm) is set by the frequency converter, and the updated data is recorded as the stirring speed optimization data n2.

[0175] The melting temperature adjustment data and the stirring speed optimization data are integrated to obtain the glass liquid dynamic homogenization parameters;

[0176] In this embodiment, the melting temperature adjustment data T2 and the stirrer speed optimization data n2 are jointly encoded to construct a glass liquid dynamic homogenization parameter set {T2, n2}. The parameter set needs to meet the stability judgment condition, that is, the glass liquid temperature fluctuation range ΔT≤±3℃ and the stirrer speed fluctuation range Δn≤±2rpm within 3 hours of continuous monitoring. If the fluctuation exceeds the range, the previous adjustment steps need to be re-executed until the standard is met. The dynamic homogenization parameter set is uploaded to the process parameter optimization module in the MES system, assigned a unique batch number and a time stamp, and ensured that the subsequent raw material ratio adjustment is linked with the actual process equipment. The parameter is used as the reference input value for adjusting the ratio in the next stage.

[0177] The raw material ratio is adjusted based on the glass liquid dynamic homogenization parameters to obtain the glass bottle melting production parameters.

[0178] In this embodiment, four main raw materials, silica sand, soda ash, limestone and boric acid, are used. The silica sand ratio is adjusted according to T2 and n2 to increase the glass strength, and the basic ratio is set as silica sand 60%, soda ash 18%, limestone 10%, and boric acid 12%. When T2<1450℃, the silica sand ratio is increased by 1% to compensate for the viscosity change caused by the decrease in melting temperature; when n2>65rpm, the soda ash ratio is reduced by 1% and the boric acid ratio is increased by 1% to reduce the formation of stirring shear bubbles. Thus, the final ratio adjustment is: silica sand 61%, soda ash 17%, limestone 10%, and boric acid 12%. The ratio adjustment is performed by the automatic raw material batching system, and the mass of each batch is set by the weighing module (e.g. 1000kg of raw materials corresponds to 610kg of silica sand, 170kg of soda ash, etc.). After the ratio calculation, the control system is written and exported as glass bottle melting production parameters for archiving and used to control the feeding operation of the glass furnace. The data acquisition frequency of the whole process is once per minute, and it is automatically bound with the quality detection results.

[0179] Preferably, the present specification also provides a production parameter optimization system for lightweight glass bottles for performing the production parameter optimization method for lightweight glass bottles as described above, which comprises:

[0180] A lightweight glass bottle model construction module is configured to obtain a glass bottle structure drawing, identify the bottle body structure and the bottle bottom structure, and construct a lightweight glass bottle model according to the bottle body structure and the bottle bottom structure.

[0181] A crack shape identification module is configured to simulate impact load based on the lightweight glass bottle model to obtain impact load data, identify structural weak points based on the impact load data, perform fatigue crack evolution according to the structural weak points to generate glass crack data, and identify crack shapes based on the glass crack data to obtain sawtooth glass crack data and radial glass crack data.

[0182] The melting production parameter optimization module is used for detecting the grain boundary based on the jagged glass crack data, obtaining the grain boundary data, identifying the bubble impurities based on the grain boundary data, obtaining the bubble impurity data, and optimizing the glass bottle melting production parameter based on the bubble impurity data.

[0183] The annealing production parameter optimization module is used for determining the annealing parameter based on the radial glass crack data, and controlling the glass bottle production program based on the glass bottle melting production parameter and the annealing parameter.

[0184] Optionally, the present specification also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the production parameter optimization method for the lightweight glass bottle.

[0185] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, the scope of the present application being defined by the appended claims and not by the above description, and it is intended to encompass all variations falling within the meaning and the scope of the equivalent elements of the claims.

[0186] The above description is merely one specific implementation of the present application, which enables those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for production parameter optimization of lightweight glass bottles, characterized by, The method comprises the following steps: Step S1: Obtain a glass bottle structure drawing, and identify a bottle body structure and a bottle bottom structure; construct a lightweight glass bottle model according to the bottle body structure and the bottle bottom structure; Step S2: Simulate impact load according to the lightweight glass bottle model to obtain impact load data; identify a structural weak point based on the impact load data; perform fatigue crack evolution according to the structural weak point to generate glass crack data; Identify crack shapes based on the glass crack data to obtain jagged glass crack data and radial glass crack data; Step S3: Detect a grain boundary based on the jagged glass crack data to obtain grain boundary data; identify a bubble impurity according to the grain boundary data to obtain bubble impurity data; and optimize glass bottle melting production parameters according to the bubble impurity data; Step S4: Determine annealing parameters according to the radial glass crack data; and control a glass bottle production program according to the glass bottle melting production parameters and the annealing parameters. Step S1 specifically comprises:

2. The method for optimizing production parameters of light-weight glass bottles according to claim 1, characterized in that, Step S11: Obtain a glass bottle structure drawing, and perform standardization processing to obtain a standardized glass bottle structure drawing; Step S12: Identify a bottle body edge curve according to the standardized glass bottle structure drawing, and construct a bottle body structure according to the bottle body edge curve; Step S13: Identify a bottle bottom structure according to the standardized glass bottle structure drawing; Step S14: Identify a high-redundancy material region based on the bottle body structure, and perform wall thickness distribution optimization on the high-redundancy material region to generate bottle body wall thickness optimization data; Step S15: Identify a main stress region based on the bottle bottom structure, and perform support rib structure reconstruction on the main stress region to generate a bottle bottom support rib optimization structure; Step S16: Construct a lightweight glass bottle model according to the bottle body wall thickness optimization data and the bottle bottom support rib optimization structure. Step S2 specifically comprises:

3. The method for optimizing production parameters of light-weight glass bottles according to claim 1, characterized in that, Step S21: Simulate impact load according to the lightweight glass bottle model to obtain impact load data; Step S22: Statistically analyze a glass bottle stress concentration region based on the impact load data; calculate a thickness gradient based on the glass bottle stress concentration region, and determine a structural weak point according to the thickness gradient; Step S23: Simulate crack propagation according to the structural weak point to obtain crack data; Step S24: Predict fatigue life based on the crack data to obtain fatigue life data; Step S25: Identify a low-life crack based on the fatigue life data to obtain glass crack data; Step S26: Identify crack shapes based on the glass crack data to obtain jagged glass crack data and radial glass crack data. Step S23 specifically comprises:

4. The method for optimizing production parameters of light-weight glass bottles according to claim 3, characterized in that, Step S231: Import the structural weak point into a crack propagation simulation software; Step S232: Set the crack length range to 0.05mm-1mm, the crack angle range to 0°-90°, and the crack tip radius range to 0.005mm-0.1mm in the crack propagation simulation software; Step S233: Set the cyclic load range to 0.1MPa-2MPa, the impact load range to 10N-200N, and the simulation step range to 100-10000 steps in the crack propagation simulation software; ​ Step S234: Set the fracture toughness range of the glass material to 0.5 MPa·m 0.5 -1.5 MPa·m 0.5 , and the critical stress intensity factor range to 0.7 MPa·m 0.5 -2.0 MPa·m 0.5 ; Step S235: running a crack simulation program, and extracting crack evolution characteristic data according to the crack propagation path and the propagation rate, so as to obtain crack data.

5. The method for optimizing production parameters of light-weighted glass bottles according to claim 3, characterized in that, Step S26 is specifically: Step S261: collecting crack coordinate points based on the glass crack data, and performing curve reconstruction based on the crack coordinate points to obtain crack boundary data; Step S262: identifying the inner edge profile of the crack according to the crack boundary data; calculating the profile fluctuation frequency based on the inner edge profile of the crack; and identifying the crack edge fluctuation tooth segment according to the profile fluctuation frequency; Step S263: calculating the fluctuation amplitude according to the crack edge fluctuation tooth segment; According to the fluctuation amplitude, the jagged glass crack is collected to obtain jagged glass crack data; Step S264: identifying the crack branch intersection point based on the glass crack data; According to the crack branch intersection point, the crack extension path is identified; According to the crack extension path, the crack path initial included angle is calculated; Step S265: calculating the direction angle distribution uniformity based on the crack path initial included angle; According to the direction angle distribution uniformity, the radial glass crack is identified to obtain radial glass crack data.

6. The method for production parameter optimization of lightweight glass bottles according to claim 1, characterized in that, The grain boundary detection in step S3 is specifically: Identifying the sharp turning region based on the jagged glass crack data; Identifying the edge fluctuation mutation region based on the jagged glass crack data; Performing grain region intersection operation according to the sharp turning region and the edge fluctuation mutation region to identify the grain region; Performing electron backscatter diffraction based on the grain region to obtain electron backscatter diffraction data; Constructing a crystal orientation map according to the electron backscatter diffraction data; Calculating the orientation difference angle of adjacent points based on the crystal orientation map; According to the orientation difference angle of adjacent points, the grain boundary is identified to obtain grain boundary data.

7. The method for production parameter optimization of lightweight glass bottles according to claim 1, characterized in that, The bubble impurity recognition in step S3 is specifically: According to the grain boundary data, the interface curvature is calculated; Identifying the interface curvature mutation point based on the interface curvature; According to the interface curvature mutation point, the glass refractive index is calculated; According to the glass refractive index, the refractive index discontinuous region is identified, and the spot blur detection is performed on the refractive index discontinuous region to obtain spot blur data; based on the spot blur data, the spot blur boundary is identified; According to the spot blur boundary, the cavity structure is identified to obtain cavity structure data; Based on the cavity structure data, the bubble impurity detection is performed to obtain bubble impurity data.

8. The method for production parameter optimization of lightweight glass bottles according to claim 1, characterized in that, The optimization of the glass bottle melting production parameters in step S3 is specifically: According to the bubble impurity data, the bubble impurity density is calculated; According to the bubble impurity data, the bubble impurity diameter is calculated; Based on the bubble impurity density, the melting temperature is adjusted to obtain melting temperature adjustment data; Based on the bubble impurity diameter, the stirrer speed is improved to obtain stirrer speed optimization data; Integrating the melting temperature adjustment data and the stirrer speed optimization data to obtain glass liquid dynamic homogenization parameters; Based on the glass liquid dynamic homogenization parameters, the raw material ratio is adjusted to obtain the glass bottle melting production parameters.

9. A production parameter optimization system for lightweight glass bottles, characterized by, The production parameter optimization system for lightweight glass bottles is used to perform the production parameter optimization method for lightweight glass bottles as claimed in claim 1, and the production parameter optimization system for lightweight glass bottles comprises: A lightweight glass bottle model construction module is configured to obtain a glass bottle structure drawing, identify a bottle body structure and a bottle bottom structure, and construct a lightweight glass bottle model according to the bottle body structure and the bottle bottom structure. The crack shape identification module is configured to simulate impact load based on the lightweight glass bottle model to obtain impact load data, identify structural weak points based on the impact load data, generate glass crack data based on fatigue crack evolution of the structural weak points, and identify crack shapes based on the glass crack data to obtain sawtooth glass crack data and radial glass crack data. The melting production parameter optimization module is configured to detect grain boundaries based on the sawtooth glass crack data to obtain grain boundary data, identify bubble impurities based on the grain boundary data to obtain bubble impurity data, and optimize glass bottle melting production parameters based on the bubble impurity data. The annealing production parameter optimization module is configured to determine annealing parameters based on the radial glass crack data, and control a glass bottle production program based on the glass bottle melting production parameters and the annealing parameters.

10. A computer readable storage medium storing a computer program, characterized in that, The computer program, when executed by a processor, implements the production parameter optimization method for lightweight glass bottles as claimed in any one of claims 1 to 8.

Images