Injection molding method and equipment for rubber demolding pipe

Abstract

The invention relates to the technical field of rubber product preparation, and discloses an injection molding method and equipment for a rubber demolding pipe. Target rubber finished product design data and demolding pipe preparation performance information are obtained to formulate a molding structure scheme, and rudiments of all parts are obtained according to the molding structure scheme; the method comprises the following steps: performing shape progress observation on a component prototype, synchronously driving construction of a component connection structure, analyzing a connection forming mode based on historical data and a deep learning algorithm, correcting the component connection structure in real time, and finally obtaining a target rubber finished product. The forming precision and the production efficiency can be effectively improved, high quality and high stability of a rubber demolding pipe finished product are ensured, and the problem that in the prior art, the precision of prepared rubber products with complex structures is insufficient is solved.

Description

Technical Field

[0001] The invention relates to the technical field of rubber product preparation, and in particular to an injection molding method and equipment for a rubber demoulding tube. Background Art

[0002] As a preparation device, rubber demoulding tubes are widely used in various rubber molding processes. They are mainly used to ensure that rubber molded products do not stick to the mold surface during demoulding. Due to the viscosity of rubber and the high temperature and high pressure characteristics during molding, the design and manufacture of demoulding tubes require precise control of the molding process to ensure its functionality and high quality. In the traditional rubber demoulding tube production process, molding accuracy and stability rely on experience and manual adjustment. For rubber products with slightly complex structures, the use of separate demoulding tubes is prone to insufficient precision. Summary of the invention

[0003] The object of the present invention is to provide an injection molding method and equipment for a rubber demoulding tube, aiming to solve the problem of insufficient precision in preparing rubber products with complex structures in the prior art.

[0004] The present invention is implemented in this way. In a first aspect, the present invention provides an injection molding method for a rubber demoulding tube, comprising: Acquire design data of a target rubber product and preparation performance information of a rubber demoulding tube, and disassemble the components of the molding structure of the design data according to the preparation performance information to obtain a molding structure preparation plan of the target rubber product; According to the molding structure preparation scheme, each preparation unit of the rubber demoulding tube is initially configured with functional parameters and pre-processed with component preparation materials to obtain the prototypes of each component of the target rubber finished product; Observe the morphological progress of each component prototype of the target rubber finished product, and synchronously drive the rubber demoulding tube to construct a component connection structure for each component prototype based on the observation result, so as to perform a molding and combining operation on each component prototype through the component connection structure; According to the historical reference database and the deep learning algorithm model, data collection and feature analysis of the connection forming mode of each component prototype in the forming combination operation are performed to obtain the connection forming mode; The functional parameters of the rubber demoulding tube are synchronously adjusted according to the connection forming mode, so as to carry out real-time correction of the component connection structure of each component prototype and combine it with the forming of each component prototype, so that each component prototype is combined to obtain the target rubber finished product.

[0005] In a second aspect, the present invention provides an injection molding device for a rubber demoulding tube, which is used to implement the injection molding method for a rubber demoulding tube as described in any one of the first aspects.

[0006] The present invention provides an injection molding method for a rubber demoulding tube, which has the following beneficial effects: The present invention obtains the design data of the target rubber finished product and the preparation performance information of the demolding tube to formulate a molding structure plan, obtains the prototypes of each component according to the molding structure plan, observes the morphological progress of the component prototypes and synchronously drives the construction of the component connection structure, analyzes the connection molding mode based on historical data and a deep learning algorithm, and corrects the component connection structure in real time to finally obtain the target rubber finished product. This method can effectively improve the molding accuracy and production efficiency by optimizing the combination of design data and preparation performance, combining deep learning with real-time monitoring, thereby ensuring the high quality and high stability of the rubber demolding tube finished product, and solving the problem of insufficient accuracy in preparing complex structure rubber products in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a schematic diagram of the steps of an injection molding method for a rubber demoulding tube provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0009] The implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0010] Reference Figure 1 As shown, a preferred embodiment of the present invention is provided.

[0011] In a first aspect, the present invention provides an injection molding method for a rubber demoulding tube, comprising: S1: acquiring design data of a target rubber product and preparation performance information of a rubber demoulding tube, and disassembling components of a molding structure of the design data according to the preparation performance information to obtain a molding structure preparation plan of the target rubber product; S2: performing initial configuration of functional parameters and preprocessing of component preparation materials for each preparation unit of the rubber demoulding tube according to the molding structure preparation scheme, so as to obtain prototypes of each component of the target rubber finished product; S3: Observe the morphological progress of each component prototype of the target rubber finished product, and based on the observation results, synchronously drive the rubber demoulding tube to construct a component connection structure for each component prototype, so as to perform a molding and combining operation on each component prototype through the component connection structure; S4: performing data collection and feature analysis of the connection forming mode of each of the component prototypes in the forming combination operation according to the historical reference database and the deep learning algorithm model to obtain the connection forming mode; S5: Synchronously adjusting the functional parameters of the rubber demoulding tube according to the connection molding mode, so as to perform real-time correction of the component connection structure of each component prototype and combine the molding of each component prototype, so that each component prototype is combined to obtain the target rubber finished product.

[0012] Specifically, in step S1 of the embodiment provided by the present invention, design data is obtained, including the size, shape, structure and specific requirements for performance (such as pressure resistance, heat resistance, aging resistance, etc.) of the target rubber product. The design data usually comes from CAD design drawings, 3D models or other design software. These data are usually geometric data (size, shape, geometric features) and physical performance requirements (such as material selection, hardness, strength, elasticity, etc.).

[0013] More specifically, the preparation performance information of the rubber demoulding tube is obtained, including the working principle, performance and parameters of the rubber demoulding tube, including: the material properties of the rubber demoulding tube (for example, applicable rubber type, high temperature resistance, elasticity, fluidity, etc.), the geometry of the demoulding tube, flow channel design, wall thickness, sealing, etc., the temperature and pressure range required for the demoulding tube, as well as its working parameters in the injection molding process, and related molding process requirements (such as molding cycle, cooling time, mold design, etc.).

[0014] More specifically, it ensures that during the molding process, the design requirements of the target product and the preparation capabilities of the demolding tube have clear basic data support, providing clear guidance for subsequent operations. The acquired design data and performance information help to achieve accurate matching of the target rubber product with the performance of the rubber demolding tube, providing comprehensive technical support for the planning and implementation of the entire injection molding process.

[0015] More specifically, based on the design data of the target rubber finished product, the finished product is decomposed into multiple sub-components, each sub-component corresponding to an independent molding unit. During the disassembly, the target product is considered to be disassembled into multiple components (such as supporting components, connecting components, sealing components, etc.) according to different functional requirements, and complex geometric shapes are decomposed into simplified forms to facilitate the molding of the demolding tube. Ensure that the geometric characteristics of each component meet the injection molding requirements of the demolding tube, and specify corresponding materials and process parameters for different components according to the physical properties of each component (such as elasticity, high temperature resistance, strength, etc.).

[0016] More specifically, based on the disassembled components, the injection mold structure of the rubber demolding tube is designed, including: runner design, demolding mechanism design, and cooling system design. By disassembling the target rubber finished product into components, the molding requirements of each component can be carefully analyzed to avoid affecting the entire molding process due to an unreasonable design of one component. The disassembled components and optimized molding structure design greatly improve the mold working efficiency, reduce production time, and improve injection molding accuracy.

[0017] More specifically, the information of the disassembled components is combined with the performance requirements of the rubber demolding tube and integrated into a complete molding plan. The molding process parameters, required materials, temperature and pressure control information of each component are recorded in detail, and a specific process from material input, injection molding, cooling to demolding is formulated for each component. The disassembled molding plan is simulated and tested, mainly through mold flow analysis software to simulate material flow, filling effect, cooling process, etc. By simulating the actual injection molding process, it is analyzed whether the material flow is uniform and whether there is incomplete filling or over-filling. The molding plan is adjusted according to the simulation results to ensure that the injection molding process of each component runs under the optimal parameters.

[0018] More specifically, by integrating the molding structures of various components, a comprehensive production plan is formed to ensure that every part of the target finished product meets the design requirements and is effectively molded. Through simulation verification and plan adjustment, deviations in actual production can be reduced, and production efficiency and product quality can be improved. Through computer simulation and virtual testing, potential problems can be predicted and solved, reducing errors and rework in the trial production stage.

[0019] Specifically, in step S2 of the embodiment provided by the present invention, according to the molding structure design scheme of the previous step, preliminary functional parameters are configured for each preparation unit (i.e., each component of the rubber demolding tube), and these parameters mainly include: temperature control: a preliminary injection temperature range is designed for each component, taking into account the fluidity and curing properties of the rubber, pressure setting: appropriate injection pressure and holding pressure are configured for each preparation unit to ensure that the rubber material can completely fill the mold without bubbles, injection speed: according to the mold shape and runner design, a suitable injection speed is selected to avoid defects such as bubbles and short shots, cooling parameters: preliminary configuration of cooling time and cooling water channel design to ensure that each component can be evenly cooled after molding to avoid deformation.

[0020] More specifically, the initial setting of functional parameters (such as temperature, pressure, injection speed, etc.) needs to take into account the overall production efficiency and component quality, and preliminarily adjust the molding process to meet the requirements of different components. Through the initial configuration of the functional parameters, it can be preliminarily verified whether the molding process is smooth, whether the mold can be effectively filled and the overall quality of the component can be ensured. Based on the preliminary configuration and analysis, unreasonable parameters can be quickly identified to avoid unnecessary debugging and waste. Through the preliminary configuration of functional parameters, the consistency of each component in different batches of production can be ensured to reduce production deviations.

[0021] More specifically, according to the performance requirements of the target rubber finished product, select suitable rubber materials (such as natural rubber, silicone rubber, fluororubber, etc.), and ensure that the materials can meet the functional requirements of the target products based on their elasticity, heat resistance, chemical corrosion resistance and other requirements. According to needs, select suitable reinforcing agents (such as carbon black), antioxidants, vulcanizers and other additives to adjust the material's physical properties such as fluidity, strength, hardness, etc.

[0022] More specifically, before the rubber material is molded, necessary pretreatment is carried out, such as drying treatment. Some rubber materials (such as silicone, thermoplastic elastomers, etc.) are hygroscopic and need to be dried to prevent moisture from affecting the molding process; the rubber material and the required additives, fillers, plasticizers, etc. are fully mixed to ensure that the material has uniform properties during the molding process; the temperature of the material is controlled to achieve appropriate fluidity to ensure the filling effect during injection molding.

[0023] More specifically, by pretreating the materials, the performance of the rubber materials can be ensured to be stable and uniform, and the impact of material unevenness, moisture or impurities on the injection molding quality can be effectively avoided. The pretreated materials have better fluidity and formability, which can improve the efficiency of the injection molding process and reduce defects. By controlling the pretreatment process, the consistency of different batches of materials can be ensured, avoiding the impact of material differences on production.

[0024] More specifically, based on the preliminary functional parameter configuration and pretreated materials, start small-batch production or trial production, observe the molding effect, and inject the pretreated materials through a rubber demolding tube to form a preliminary prototype of the component. Check the appearance quality of each component (such as whether there are bubbles, cracks, deformation, etc.), as well as whether the structure is complete and whether the size meets the requirements. Perform performance tests on the resulting component prototypes to ensure that the physical properties of each component meet the design requirements. Test the tensile strength, compressive strength, etc. of the components to ensure that they have sufficient load-bearing capacity. According to the test results of the component prototypes, adjust the molding process, material ratio and functional parameters to ensure that the final component meets the design requirements.

[0025] More specifically, if it is found that some parts have problems such as uneven filling and warping, the flow channel design is optimized or the temperature and pressure parameters are adjusted. According to the test results, the material composition is adjusted, and certain additives are increased or decreased to meet the final performance requirements. The prototype of the component obtained through preliminary molding can verify whether the process and material meet the design requirements, and problems can be discovered and solved in time. Through the adjustment and verification at this stage, potential quality problems can be eliminated before formal production, avoiding rework and cost waste after large-scale production, and ensuring that the performance of each component meets the expected requirements, especially key performance such as load-bearing capacity, sealing, and temperature resistance.

[0026] Specifically, in step S3 of the embodiment provided by the present invention, the morphological changes of the component prototype are monitored in real time, and the morphological changes of the rubber component are observed in real time by means of sensors, visual systems (such as cameras, infrared sensors, etc.) or laser scanning, and the size, surface morphology, hardness and other data of the component are recorded. The monitored data are collected and analyzed using a computer control system to determine in real time whether the component morphology meets the design requirements, with particular attention paid to dimensional deviations, surface defects or any potential deformation problems.

[0027] More specifically, the morphological development progress of each component is compared with the predetermined molding progress to evaluate whether the component has completed the morphological formation according to the predetermined molding time and quality requirements. If any morphological discrepancies are found (such as local warping, bubbles, cracks, etc.), timely feedback and adjustments are made to optimize production conditions or process flows.

[0028] More specifically, by observing the morphology of components in real time, it is possible to ensure that each component completes the morphological changes according to the predetermined plan, avoiding delays or quality fluctuations in the production process. Through progress observation, it is possible to discover defects that may occur in the component molding process (such as uneven surface, dimensional deviation, etc.) in advance, and make adjustments at the first time to avoid the expansion of defects. Through continuous morphological tracking, the dimensional accuracy and appearance quality of the final product can be guaranteed to the greatest extent.

[0029] More specifically, according to the design requirements of the rubber product, the connection structure between the components is defined, which may include screw joints, plug holes, snap-on structures, etc., or gluing, welding and other means. During the rubber molding process, focus on the design of the connection points of the components to ensure that these connection points can be effectively combined and will not loosen or be damaged due to physical stress or deformation.

[0030] More specifically, based on the morphological progress observation results, the computer control system synchronously drives the rubber demoulding tube to push the various components to connect at the appropriate time. According to the progress of the components, the temperature, pressure, speed and other parameters of the rubber demoulding tube and the mold are adjusted to ensure that the components can be seamlessly connected during connection and complete the final combination. When the components are connected, the rubber demoulding tube must ensure that the components are in the correct position to avoid misalignment or sliding, and the positioning device must be used for auxiliary fixation when necessary.

[0031] More specifically, by adjusting the movements of the demolding tube and the mold synchronously in real time, the connection structure of the components can be constructed efficiently and accurately, reducing human operation errors. During the connection operation, each component can be accurately docked to avoid affecting product quality due to misalignment, deformation and other reasons. Through synchronous drive and automatic control, the production rhythm can be accelerated, production efficiency can be improved, and time waste caused by human operation errors or production delays can be reduced.

[0032] More specifically, the temperature and pressure of the rubber demolding tube are adjusted according to the material and shape of the components to ensure that the components can be smoothly connected during molding and maintain sufficient adhesion. In the process of combining the components, the molding pressure is evenly distributed to avoid loose bonding or uneven surface due to local overpressure or underpressure. By controlling the molding time and cooling time, the structure after the components are combined can be completely cured to avoid loose bonding or deformation due to incomplete curing.

[0033] More specifically, reinforcement molding operations are performed on key points where components are connected, such as reinforcing certain areas or using other auxiliary means to increase the strength of the connection points. After the connection is completed, surface treatment is performed to remove excess rubber or perform trimming to ensure that the connection is smooth and free of defects.

[0034] More specifically, by precisely controlling parameters such as temperature, pressure, and time during the molding process, we can ensure that the structural strength of the component joints meets the use requirements and avoid loose joints due to improper operation. Optimizing the molding process of the connection points can improve the structural stability of the entire product and ensure the consistency and reliability of each component during use. Through precise molding and bonding, the various components of the final product can achieve a seamless docking effect and enhance overall performance, such as waterproofing and sealing.

[0035] More specifically, each connection point is visually inspected to ensure that there are no obvious defects such as misalignment, bubbles, cracks, etc., and the strength of the connection is checked by applying a certain amount of pressure to the connection to ensure that it can withstand the stress in actual use. For some parts with special functional requirements (such as sealing function), special functional tests are carried out to ensure that the connection can function effectively.

[0036] More specifically, based on the quality inspection results, necessary trimming and optimization operations are carried out to ensure that all connection points meet the design standards. If some parts are found to be poorly connected, the molding process can be adjusted to increase the pressure, temperature or molding time to ensure the connection quality. Through strict inspection and subsequent adjustments of the connection parts, it is ensured that each component can be accurately combined to ensure the overall quality of the product. Through continuous optimization and inspection, it is ensured that the combination of various parts of the product will not affect its stability and safety in subsequent use. Strict inspection and adjustment ensure the quality consistency of each component connection and ensure the stable quality of each batch of rubber products.

[0037] Specifically, in step S4 of the embodiment provided by the present invention, a database containing historical production data is established, and the data content includes molding parameters (such as temperature, pressure, time, etc.) under different process conditions, component morphology (such as size, surface quality, hardness, etc.) and defect types and frequencies occurring during the molding process, and various sensors (such as temperature sensors, pressure sensors, displacement sensors, etc.) are installed on the production line to collect data of components during the molding process in real time. These data can be parameters such as temperature changes, pressure curves, component dimensions, surface quality, etc.

[0038] More specifically, the status of the component prototype is monitored through visual sensors or laser scanning devices to obtain real-time morphological data. Various types of data collected in real time are transmitted to the computing platform through the data transmission system for subsequent analysis and processing. Environmental change factors in the molding process are recorded, such as mold temperature, production environment humidity, air flow rate, etc. These factors may affect the connection molding mode of the components, and process control parameters are recorded, including injection pressure, mold opening and closing speed, cooling rate, etc.

[0039] More specifically, by combining real-time collection with historical data, comprehensive molding process data can be provided, which is helpful to analyze the relationship between different process conditions and product quality. The real-time collected production data can reflect the immediate changes between process parameters and component quality, ensuring that potential problems can be quickly discovered during the production process.

[0040] More specifically, machine learning algorithms (such as principal component analysis (PCA), independent component analysis (ICA), etc.) are used to extract features from the raw data. The extracted features may include numerical data such as temperature, pressure, and time, as well as image features of component morphology (such as thickness, surface smoothness, etc.). Data from different sensors are fused to extract multi-dimensional and multi-level features. For example, visual data can be combined with pressure and temperature data to analyze the impact of different process parameters on the quality of component connection.

[0041] More specifically, the collected data is cleaned, noise data is removed, and missing values ​​are filled to ensure the quality of the data during the analysis process. Various features are normalized or standardized to ensure that data of different dimensions will not introduce deviations in the analysis. According to the quality control standards in the molding process (such as qualified / unqualified, defect type, etc.), the data is classified to generate label data suitable for deep learning algorithm model training. The label can include whether the part is qualified or the specific defect type (such as cracks, dislocations, bubbles, etc.).

[0042] More specifically, feature extraction and data preprocessing can transform complex raw data into feature data with analytical significance, improve the predictive ability of subsequent models, and ensure the high quality of input data through denoising, missing value processing and standardization, thus avoiding the impact of data problems on the accuracy of the model.

[0043] More specifically, convolutional neural networks (CNNs) are used to extract and analyze image features for image data, such as the surface quality and shape of parts, to identify different connection molding modes; long short-term memory networks (LSTMs) are used to process time series data, such as temperature changes and pressure curves, to capture time-dependent information in the molding process; deep reinforcement learning (DRL) can be used in scenarios where process parameters need to be adaptively adjusted to find the optimal connection molding mode through continuous experiments and feedback.

[0044] More specifically, historical data is used for supervised learning training, and labeled data is used to adjust model parameters. At the same time, unsupervised learning methods (such as clustering algorithms, principal component analysis, etc.) are combined to further explore potential connection forming patterns. The model is continuously optimized through parameter adjustment, cross-validation and other methods, and the optimal learning rate, batch size, number of iterations and other hyperparameters are selected. Through the trained model, the connection forming patterns under different process conditions are automatically identified, and compared with historical patterns for analysis to determine the rationality of the current pattern. According to the current process parameters, the best connection forming pattern is predicted, and the production process is adjusted according to the prediction results to achieve the best forming effect.

[0045] More specifically, the deep learning algorithm model can automatically identify the connection and forming patterns under different process conditions through training on a large amount of historical data, thereby improving the accuracy of pattern recognition in the production process. Through pattern prediction and optimization, it can predict in advance which process conditions will cause poor connections, avoid the production of defective products, and reduce production losses. The deep learning algorithm model has automatic adaptability and can dynamically adjust the forming pattern according to the ever-changing process conditions and product requirements in the production process, thereby improving production flexibility.

[0046] More specifically, based on the optimal connection molding mode identified by the deep learning algorithm model, the process parameters on the production line (such as pressure, temperature, cooling speed, etc.) are adjusted in real time to ensure that each component can achieve the best connection effect during molding. During the production process, an automated feedback mechanism is established to monitor production data in real time and compare it with the predicted results of the deep learning algorithm model to automatically adjust the parameters in the molding process.

[0047] More specifically, new data collected during the production process can be fed back to the deep learning algorithm model for retraining and optimization, gradually improving the model's prediction accuracy. As the production process continues, the deep learning algorithm model continuously optimizes the connection and forming mode to meet the production needs of different batches and specifications. The connection and forming mode optimized by deep learning can improve the efficiency of the production line and reduce ineffective operations and energy consumption in the production process. The optimized connection and forming mode can ensure the stable combination quality of each component and improve the consistency and reliability of the product. The continuous optimization of the deep learning algorithm model enables the production process to be adaptively adjusted according to different production needs to meet high-precision and high-efficiency production requirements.

[0048] Specifically, in step S5 of the embodiment provided by the present invention, the key quality standards and functional requirements of the target rubber finished product, such as dimensional tolerance, hardness, strength, surface quality, demoulding property, etc., are clarified. According to the functional requirements of the target rubber finished product, the functional role of each component prototype in the molding process is analyzed, and the functional requirements of each component (such as sealing, temperature resistance, pressure resistance, etc.) are defined. By conducting an in-depth analysis of the functional requirements of the target product, it is ensured that the optimization and adjustment of all subsequent operations can point to the target quality standards to avoid invalid adjustments.

[0049] More specifically, sensors are installed at key locations of the production line (such as inside the mold, on the surface of the demoulding tube, at the joints of various components, etc.) to monitor temperature, pressure, flow, demoulding tube position, component shape and other data in real time. Through the automated control system and real-time data acquisition system, it is ensured that various parameters and characteristic data are synchronously collected during the production process and transmitted to the central data processing platform. Through real-time monitoring, any abnormalities in the production process can be captured in time, ensuring real-time feedback and adjustments in all aspects of production.

[0050] More specifically, a predictive model for the connection molding mode is established using historical production data and deep learning algorithms. This model can predict and optimize the connection mode of components based on real-time data, and automatically adjust the connection position, temperature, pressure and other parameters of each component during the molding process. According to the analysis results of the deep learning algorithm model, the functional parameters of the rubber demolding tube (such as temperature, pressure, mold opening and closing speed, etc.) are optimized and adjusted in real time, so that the prototype of each component can be accurately connected during the molding process.

[0051] More specifically, through real-time optimization of the deep learning algorithm model, it is possible to intelligently identify and correct the connection and forming patterns according to the specific needs of production, thereby improving production accuracy and efficiency. The model can automatically adjust parameters according to actual changes in the production process to ensure that product quality always meets the standards.

[0052] More specifically, according to the requirements of the connection molding mode, the temperature, pressure, cooling rate and other functional parameters of the rubber demoulding tube are adjusted synchronously. For example, the temperature of the demoulding tube is adjusted according to the change of the shape of the component to prevent the deformation of the component due to overheating or overcooling during the molding process. When adjusting the functional parameters of the demoulding tube, the mold opening and closing speed, filling speed and other process parameters are combined to ensure the stability of the shape of each component prototype when connected. The surface quality and demoulding property of the demoulding tube are guaranteed by adjusting the temperature and pressure through real-time feedback. By synchronously adjusting the functional parameters of the demoulding tube, molding defects caused by improper connection of various components can be avoided, and the quality of the final product can be ensured. By optimizing the parameters of the demoulding tube, it can be ensured that the finished product is not damaged during the demoulding process, while improving the bonding quality between components.

[0053] More specifically, the data collected in real time during the molding process is used to correct the connection structure of each component prototype in real time to ensure that each component is accurately combined according to the set connection mode. For example, local temperature and pressure adjustment is performed at the connection of the components to prevent bubbles or irregular deformation of the joint part. The mold is adjusted according to the corrected connection mode to ensure that the opening and closing accuracy, gap, and position of the mold match the shape of the component, thereby optimizing the molding effect. By adjusting the heat distribution and pressure of the mold, the connection position of the component is guaranteed to be accurate.

[0054] More specifically, by combining real-time correction of component connections with molding, the tightness and stability between components can be significantly improved, and defects caused by poor connections can be avoided. After correcting the component connection structure, product quality fluctuations caused by poor connections during the molding process can be effectively avoided, making the quality of each product more consistent.

[0055] More specifically, after molding is completed, the finished product is inspected by automatic inspection equipment (such as three-coordinate measuring machines, visual inspection systems, etc.) to confirm whether its size, hardness, surface quality, etc. meet the design requirements. If defects are found in the molding process (such as dimensional deviation, surface unevenness, difficulty in demolding, etc.), the defect information is fed back to the deep learning algorithm model to optimize the subsequent production process. Through the inspection and verification of the target finished product, it is ensured that the finished product is highly consistent with the expected standards in terms of size, function, etc., thereby improving the stability of the production process. Through the feedback mechanism, the deep learning algorithm model can continuously optimize the production process so that each production can be adjusted according to the previous defects, thereby continuously improving production efficiency and finished product quality.

[0056] The present invention provides an injection molding method for a rubber demoulding tube, which has the following beneficial effects: The present invention obtains the design data of the target rubber finished product and the preparation performance information of the demolding tube to formulate a molding structure plan, obtains the prototypes of each component according to the molding structure plan, observes the morphological progress of the component prototypes and synchronously drives the construction of the component connection structure, analyzes the connection molding mode based on historical data and a deep learning algorithm, and corrects the component connection structure in real time to finally obtain the target rubber finished product. This method can effectively improve the molding accuracy and production efficiency by optimizing the combination of design data and preparation performance, combining deep learning with real-time monitoring, thereby ensuring the high quality and high stability of the rubber demolding tube finished product, and solving the problem of insufficient accuracy in preparing complex structure rubber products in the prior art.

[0057] Preferably, the step of obtaining the design data of the target rubber finished product and the preparation performance information of the rubber demoulding tube, and disassembling the components of the molding structure of the design data according to the preparation performance information to obtain the molding structure preparation scheme of the target rubber finished product includes: S11: Acquire design data of a target rubber product; wherein the design data includes 3D structural information of the target rubber product and a performance requirement annotation set corresponding to the 3D structural information; S12: Acquire the preparation performance information of the rubber demoulding tube; wherein the preparation performance information of the rubber demoulding tube includes the performance information of each preparation unit and the performance information of each connection unit; S13: digitally modeling the target rubber product according to the 3D structure information, and feature-labeling the digital modeling of the target rubber product according to the performance requirement labeling set to obtain a digital model of the finished product; S14: simulating the component disassembly scheme of the finished digital model to obtain several original disassembly schemes of the finished digital model, and simulating the process of single component preparation and connection of each component for various original disassembly schemes of the finished digital model according to the performance information of each preparation unit and the performance information of each connection unit, and performing feedback optimization on the component disassembly form, single component preparation method, and connection method of each component for each original disassembly scheme according to the evaluation result, so as to obtain a molding structure preparation scheme with the best simulation evaluation result in terms of component disassembly form, single component preparation method, and connection method of each component.

[0058] Specifically, the three-dimensional structural data of the target rubber product is obtained from the design stage. This information usually includes the size, shape, and geometric form of each part of the product, and the performance requirement annotation set is obtained. The performance requirement annotation set corresponding to the design data should include the performance requirements for each part, such as hardness, elasticity, heat resistance, strength, toughness, surface quality, etc. These performance requirements are key indicators of the finished product in actual use. Ensure that the design data of the target rubber product is complete and has annotations of all functional requirements, lay the foundation for the subsequent molding process, clarify the performance requirements of each component of the finished product, and avoid errors or failures in the design process.

[0059] More specifically, the performance data of the rubber demoulding tube in the production process is obtained, including parameters such as the temperature range, pressure range, time control, etc. that can be achieved by different preparation units (such as heating, cooling, mixing, etc.), and the performance data of each connection unit of the rubber demoulding tube (such as mold connection, temperature control pipeline, demoulding system, etc.) is obtained. These data may involve connection strength, pressure resistance, corrosion resistance, demoulding, etc. By analyzing the performance information of each preparation unit and connection unit of the rubber demoulding tube, it can provide a basis for parameter adjustment in the molding process to ensure the smooth progress of the molding process. Obtaining preparation performance information is helpful for overall optimization of the production process to ensure that each production link can operate under optimal conditions.

[0060] More specifically, based on the acquired 3D structural information, the design data of the target rubber product is converted into a digital model. CAD or other modeling software is used to convert the design's geometric information, dimensions, etc. into a computer-operable digital model. The finished product digital model is annotated according to the performance requirement annotation set to clarify the key performance requirements of each component. For example, the strength requirements and temperature resistance requirements of a certain part are annotated. Through digital modeling, the structure of the target rubber product can be clearly displayed, and an intuitive model basis can be provided for subsequent optimization and testing. Through feature annotation, the performance requirements of each component can be directly applied to the digital model, providing detailed guidance for the subsequent optimization process.

[0061] More specifically, based on the digital model of the target rubber finished product, the component disassembly scheme is simulated. The finished product model is decomposed into multiple original component schemes, each of which includes component disassembly, assembly sequence, accessory design, etc., to simulate the molding process and connection method of each component. By simulating different component disassembly methods, the feasibility and efficiency of different schemes can be evaluated. By generating multiple original disassembly schemes, different component combinations, molding methods, and connection methods can be evaluated to find the most suitable solution for production. Through simulation and evaluation, the optimal disassembly scheme can be quickly screened out to avoid unnecessary waste or complexity in the actual production process.

[0062] More specifically, based on the preparation performance information of the rubber demolding tube, each disassembly plan is simulated in detail, including the molding process of a single component, the connection process between components, etc. For example, the influence of parameters such as pressure, temperature, and cooling time on each component is simulated to evaluate whether the performance requirements can be met. The effect of each disassembly plan is evaluated, and the evaluation criteria include but are not limited to finished product quality, production efficiency, preparation difficulty, cost, material consumption, etc. Through simulation and evaluation, the actual effect of each disassembly plan can be accurately predicted, potential problems can be discovered in advance and optimized, and the evaluation results provide a basis for subsequent decision-making, which helps to select the optimal plan and reduce errors and losses in production.

[0063] More specifically, according to the simulation results and evaluation data, each disassembly plan is adjusted and optimized. For example, it may be necessary to adjust the form of component disassembly, the preparation method of a single component, or the connection method between components. During the evaluation and optimization process, adjustments are made repeatedly until the optimal form of component disassembly, the preparation method of a single component, and the connection method of components are found, and finally a molding structure preparation plan that meets all performance requirements and has the best production efficiency is obtained. Through repeated optimization and adjustment, an efficient and quality-compliant production plan is finally obtained, which can maximize product quality and production efficiency in actual production. The optimization process ensures that each link from design to production is accurately connected, reduces unnecessary waste of resources and time, and improves the accuracy and efficiency of the overall production line.

[0064] Preferably, the steps of initially configuring the functional parameters of each preparation unit of the rubber demoulding tube and pre-processing the component preparation materials according to the molding structure preparation scheme to obtain the prototypes of each component of the target rubber finished product include: S21: performing initial configuration of cavity morphology function parameters for each preparation unit of the rubber demoulding tube according to the component disassembly form in the molding structure preparation scheme, so that the preparation cavity of each preparation unit adapts to the structural information of the finished product component to be prepared; S22: performing initial configuration of heating function parameters for the temperature control modules of each of the preparation units according to the single component preparation method in the molding structure preparation scheme, so that the preparation cavity of each of the preparation units is in a heating state of specified specifications; S23: according to the single component preparation method in the molding structure preparation scheme, the inlet of each preparation unit is filled with component preparation materials in an orderly manner, so that the preparation cavity of each preparation unit receives the component preparation materials filled through the inlet in sequence; wherein the component preparation materials include main materials and auxiliary materials, the main materials include silicone, fluororubber or chloroprene rubber, and the auxiliary materials include fillers, plasticizers or cross-linking agents; S24: By performing real-time temperature control synchronization control on the temperature control modules of each of the preparation units, each of the preparation units is instructed to heat and mix the component preparation materials that are sequentially filled into the preparation cavity, so that the component preparation materials in the preparation cavity of each of the preparation units are prepared into corresponding component prototypes through heating and mixing at different temperature specifications.

[0065] Specifically, according to the disassembly form of the components in the molding structure preparation plan, the morphological parameters of the cavity of each preparation unit are initially configured. Specifically, the shape, size, distribution, etc. of the cavity are adjusted to adapt it to the structural information of the component to be prepared. These adjustments need to accurately match the geometric shape and performance requirements of the finished product to ensure that the preparation cavity can effectively support the shape forming of the finished component under the design parameters. For example, when considering the complex curved surface or special shape of the component, the design of the cavity must be able to accurately accommodate these structural features. Through the precise configuration of the preparation unit cavity, it can be ensured that the shape and size of each component meet the design requirements and avoid dimensional errors in subsequent processing. The initial configuration of the cavity morphology makes it adaptable and can be adjusted to different shapes of finished components to ensure high-precision production of different components.

[0066] More specifically, according to the preparation method of a single component in the molding structure preparation plan, the heating function parameters of the temperature control module of each preparation unit are preliminarily configured. During the configuration process, it is necessary to set the temperature range, heating rate, etc. of the heating system of each preparation unit according to the material properties, molding method and temperature requirements of the required components. According to the specific requirements of the material, the control accuracy and response time of the temperature control module are adjusted to ensure that the temperature in the cavity is always within the specified range during the component preparation process. By accurately configuring the heating parameters of the temperature control module, it can be ensured that the temperature in the preparation process is controlled within the optimal range, thereby avoiding overheating of the material or uneven heating. The optimized configuration of the temperature control module can ensure temperature stability throughout the production process and ensure that the rubber material can be evenly mixed and molded during heating, thereby obtaining high-quality finished components.

[0067] More specifically, the feed port configuration of each preparation unit is determined according to the component preparation method in the molding structure preparation plan. The main material (such as silicone, fluororubber or chloroprene rubber) and auxiliary materials (such as fillers, plasticizers or cross-linking agents) are filled into the preparation cavity in an orderly manner through the feed port. The filling amount, filling order and material ratio of each preparation unit need to be accurately configured according to the design requirements of the component to ensure the accurate ratio and distribution of the main material and auxiliary materials to meet the performance requirements of the finished component. For example, the appropriate plasticizer ratio can ensure the flexibility of the material, while the cross-linking agent can ensure its strength and durability. Through precise filling methods and material ratios, the material properties of each component are ensured to remain consistent during the preparation process to avoid fluctuations in the quality of the finished product due to uneven filling. Orderly material filling can improve production efficiency and ensure that each preparation unit accurately receives the filling material in a predetermined order and proportion to avoid repeated operations and material waste.

[0068] More specifically, by performing real-time synchronous control on the temperature control modules of each preparation unit, it is ensured that the component preparation materials in each preparation unit are heated and mixed at temperatures of different specifications, and the temperature changes are monitored in real time and the heating parameters are adjusted to ensure uniform heating and mixing of the materials, and avoid areas with too high or too low temperatures. According to the material properties (such as the plasticity of silicone, the heat resistance of fluororubber, etc.), reasonable temperature control is performed to ensure that the component preparation materials can be evenly heated in the preparation cavity to achieve an ideal mixing effect, thereby forming the required component prototype. Through precise temperature control and heating and mixing treatments, the uniformity of the component preparation materials is ensured, so that the performance of each component meets the design requirements and quality defects caused by uneven materials are avoided. Through the fine regulation of the temperature control system, the molding quality and performance of each component are guaranteed, and problems such as overheating of materials, insufficient hardening or uneven mixing during the molding process are avoided, thereby improving production efficiency and finished product quality.

[0069] Preferably, the steps of observing the morphological progress of each component prototype of the target rubber finished product, and synchronously driving the rubber demoulding tube to construct a component connection structure for each component prototype based on the observation result, so as to perform a molding and combining operation on each component prototype through the component connection structure include: S31: performing multi-dimensional data collection on each component prototype of the target rubber product through a sensor group preset on each preparation unit to obtain multi-dimensional feedback data of the component prototype of each preparation unit; wherein the sensor group includes a temperature sensor, a pressure sensor and a visual sensor, and the multi-dimensional feedback data includes temperature data, pressure data and visual data; S32: performing a morphological progress analysis on the component prototype according to the multi-dimensional feedback data to obtain a morphological progress feature of the component prototype at the current moment; S33: performing a continuous trend analysis on the morphological progress characteristics of the component prototype at each continuous moment, and performing a forward correlation feature analysis on the morphological progress characteristics at the current moment according to the result of the trend analysis, so as to obtain a forward correlation feature of the morphological progress characteristics of the component prototype at the current moment; S34: according to the connection mode of each component in the molding structure preparation plan, reference analysis is performed on the morphological progress characteristics and the forward correlation characteristics of each component prototype at the current moment to determine whether the connection work can be started; S35: When the result of the reference analysis shows that the connection work can be started, the transfer order of the component prototypes in the preparation cavity of each preparation unit to the inside of the cavity for molding combination is determined according to the connection mode of each component in the molding structure preparation plan, and the component prototype with the earliest transfer order is marked as a molding matrix, and the component prototype with the subsequent transfer order is marked as a molding assembly; S36: driving the preparation unit where the molding substrate is located to transfer the molding substrate to a cavity for molding combination, and constructing a component connection structure for the docking position of each molding assembly corresponding to the molding substrate, so as to obtain a component connection structure of each molding assembly corresponding to the molding substrate; wherein the component connection structure includes an internal insertion guide structure and an external pressure constraint structure; S37: driving the preparation unit where the molding assembly is located to transfer the molding assembly to the inside of the cavity for the molding structure, so that the molding assembly is docked with the molding substrate in the cavity for the molding assembly through the component connection structure.

[0070] Specifically, a group of sensors are preset on each preparation unit, including temperature sensors, pressure sensors and visual sensors. These sensors will collect status data of the prototypes of each component of the target rubber finished product in real time. Temperature sensor: monitors the changes in cavity temperature during the preparation process to help grasp the heating progress of the material. Pressure sensor: measures the pressure changes of the component prototype during the molding process to evaluate the molding pressure and material fluidity of the component. Visual sensor: through image recognition, it monitors the appearance of the component prototype in real time to determine whether its shape, size and molding meet the requirements. The sensor group feeds back the collected temperature, pressure and visual data to the control system. These data form multi-dimensional feedback data, including temperature data, pressure data and visual data. The real-time collection of multi-dimensional data ensures comprehensive monitoring of each preparation unit and can promptly discover potential molding problems. The joint analysis of temperature, pressure and visual data provides a comprehensive basis for subsequent morphological progress analysis.

[0071] More specifically, based on the multi-dimensional data fed back by the sensor group, the current morphological progress of the component prototype is analyzed, and whether the material has reached the predetermined molding state is determined by temperature and pressure data. Combined with the visual sensor feedback, it is determined whether the appearance of the component meets the requirements. The morphological progress of the component prototype at different time points is trended and analyzed. By correlating the data at each moment, the changing trend of the morphological progress is identified. According to the trend analysis results, the morphological progress characteristics at the current moment are analyzed for forward correlation characteristics, that is, the molding progress and state of the component at the next moment are predicted, thereby providing a decision-making basis for subsequent connection work, and being able to judge the molding progress and state of the component in real time to avoid situations that do not meet the design requirements during the molding process. The forward correlation analysis can predict the changing trend of the component morphology in advance, prepare for subsequent operations, and improve the accuracy of operations.

[0072] More specifically, based on the results of the morphological progress analysis and the feedback from the forward correlation feature analysis, a reference analysis is performed on the current morphological progress features and forward correlation features of each component prototype. If the analysis results show that the component has reached the connection standard, the connection work can be started. According to the connection methods of each component in the molding structure preparation plan, it is determined how to connect the prototypes of each component. This involves how to mark the first transferred component as a "molding matrix" and the subsequently transferred components as a "molding assembly". The forward correlation analysis is used to automatically determine whether the connection conditions are met, thereby improving the intelligence of the production process and reducing manual intervention. The connection method based on the design plan ensures that the prototypes of each component are connected at the appropriate time.

[0073] More specifically, the transfer sequence of the component prototypes is determined according to the connection method. First, the "molding matrix" is transferred to the cavity used for molding and bonding, and then the "molding assembly" is transferred to the same cavity in turn to prepare for the docking operation. The component connection structure includes an internal insertion guide structure: design and construct a guide structure between components to enable the components to be correctly docked in the cavity by insertion; an external pressure constraint structure: after the components are docked, an external pressure constraint structure is designed to ensure a stable connection between the components to avoid deformation during the molding process; precise control of the transfer sequence ensures that the components can be connected in the planned order without position confusion or mismatching. Through the synergistic effect of the internal insertion guide structure and the external pressure constraint structure, the connection of the components is ensured to be both accurate and firm, which improves the strength and stability of the final molded components.

[0074] More specifically, in the cavity used for molding and combining, the "molding base" and the "molding assembly" are connected by means of a component connection structure. The specific operations include: accurately connecting the molding assembly to the molding base according to a preset connection method and a guiding structure, and firmly combining the two components by means of an external pressure constraint structure to ensure that they will not be displaced or loosened during the molding process. The precisely designed connection structure makes the combination of the "molding base" and the "molding assembly" tighter, avoiding deformation or loose connection during molding. The precise connection operation and the stable fixing method ensure the overall structural stability and mechanical properties of the finished rubber components, meeting the design requirements of the product.

[0075] Preferably, the step of performing a reference analysis on the morphological progress characteristics and the forward correlation characteristics of each component prototype at the current moment according to the connection mode of each component in the molding structure preparation scheme to determine whether the connection work can be started includes: S341: performing a weighted comprehensive analysis on the morphological progress characteristics and the forward correlation characteristics of each component prototype at the current moment according to the connection mode of each component in the molding structure preparation plan, so as to obtain the connection timing characteristics of the component prototype at the current moment; S342: performing parameter conversion and parameter linking on the connection timing characteristics of each preparation unit of the rubber demoulding tube to obtain a connection parameter matrix for providing data feedback on the overall connection timing of the rubber demoulding tube; S343: performing multi-dimensional extraction of matrix expression features for each of the component prototypes based on the connection parameter matrix, and using the extracted multi-dimensional matrix expression features as constraints, and performing reverse analysis of the theoretical expression features of subsequent time nodes on the connection parameter matrix according to the constraints, to obtain the theoretical expression features of the connection parameter matrix at subsequent time nodes; S344: analyzing the timing of starting or not the connection work of each preparation unit of the rubber demoulding tube according to the theoretical description characteristics of the connection parameter matrix at the subsequent time node, and synchronously adjusting the directional working parameters of each preparation unit of the rubber demoulding tube according to the theoretical description characteristics, so that the multi-dimensional matrix description characteristics of the connection parameter matrix brought by the working parameters of each preparation unit at the subsequent time node meet the theoretical description characteristics; S345: Analyze the timing analysis results of the theoretical expression characteristics to obtain reference analysis results.

[0076] Specifically, a weighted comprehensive analysis is performed based on the morphological progress characteristics and forward correlation characteristics of each component prototype at the current moment. These characteristics may include data such as the component's temperature, pressure, appearance, and the forward-predicted morphological change trend. Different weight values ​​are assigned to data from different sources to comprehensively evaluate the connection timing characteristics of the component prototype, that is, to determine whether the current moment is suitable for starting the connection work. Through weighted analysis, not only a single feature is considered, but data from multiple dimensions are integrated to provide a more accurate and comprehensive basis for judging the connection timing.

[0077] More specifically, the connection timing characteristics of each component prototype are converted into parameter form, and these parameters are uniformly processed through a mathematical model to form a connection parameter matrix. The connection timing characteristics of different preparation units are parameter-linked to form a complete parameter matrix. This matrix will be used for the overall connection timing feedback analysis. Through the connection parameter matrix, the timing characteristics of each preparation unit can be effectively integrated to provide a global timing feedback, thereby providing precise time point control for subsequent operations.

[0078] More specifically, based on the connection parameter matrix, the connection timing characteristics of each component prototype are extracted in multiple dimensions. These characteristics may involve multiple dimensions such as pressure, temperature, and shape of each component. The extracted multi-dimensional matrix representation characteristics are used as constraints to further analyze whether the connection work can be successfully started at the subsequent time node. Through the multi-dimensional extraction of the connection parameter matrix, more precise constraints can be obtained, which helps to better predict and control the connection timing in subsequent operations.

[0079] More specifically, based on the established constraints, a reverse anticipation analysis is performed on the connection parameter matrix. This means that under the conditions at the current moment, the theoretical expression characteristics at subsequent time nodes can be inferred. Through reverse analysis, a theoretical connection timing characteristic is obtained, which indicates whether the connection operation can proceed smoothly at the subsequent time nodes and whether it meets the expected forming requirements. The results of the reverse analysis can predict in advance whether the future timing is appropriate, thereby providing more accurate time and operational guidance for subsequent connection work, avoiding quality problems caused by improper connection timing.

[0080] More specifically, based on the theoretical description characteristics of the connection timing obtained by reverse analysis, a timing analysis is performed on each preparation unit of the rubber demolding tube to determine whether the connection work can be started. If the starting conditions are met, the working parameters of each preparation unit are synchronously adjusted according to the theoretical description characteristics to ensure that their multi-dimensional matrix description characteristics at subsequent time nodes are consistent with the theoretical description characteristics. Through timing analysis, it is ensured that each preparation unit starts the connection work at the correct time to avoid adverse effects caused by premature or late start-up. By synchronously adjusting the working parameters of each preparation unit, it is ensured that their operation is consistent with the timing of the overall production process, thereby ensuring the consistency and stability of product quality.

[0081] More specifically, the results of the connection timing analysis are analyzed to determine whether the connection work can be successfully started, and the operation strategy is adjusted according to the actual situation. The analysis results are fed back to the entire production process to guide subsequent production operations. If the analysis results show that the timing is not appropriate, the subsequent operation rhythm and work parameters are adjusted. By analyzing the timing analysis results, the production process can be adjusted in time to ensure that each link can be started at the best time to maximize production efficiency and product quality. The analysis results provide a flexible adjustment plan for subsequent operations to adapt to the changing production environment and component characteristics.

[0082] Preferably, the step of collecting data and analyzing features of the connection forming mode of each component prototype in the forming and combining operation according to the historical reference database and the deep learning algorithm model to obtain the connection forming mode includes: S41: performing data collection and feature analysis on the molding combination state of each of the component prototypes in the molding combination operation through a preset sensor group to obtain an original state data set of the molding combination state of each of the component prototypes; wherein the original state data set includes the original state data of each detection time node, and the original state data includes temperature data, pressure data, molding state data, and material fluidity data; S42: performing reference matching processing of historical data on the original state data set according to the historical reference database to obtain a deviation reference feature distribution between the original state data set and a plurality of historical operation data sets in the historical reference database; S43: performing scatter plotting and linear variable observation on the distribution of each deviation reference feature to obtain a linear deviation sequence of the original state data set, and performing information mapping of a pre-analysis feature matrix on the linear deviation sequence so that the pre-analysis feature matrix has matrix features corresponding to the linear deviation sequence; S44: Substituting a pre-analysis feature matrix having matrix features corresponding to the linear deviation sequence into a pre-trained deep learning algorithm model; wherein the deep learning algorithm model includes a convolutional neural network, a recurrent neural network, or a long short-term memory network; S45: Instruct the deep learning algorithm model to perform a deep analysis of the connection and forming patterns of the prototypes of each component on the pre-analysis feature matrix to obtain the connection and forming patterns.

[0083] Specifically, during the molding and combination operation, a set of preset sensors (such as temperature sensors, pressure sensors, etc.) are used to collect real-time data on the molding combination status of the component prototype. The data acquired by the sensors include the original state data of multiple detection time nodes. These data involve: temperature data: reflecting the heat changes during the molding process; pressure data: reflecting the external pressure applied during the molding process; molding state data: changes in the appearance or shape of the component, etc.; material fluidity data: reflecting the state of the material flowing in the mold; the sensors collect data on each key parameter in real time to ensure that the acquired original state data set is highly representative and timely, providing reliable data support for subsequent analysis.

[0084] More specifically, a historical reference database is used, which contains past operation data and molding patterns. These historical data reflect the operation performance under different molding conditions. According to the collected original state data set, historical data matching processing is performed on it. By comparing it with the historical data of similar conditions in the database, the deviation between the original state data and the historical operation data set is calculated, and the deviation reference feature distribution is obtained. Through historical data matching, the difference between the current operation and the historical operation can be revealed, which helps to judge the deviation in the current component molding process and provide a basis for subsequent optimization.

[0085] More specifically, the deviation reference feature distribution is visualized through a scatter plot to observe the relationship between different variables. By analyzing the scatter plot spectrum, variables that may have a linear relationship are identified. Based on the relationship between linear variables, the linear deviation sequence related to the molding process is extracted. Through the scatter plot and linear observation, the correlation and trend between different variables can be clearly seen, which helps to identify which factors have a greater impact on the molding process. By extracting the linear deviation sequence, the deviation between the current molding process and the historical pattern can be clearly pointed out, helping to locate potential quality problems.

[0086] More specifically, the obtained linear deviation sequence is information mapped to generate a pre-analysis feature matrix, which will contain information of all key features and have corresponding matrix characteristics. The feature matrix includes not only linear deviations, but may also contain other nonlinear features, time series features, etc., thereby providing sufficient input data for subsequent deep learning analysis. By mapping the deviation sequence, the obtained feature matrix has a strong multi-dimensional information expression capability, which provides sufficient training data for the deep learning algorithm model.

[0087] More specifically, the feature matrix obtained above is input into a pre-trained deep learning algorithm model. The deep learning algorithm model is selected. Different types of deep learning algorithm models can be used, including: Convolutional Neural Network (CNN): suitable for processing data with spatial structure, usually used for image or feature extraction tasks; Recurrent Neural Network (RNN): suitable for processing sequence data, and can identify time series features in the data; Long Short-Term Memory Network (LSTM): as a special form of RNN, it is more suitable for processing long sequence data and can effectively capture long-term dependencies. Through the training and reasoning of the deep learning algorithm model, the connection forming mode of the current forming operation is obtained, including the optimal parameter setting of the forming process, the operation timing, etc. The deep learning algorithm model can automatically extract complex nonlinear features from the data, not only provide accurate connection forming mode prediction, but also automatically identify potential mode changes. The deep learning algorithm model can identify subtle changes in the forming process through training on a large amount of data, thereby improving the accuracy and reliability of the connection forming mode prediction.

[0088] More specifically, after training and reasoning, the deep learning algorithm model outputs a connection molding mode. This mode includes which operating parameters are optimal in the current molding process, when is the best time to connect, and whether the operating strategy needs to be adjusted under the current characteristic conditions. This process can achieve a comprehensive prediction of the current molding process and ensure that the connection operation can be carried out at the best time, thereby maximizing the molding quality and production efficiency. Based on the feedback of the deep learning algorithm model, various operations in the production process can be continuously optimized, and molding conditions can be adjusted in time to meet different production needs.

[0089] Preferably, the pre-training step of the deep learning algorithm model includes: S401: Collecting several original state data sets for training through data simulation experiments and actual operation experiments, and performing format conversion and evaluation annotation on each of the original state data sets to obtain a corresponding pre-analysis feature matrix and pattern evaluation annotation, and combining each of the pre-analysis feature matrices with the corresponding pattern evaluation annotation to obtain a group of training data, and each group of training data together constitutes an overall data set; S402: Divide the overall data set into a training set, a validation set, and a test set; S403: Substituting the training set into the deep learning algorithm model, allowing the deep learning algorithm model to perform model training on the training set, and synchronously adjusting model parameters of the deep learning algorithm model according to the result of the model training; S404: After each round of model training of the training set is completed, the verification set is substituted into the deep learning algorithm model, and the deep learning algorithm model is allowed to perform model verification on the verification set, so as to check whether there is overfitting through the verification result, and adjust the model hyperparameters according to the verification result; S405: After completing the model training of the training set, the test set is substituted into the deep learning algorithm model, and the deep learning algorithm model is allowed to perform a model test on the test set, so as to check the model accuracy through the test results and decide whether to end the training.

[0090] Specifically, several original state data sets for training are collected through data simulation experiments and actual operation experiments. These data sets may include relevant process parameters and process information such as temperature, pressure, and material fluidity. The collected original data sets are formatted to meet the model input requirements, and the data are evaluated and annotated. These annotations may include state labels of the molding mode (for example, normal, abnormal, deviation, etc.). Through feature extraction, the original data is converted into a feature matrix to form a pre-analysis feature matrix, and combined with the corresponding mode evaluation annotations (for example, the quality of operation or the advantages and disadvantages of the molding mode) as the goal of model training. Through format conversion, the data can be effectively input into the deep learning algorithm model, avoiding the problems caused by inconsistent data formats. The evaluation annotations ensure that the actual situation of the data can be reflected in the training process, which helps to train a model that meets actual needs.

[0091] More specifically, each pre-analysis feature matrix is ​​combined with the corresponding mode evaluation annotation to obtain a set of training data. Each set of data contains input (feature matrix) and output (annotation) information. All training data are merged into an overall data set, which will be used for subsequent training, verification and testing processes. By integrating data from different sources, it is ensured that the training set has sufficient diversity to cover a variety of possible molding modes and operating scenarios. The training data not only contains input features, but also correct annotations, which helps the model learn the accurate relationship between input and output.

[0092] More specifically, the overall data set is divided into a certain proportion (such as 70% training set, 15% validation set, and 15% test set): Training set: used for model training, through which the model learns the mapping relationship between features and outputs; Validation set: used for verification during the training process to check whether the model is overfitting or underfitting, and to adjust the model hyperparameters; Test set: used to evaluate the final performance of the model after training, and to test its accuracy and generalization ability on unseen data. Using training, validation, and test data separately effectively prevents data leakage and ensures the performance evaluation of the model on unseen data. By dividing the validation set and the test set, the complexity of the model can be effectively controlled to avoid overfitting.

[0093] More specifically, the training set is input into the deep learning algorithm model for model training. The model continuously adjusts internal parameters (such as weights and biases) through a back-propagation algorithm (such as gradient descent) to make the prediction results as close to the true annotations as possible. After each round of training, the model automatically adjusts its parameters (such as learning rate, weights, etc.) according to the feedback of the loss function to optimize the performance of the model. Through multiple iterations of the training set, the model gradually adjusts its parameters and optimizes the performance, and ultimately a lower error can be obtained on the training data. By gradually adjusting the model parameters, the model can quickly adapt to the training data and effectively reduce errors.

[0094] Adjust model parameters synchronously: After each round of training, the validation set data is input into the model for verification. The difference between the prediction results of the validation set and the actual annotation is calculated to determine whether the model is overfitting. If the error on the validation set is large and the error on the training set is small, it may indicate that the model is overfitting, that is, the model is too focused on the details of the training data, resulting in poor generalization ability. According to the verification results, the model's hyperparameters (such as learning rate, number of layers, number of neurons, etc.) will be adjusted to improve the model's generalization ability. By checking the validation set, overfitting can be discovered in time, and measures can be taken to correct it. By adjusting the hyperparameters, the model's ability to adapt to new data can be enhanced, improving its performance in real scenarios.

[0095] Adjust model parameters synchronously: After the training of the training set and validation set is completed, the test set is input into the trained deep learning algorithm model for testing. The test set is used to evaluate the real performance of the model and check its prediction accuracy on unseen data. By comparing the prediction results of the model on the test set with the real labels, the accuracy, precision, recall rate and other indicators of the model are calculated to judge the final effect of the model. Through the test set, the prediction ability of the model can be truly evaluated to ensure its effectiveness in practical applications. Through the evaluation of the test set, it can be ensured that the trained model has sufficient accuracy and can run stably in the actual production environment.

[0096] Adjust model parameters synchronously: If the performance of the model on the test set reaches the predetermined accuracy or performance requirements, the training can be considered completed. If it does not meet the requirements, it is necessary to return to the training stage and continue to optimize the model. After the training is completed, the trained model and its parameters are saved for subsequent use. After multiple rounds of training, verification and testing, the model can eventually perform prediction tasks stably. The saved model can be directly applied to the actual molding process prediction to further improve production efficiency and product quality.

[0097] Preferably, the step of synchronously adjusting the functional parameters of the rubber demoulding tube according to the connection forming mode to perform real-time correction of the component connection structure of each component prototype and combine the molding of each component prototype so that each component prototype is combined to obtain the target rubber finished product includes: S51: Acquire structural information of an existing component connection structure of the rubber demoulding tube; wherein the component connection structure includes an internal insertion guide structure and an external pressure constraint structure; S52: performing a subsequent demand analysis of the component connection structure on the structural information of the component connection structure according to the connection forming mode, so as to obtain an internal guide supplement demand and an external pressure adjustment demand of the component connection structure; S53: According to the internal guide supplementation requirements and the external pressure adjustment requirements, the component connection structure of each component prototype is modified in real time to promote the molding and combination of each component prototype, so that each component prototype is combined to obtain the target rubber product.

[0098] Specifically, the detailed information of the component connection structure of the current rubber demolding tube is obtained. This structural information usually includes the geometric shape, size, position, and connection method and connection structure of the components. The types of component connection structures include internal insertion guide structure: this is the internal connection method between components, and the components are fixed and connected through an inserted connection structure to ensure the stability of the components; external pressure constraint structure, which is a structure that applies pressure to the outside of the component, through annular pressure, external coating or clamping, etc., to ensure that the component maintains the correct shape and position during the molding process. Obtaining detailed information on the component connection structure provides an accurate foundation for subsequent optimization, ensuring the correct docking of all components during the connection process. By analyzing the existing structure, a preliminary framework and data support are provided for subsequent optimization to avoid conflicts in the later modification process.

[0099] More specifically, according to the connection forming mode, a subsequent demand analysis of the component connection structure is carried out, and the analysis content mainly includes: internal guide supplementary needs: assess whether there are problems with inaccurate docking position, mismatched shapes, or insufficient docking strength based on the existing internal insertion guide structure, and which components or connection structures need to be supplemented or adjusted; external pressure adjustment needs: determine whether it is necessary to adjust the design of the external pressure constraint structure based on the pressure distribution of each component during the forming process to ensure that the pressure can be evenly and properly distributed to avoid forming defects (such as warping, cracking, etc.). Through subsequent demand analysis, the deficiencies in the connection structure of each component can be clearly identified, and corresponding adjustment strategies can be formulated. The analysis of the internal guide structure and the external pressure constraint structure can avoid deformation or connection failure due to structural problems during the forming process.

[0100] More specifically, based on the analyzed internal guidance supplementary needs, the guidance structure of the component is modified in real time, including: adding guide pins or sockets to enhance the stability of component docking, adjusting the insertion depth or angle of the component to enable more precise docking, and optimizing the shape or material of the insertion part to reduce friction during the docking process, ensure better fluid dynamics, and reduce molding defects.

[0101] More specifically, according to the external pressure adjustment requirements, the pressure constraint structure outside the component is optimized. The specific adjustments include: increasing or decreasing the pressure of the external coating to adapt to the shrinkage characteristics of different component materials, adjusting the shape or thickness of the external packaging structure so that the pressure can be evenly applied to the component surface to avoid excessive or insufficient local pressure causing molding defects, using different materials or improving surface treatment technology to improve pressure distribution, ensuring the stability of the component molding process, and through real-time correction, it can ensure that the connection between the various components is more precise, avoiding molding failures caused by loose connections, misalignment and other problems. By adjusting the external pressure constraint structure, the various components under pressure during the molding process can be made more stable, thereby improving the molding quality and avoiding dimensional deviations or quality defects in the finished product.

[0102] More specifically, the corrected component connection structure can ensure that the prototypes of each component (i.e., the initial shapes of each molded component) are seamlessly connected during the combination process. On the basis of the correction of the component connection structure, other factors in the molding process (such as temperature, pressure, time, etc.) are monitored and adjusted in real time to ensure that each component can be smoothly combined to eventually form the target rubber product. The connection structure and molding combination between components can proceed more smoothly, reducing problems such as jamming, misalignment, and deformation during the molding process. Through real-time correction and adjustment, the correct combination of each component can be maintained during the molding process, thereby ensuring the dimensional accuracy and functional stability of the final rubber product.

[0103] More specifically, through the correction and adjustment of the above-mentioned connection structure, the prototypes of various components are combined and finally formed into the target rubber demolding tube. The finished rubber product after molding is quality inspected to ensure that it meets the target design requirements, including size, strength, durability, etc. By optimizing the connection molding mode, it is ensured that the final rubber product meets the predetermined quality standards and has good strength, wear resistance and service life. The corrected and optimized connection molding mode can greatly improve production efficiency, reduce scrap rate and reduce production costs.

[0104] In a second aspect, the present invention provides an injection molding device for a rubber demoulding tube, which is used to implement the injection molding method for a rubber demoulding tube as described in any one of the first aspects.

[0105] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for injection molding a rubber demoulding tube, characterized in that: include: Acquire design data of a target rubber product and preparation performance information of a rubber demoulding tube, and disassemble the components of the molding structure of the design data according to the preparation performance information to obtain a molding structure preparation plan of the target rubber product; According to the molding structure preparation scheme, each preparation unit of the rubber demoulding tube is initially configured with functional parameters and pre-processed with component preparation materials to obtain the prototypes of each component of the target rubber finished product; Observe the morphological progress of each component prototype of the target rubber finished product, and synchronously drive the rubber demoulding tube to construct a component connection structure for each component prototype based on the observation result, so as to perform a molding and combining operation on each component prototype through the component connection structure; According to the historical reference database and the deep learning algorithm model, data collection and feature analysis of the connection forming mode of each component prototype in the forming combination operation are performed to obtain the connection forming mode; The functional parameters of the rubber demoulding tube are synchronously adjusted according to the connection forming mode, so as to carry out real-time correction of the component connection structure of each component prototype and combine it with the forming of each component prototype, so that each component prototype is combined to obtain the target rubber finished product.

2. The method for injection molding of a rubber demoulding tube according to claim 1, characterized in that: The steps of obtaining design data of a target rubber product and preparation performance information of a rubber demoulding tube, and disassembling components of a molding structure of the design data according to the preparation performance information to obtain a molding structure preparation scheme of the target rubber product include: Acquire design data of a target rubber product; wherein the design data includes 3D structural information of the target rubber product and a performance requirement annotation set corresponding to the 3D structural information; Acquire the preparation performance information of the rubber demoulding tube; wherein the preparation performance information of the rubber demoulding tube includes the performance information of each preparation unit and the performance information of each connection unit; Digitally modeling the target rubber product according to the 3D structure information, and feature-labeling the digital modeling of the target rubber product according to the performance requirement labeling set to obtain a digital model of the product; The component disassembly scheme of the finished digital model is simulated to obtain several original disassembly schemes of the finished digital model, and the process of single component preparation and connection of each component is simulated and the effect is evaluated for the various original disassembly schemes of the finished digital model according to the performance information of each preparation unit and each connection unit. According to the evaluation results, the component disassembly form, single component preparation method and each component connection method of each original disassembly scheme are feedback optimized to obtain the component disassembly form, single component preparation method and each component connection method with the best simulation evaluation results.

3. The method for injection molding of a rubber demoulding tube according to claim 2, characterized in that: The steps of initially configuring the functional parameters of each preparation unit of the rubber demoulding tube and pre-processing the component preparation materials according to the molding structure preparation scheme to obtain the prototypes of each component of the target rubber finished product include: Initially configuring the cavity morphology function parameters of each preparation unit of the rubber demoulding tube according to the component disassembly form in the molding structure preparation scheme, so that the preparation cavity of each preparation unit adapts to the structural information of the finished product component to be prepared; Initially configuring the heating function parameters of the temperature control modules of each of the preparation units according to the single component preparation method in the molding structure preparation scheme, so that the preparation cavity of each of the preparation units is in a heating state of specified specifications; According to the single component preparation method in the molding structure preparation scheme, the inlet of each preparation unit is filled with component preparation materials in an orderly manner, so that the preparation cavity of each preparation unit sequentially receives the component preparation materials filled through the inlet; wherein the component preparation materials include main materials and auxiliary materials, the main materials include silicone, fluororubber or chloroprene rubber, and the auxiliary materials include fillers, plasticizers or cross-linking agents; By performing real-time temperature control synchronization control on the temperature control modules of each of the preparation units, each of the preparation units heats and mixes the component preparation materials that are orderly filled into the preparation cavity, so that the component preparation materials in the preparation cavity of each of the preparation units are prepared into corresponding component prototypes through heating and mixing at different temperature specifications.

4. The method for injection molding of a rubber demoulding tube according to claim 2, characterized in that: The steps of observing the morphological progress of each component prototype of the target rubber finished product, and synchronously driving the rubber demoulding tube to construct a component connection structure for each component prototype based on the observation result, so as to perform a molding and combining operation on each component prototype through the component connection structure include: The multi-dimensional data of each component prototype of the target rubber product is collected by a sensor group preset on each preparation unit to obtain multi-dimensional feedback data of the component prototype of each preparation unit; wherein the sensor group includes a temperature sensor, a pressure sensor and a visual sensor, and the multi-dimensional feedback data includes temperature data, pressure data and visual data; Performing a morphological progress analysis on the component prototype according to the multi-dimensional feedback data to obtain a morphological progress feature of the component prototype at the current moment; Performing a continuous trend analysis on the morphological progress characteristics of the component prototype at each continuous moment, and performing a forward correlation feature analysis on the morphological progress characteristics at the current moment according to the result of the trend analysis, so as to obtain a forward correlation feature of the morphological progress characteristics of the component prototype at the current moment; According to the connection mode of each component in the molding structure preparation plan, the morphological progress characteristics and the forward correlation characteristics of each component prototype at the current moment are referenced and analyzed to determine whether the connection work can be started; When the result of the reference analysis shows that the connection work can be started, the transfer order of the component prototypes in the preparation cavity of each preparation unit to the inside of the cavity for molding combination is determined according to the connection mode of each component in the molding structure preparation plan, and the component prototypes with the first transfer order are marked as molding bases, and the component prototypes with the subsequent transfer order are marked as molding assemblies; The preparation unit where the molding substrate is located is driven to transfer the molding substrate to a cavity for molding combination, and a component connection structure is constructed for the docking position of each molding assembly corresponding to the molding substrate, so as to obtain a component connection structure of each molding assembly corresponding to the molding substrate; wherein the component connection structure includes an internal insertion guide structure and an external pressure constraint structure; The preparation unit where the molding assembly is located is driven to transfer the molding assembly to the inside of the cavity for the molding structure, so that the molding assembly is docked with the molding substrate through the component connection structure in the cavity for the molding assembly.

5. The method for injection molding of a rubber demoulding tube according to claim 4, characterized in that: The steps of referring to and analyzing the morphological progress characteristics and the forward correlation characteristics of the prototypes of the components at the current moment according to the connection mode of each component in the molding structure preparation scheme to determine whether the connection work can be started include: According to the connection mode of each component in the molding structure preparation plan, a weighted comprehensive analysis is performed on the morphological progress characteristics and the forward correlation characteristics of each component prototype at the current moment to obtain the connection timing characteristics of the component prototype at the current moment; Performing parameter conversion and parameter linking on the connection timing characteristics of each preparation unit of the rubber demoulding tube to obtain a connection parameter matrix for providing data feedback on the overall connection timing of the rubber demoulding tube; Based on the connection parameter matrix, multi-dimensional extraction of matrix expression features is performed on each of the component prototypes, and the extracted multi-dimensional matrix expression features are used as constraints. According to the constraints, the connection parameter matrix is ​​reversely analyzed for the expected theoretical expression features of subsequent time nodes to obtain the theoretical expression features of the connection parameter matrix at subsequent time nodes; According to the theoretical description characteristics of the connection parameter matrix at subsequent time nodes, the timing of starting the connection work of each preparation unit of the rubber demoulding tube is analyzed, and the directional working parameters of each preparation unit of the rubber demoulding tube are synchronously adjusted according to the theoretical description characteristics, so that the multi-dimensional matrix description characteristics of the connection parameter matrix brought by the working parameters of each preparation unit at subsequent time nodes meet the theoretical description characteristics; The timing analysis results of the theoretical expression characteristics are analyzed to obtain the results of the reference analysis.

6. The method for injection molding of a rubber demoulding tube according to claim 1, characterized in that: The steps of collecting data and analyzing features of the connection forming mode of each component prototype in the forming combination operation according to the historical reference database and the deep learning algorithm model to obtain the connection forming mode include: The molding combination state of each of the component prototypes in the molding combination operation is subjected to data collection and feature analysis through a preset sensor group, so as to obtain an original state data set of the molding combination state of each of the component prototypes; wherein the original state data set includes the original state data of each detection time node, and the original state data includes temperature data, pressure data, molding state data, and material fluidity data; Performing a reference matching process of historical data on the original state data set according to the historical reference database to obtain a deviation reference feature distribution between the original state data set and a plurality of historical operation data sets in the historical reference database; Performing scatter plotting and linear variable observation on the distribution of each deviation reference feature to obtain a linear deviation sequence of the original state data set, and performing information mapping of a pre-analysis feature matrix on the linear deviation sequence so that the pre-analysis feature matrix has matrix features corresponding to the linear deviation sequence; Substituting a pre-analyzed feature matrix having matrix features corresponding to the linear deviation sequence into a pre-trained deep learning algorithm model; wherein the deep learning algorithm model includes a convolutional neural network, a recurrent neural network, or a long short-term memory network; The deep learning algorithm model is enabled to perform a deep analysis of the connection and forming patterns of the prototypes of each component on the pre-analysis feature matrix to obtain the connection and forming patterns.

7. The method for injection molding of a rubber demoulding tube according to claim 6, characterized in that: The pre-training steps of the deep learning algorithm model include: Through data simulation experiments and actual operation experiments, several original state data sets for training are collected, and each of the original state data sets is format converted and evaluated and annotated to obtain a corresponding pre-analysis feature matrix and pattern evaluation annotation, and each of the pre-analysis feature matrices and the corresponding pattern evaluation annotations are combined to obtain a group of training data, and each group of training data together constitutes an overall data set; Dividing the overall data set into a training set, a validation set, and a test set; Substituting the training set into the deep learning algorithm model, allowing the deep learning algorithm model to perform model training on the training set, and synchronously adjusting the model parameters of the deep learning algorithm model according to the results of the model training; After each round of model training of the training set is completed, the verification set is substituted into the deep learning algorithm model, and the deep learning algorithm model is allowed to perform model verification on the verification set, so as to check whether there is overfitting through the verification results, and adjust the model hyperparameters according to the verification results; After completing the model training of the training set, the test set is substituted into the deep learning algorithm model, and the deep learning algorithm model is allowed to perform model testing on the test set to check the model accuracy through the test results to decide whether to end the training.

8. The method for injection molding of a rubber demoulding tube according to claim 1, characterized in that: The steps of synchronously adjusting the functional parameters of the rubber demoulding tube according to the connection forming mode, so as to perform real-time correction of the component connection structure of each component prototype and combine the molding of each component prototype so that each component prototype is combined to obtain the target rubber finished product include: Acquire structural information of an existing component connection structure of the rubber demoulding tube; wherein the component connection structure includes an internal insertion guide structure and an external pressure restraint structure; Performing a subsequent demand analysis of the component connection structure on the structural information of the component connection structure according to the connection forming mode, so as to obtain the internal guidance supplement demand and the external pressure adjustment demand of the component connection structure; According to the internal guide supplementation requirements and the external pressure adjustment requirements, the component connection structure of each component prototype is corrected in real time to promote the molding and combination of each component prototype, so that each component prototype is combined to obtain the target rubber product.

9. An injection molding device for a rubber demoulding tube, characterized in that: An injection molding method for realizing a rubber demoulding tube as described in any one of claims 1 to 8.

Images