Injection molding method of anti-aging simulation plant

Abstract

The invention discloses an injection molding method of an anti-aging simulation plant. The injection molding method comprises the following steps: preparing raw materials; uniformly mixing the raw materials according to a set material proportioning model so as to obtain anti-aging proportioning raw materials exceeding a preset threshold value; according to the shape and the size of the simulation plant, through a system integrated with an intelligent design engine, design data are extracted, and a design mold is generated; the proportioned raw materials are heated in a heating cylinder of an injection molding machine to be in a molten state, and molten plastic is obtained; the molds are firmly clamped together; injecting the molten plastic into the cavity of a mold under a predetermined pressure; a preset pressure of a preset time is kept in the cavity; cooling and solidifying the material in the mold to form the shape of the mold; and opening the mold to obtain the formed simulation plant. According to the technical scheme, the service life of the anti-aging simulation plant is prolonged, and the safety of the anti-aging simulation plant is improved by optimizing the raw material ratio, accurately controlling the injection molding process and other key steps.

Description

Technical Field

[0001] The present invention generally relates to the field of artificial intelligence technology. More specifically, the present invention relates to an injection molding method for anti-aging simulated plants. Background Art

[0002] The injection molding process involves injecting molten plastic material into a mold and solidifying it into the desired shape after cooling. However, the selection of raw materials in production currently relies mainly on empirical models, which makes it difficult to output optimized material ratios according to different needs. This empirical selection method makes it difficult to accurately control the material ratio of each batch, thus affecting the consistency of product quality.

[0003] In addition, the injection molding process also faces a variety of quality problems, such as aging, shrinkage, shrinkage, warping, etc. These problems may be caused by factors such as unreasonable material ratio, unreasonable mold design, improper molding process control, or mismatch of plastic material characteristics. For example, the thermophysical properties and rheological properties of different polymer materials vary greatly. Even under the same molding conditions, the quality of the products (including anti-aging) may vary significantly. These problems not only affect the appearance quality of the product, but may also affect the safety and functionality of the product.

[0004] In view of this, it is urgent to provide an injection molding method for anti-aging simulated plants so as to improve the quality of the product. Summary of the invention

[0005] In order to at least solve one or more of the above-mentioned technical problems, the present invention provides an injection molding method for an anti-aging simulated plant.

[0006] The technical solution provided by the embodiment of the present invention includes: Prepare raw materials, which include a base material: polyethylene (PE), and one or more of the following additives: intelligent temperature-regulating masterbatch, anti-aging additive, color masterbatch, temperature-changing masterbatch, UV masterbatch or flame retardant.

[0007] According to the set material ratio model, the raw materials are mixed evenly to obtain the anti-aging ratio raw materials exceeding the preset threshold.

[0008] According to the shape and size of the simulated plant, the design data is extracted and a design mold is generated through a system integrating an intelligent design engine; the mold includes a cavity.

[0009] The raw materials with good proportions are heated in a heating cylinder of an injection molding machine to a molten state to obtain molten plastic.

[0010] The mold is firmly clamped together; the molten plastic is injected into the mold cavity of the mold under a predetermined pressure. The predetermined pressure is maintained in the mold cavity for a predetermined time. The material in the mold is cooled and solidified to form the shape of the mold. The mold is opened to obtain a molded simulated plant.

[0011] In some embodiments, the preparation of the intelligent temperature-regulating masterbatch includes: adding a phase change material and a shell material monomer aqueous solution into an organic solvent containing a surfactant to form an inverse emulsion, heating the inverse emulsion to react, and separating to obtain a phase change microcapsule with a hydrophobic surface.

[0012] In some embodiments, the steps of constructing the material ratio model include: collecting historical mixing data and material performance data; according to a deep learning algorithm, using the historical mixing data and material performance data to perform performance learning training on the material ratio model to obtain a material ratio model; using the trained material ratio model to simulate different mixing ratios to obtain an anti-aging raw material ratio that exceeds a preset threshold.

[0013] In some embodiments, the ratio of the anti-aging raw materials that exceeds the preset threshold includes: polyethylene: 35-75 parts, temperature-sensitive masterbatch: 20-50 parts, color masterbatch: 1-3 parts, UV masterbatch: 1-3 parts, flame retardant: 1-5 parts; wherein the temperature-sensitive masterbatch includes temperature-sensitive microcapsules, preservatives, and dispersants; the UV masterbatch includes light stabilizers and ultraviolet light absorbers.

[0014] In some embodiments, the system integrating the intelligent design engine includes: collecting historical mold design data; using the historical mold design data and machine learning algorithms to identify and predict key factors affecting mold design performance; automatically extracting design data based on the key factors and generating a preliminary design plan; simulating the performance of the mold under actual working conditions through finite element analysis methods, predicting problems that will arise and adjusting the preliminary design plan.

[0015] In some embodiments, the method of identifying and predicting key factors affecting mold design performance through historical mold design data and using a machine learning algorithm includes: using a feature selection method to screen out key features that affect mold performance from the historical mold design data; and training a deep learning model to predict the performance of the mold under different working conditions.

[0016] By providing an anti-aging simulated plant injection molding method as described above, the embodiment of the present invention can significantly improve the anti-aging performance of the simulated plant by adding anti-aging additives to the raw materials, so that the color and shape stability can be maintained during long-term outdoor use. By adding flame retardants, the simulated plant can slow down the burning speed or prevent burning when encountering a fire source, thereby improving the safety of the product. By adding intelligent temperature-regulating masterbatch and temperature-changing masterbatch, the simulated plant can adjust its own temperature according to the change of ambient temperature, and the color changes with the temperature, thereby increasing the intelligence and interactivity of the product. Further, in some embodiments, the raw materials are optimized to mix in a ratio through a deep learning algorithm to obtain an anti-aging raw material ratio that exceeds a preset threshold, thereby ensuring the uniformity and stability of the material and improving the quality of the simulated plant injection molding. Furthermore, in some embodiments, artificial intelligence technology, such as a deep learning algorithm, is effectively used to identify and predict key factors affecting the performance of the mold design, thereby improving the accuracy and efficiency of the mold. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 An exemplary flow chart of an injection molding method of an anti-aging simulated plant according to some embodiments of the present invention is shown. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0020] Figure 1 An exemplary flow chart of an injection molding method 100 of an anti-aging artificial plant according to some embodiments of the present invention is shown.

[0021] like Figure 1As shown, in method 100, an injection molding method for anti-aging simulated plants includes: step S101: preparing raw materials. The raw materials include a base material: polyethylene (PE), and one or more of the following additives: intelligent temperature-regulating masterbatch, anti-aging additive, color masterbatch, temperature-changing masterbatch, UV masterbatch or flame retardant.

[0022] In the embodiment scheme provided by the present invention, polyethylene (PE) can be selected as the base material because it has good processing performance and cost-effectiveness. In some embodiments, in order to improve the anti-aging performance, ultraviolet light curing technology, special functional group addition and other technologies can also be combined. Specifically, in the preparation process of polyethylene composite materials, the use of ultraviolet light curing technology can improve the aging resistance of the material. The wavelength of ultraviolet light in ultraviolet light curing is 320-400nm, and the energy is 150-300mj. When adding special functional groups, by adding functional groups such as zinc bromide, tetrabromobisphenol A and silsesquioxane to the aging-resistant polyethylene composite material, the aging resistance and abrasion resistance of the material can be improved.

[0023] In one embodiment, the anti-aging performance of the product can be improved by introducing a 2000-hour anti-aging masterbatch for polypropylene, including homopolymer polypropylene, a primary antioxidant, an auxiliary antioxidant, an ultraviolet absorber, a hindered amine light stabilizer, an auxiliary light stabilizer, and a dispersant.

[0024] Through the combination of the above technologies, the embodiment scheme provided by the present invention can significantly improve the anti-aging performance of the simulated plant.

[0025] In one embodiment, the preparation of the intelligent temperature-adjusting masterbatch includes: adding a phase change material and a shell material monomer aqueous solution into an organic solvent containing a surfactant to form an inverse emulsion, heating the inverse emulsion for reaction, and separating to obtain a phase change microcapsule with a hydrophobic surface.

[0026] Furthermore, when preparing the temperature-changing masterbatch, the required materials may include temperature-sensitive microcapsules, preservatives, dispersants and PE. The temperature-sensitive microcapsules can make the plants present different colors at different temperatures, increasing the simulation effect. Next, prepare UV masterbatch to improve the light resistance and anti-aging properties of plants. You can choose light stabilizers, ultraviolet light absorbers, etc. And add flame retardants, such as brominated flame retardants, magnesium hydroxide, etc., to improve the safety of plants.

[0027] Furthermore, in some embodiments, if special effects are to be achieved, for simulated plants that require temperature-sensitive color-changing effects, specific temperature-sensitive materials, such as a mixture of diethylamine hydrochloride and cupric chloride dihydrate, and nano-titanium dioxide can be added to the temperature-changing masterbatch to achieve color changes when the temperature changes. For simulated plants that require light-sensitive color-changing effects, photosensitive materials, such as light stabilizers and ultraviolet light absorbers, can be added to improve the color stability of the plants under light.

[0028] In order to verify the special effect, a temperature sensitivity test can be carried out, where the sample is placed at different temperatures and its color changes are observed to ensure the temperature-sensitive color change effect. A light resistance test can also be carried out, where the sample is placed in a simulated artificial sunlight climate for 500 hours to check the color and morphological changes of the plant to ensure light resistance and anti-aging properties.

[0029] Through the preparation of the above raw materials, artificial plants that are both beautiful and anti-aging can be produced. These plants can not only simulate the appearance of real plants, but also maintain the stability of their color and form under different environmental conditions. This can significantly improve the anti-aging performance, safety, environmental adaptability and overall effect of artificial plants, so that they can maintain a lasting landscape effect in various environments.

[0030] Further, in step S102: according to the set material ratio model, the raw materials are mixed evenly to obtain the anti-aging ratio raw materials exceeding the preset threshold.

[0031] In one embodiment, the step of constructing the material ratio model includes: collecting historical mixing data and material performance data. According to a deep learning algorithm, the material ratio model is trained using the historical mixing data and material performance data to obtain a material ratio model. Using the trained material ratio model, different mixing ratios are simulated to obtain an anti-aging raw material ratio that exceeds a preset threshold.

[0032] Collect historical mixing data and material performance data, including material performance parameters under different ratios, such as tensile strength, aging resistance, etc., as well as density, compressive strength, tensile strength, cohesion, internal friction angle, dynamic elastic modulus, dynamic Poisson's ratio, static elastic modulus and other parameters under different ratios.

[0033] Using deep learning feature selection techniques such as autoencoders or feature importance assessment, key features that have a significant impact on material properties can be screened out from large amounts of data.

[0034] The collected data is used to train deep learning models, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs), to predict the effects of different mixing ratios on material properties.

[0035] The following uses anti-aging performance as an example to illustrate the learning and training process using a deep learning model. The formula includes: Let f be the anti-aging performance function, For different environmental factors and material parameters, including temperature T, humidity H, solar radiation R, material ratio C, etc.

[0036] The relationship between these factors and the anti-aging performance y is: y = f( ).

[0037] Among the above factors, T is temperature, in degrees Celsius (℃), which affects the aging rate of the material; H is humidity, in percentage (%), which affects the hygroscopicity and expansion of the material. R is solar radiation, in megajoules per square meter (MJ / m²), which affects the photodegradation of the material. C is the material ratio, including the proportion of different additives, such as anti-aging additives, masterbatches, and intelligent temperature-regulating masterbatches.

[0038] A deep learning model, such as a neural network, is used to learn the relationship between the above factors and anti-aging performance. The model can be expressed as: y=NN(T,H,R,C), where NN represents a neural network, which can be a multi-layer perceptron (MLP) including an input layer, a hidden layer, and an output layer.

[0039] Next, training and validation are performed. Specifically, the deep learning model is trained using historical data sets, which include changes in material performance parameters under different environmental conditions. During the training process, the difference between the predicted performance and the actual performance can be minimized, such as the mean square error (MSE). The formula is: , in, It is the actual performance. is the performance of the model prediction and NN is the number of samples.

[0040] Furthermore, the performance of the model is optimized by adjusting the parameters of the neural network, such as the learning rate, the number of hidden layers, and the number of neurons. The trained model is then applied to new environmental conditions and material ratios to predict their anti-aging performance, and the material ratio is adjusted accordingly to optimize performance.

[0041] Using the trained model, the best raw material ratio is predicted and optimized by simulating different mixing ratios to achieve the desired material properties.

[0042] Based on the above-mentioned embodiments of the present invention, those skilled in the art can understand that in the scenario of large-scale production, an online detection system can be used to monitor product size and mixing quality in real time, and artificial intelligence technology can be used to analyze data to promptly discover and solve problems in production. New data collected during the production process is continuously input into the machine learning model, so that the model can continue to learn and optimize, further improving the optimization effect of the mixing ratio.

[0043] When data is scarce or labeling is expensive, active learning can be used to optimize and select samples that are most helpful for model improvement for training, thereby improving the learning efficiency and performance of the model.

[0044] Therefore, by building a material ratio model based on deep learning, the model can predict the impact of different environmental factors and material parameters on anti-aging performance, thereby providing scientific data support for the injection molding of simulated plants. This method takes into account multiple influencing factors, ensures the uniformity and stability of the material, and thus improves the quality of simulated plant injection molding.

[0045] In one embodiment, the specific ratio of raw materials for anti-aging can be: polyethylene: 35-75 parts, temperature-sensitive masterbatch: 20-50 parts, color masterbatch: 1-3 parts, UV masterbatch: 1-3 parts, flame retardant: 1-5 parts; wherein the temperature-sensitive masterbatch includes temperature-sensitive microcapsules, preservatives, and dispersants; and the UV masterbatch includes light stabilizers and ultraviolet light absorbers.

[0046] Further, in step S103: according to the shape and size of the simulated plant, the design data is extracted and a design mold is generated through a system integrating an intelligent design engine; the mold includes a cavity.

[0047] When designing the mold, to ensure that it accurately reflects the shape and size of the simulated plant, it can be made of metal such as steel or aluminum, including the cavity and core. The mold is manufactured using advanced manufacturing technologies such as CNC machining and electrical discharge machining (EDM).

[0048] In one embodiment, the system of the integrated intelligent design engine includes: collecting historical mold design data. Using the historical mold design data, using machine learning algorithms to identify and predict key factors affecting mold design performance; automatically extracting design data based on the key factors and generating a preliminary design plan; simulating the performance of the mold under actual working conditions through finite element analysis methods, predicting problems that will occur and adjusting the preliminary design plan.

[0049] In one embodiment, the method of identifying and predicting key factors affecting mold design performance through historical mold design data and using a machine learning algorithm includes: using a feature selection method to screen out key features that affect mold performance from the historical mold design data; and training a deep learning model to predict the performance of the mold under different working conditions.

[0050] Specifically, in order to use machine learning algorithms to identify and predict key factors that affect mold design performance through historical mold design data, and automatically extract design data to generate preliminary design solutions based on these key factors, the following steps and formulas can be used: First, the historical mold design data is cleaned and standardized to ensure data quality, including removing outliers, filling missing values, and normalizing.

[0051] Secondly, feature selection techniques such as filtering, packaging and embedding are used to select key features that have a significant impact on mold design performance from all features. For example, mutual information can be used to measure the dependency between features and target variables, and features with high mutual information can be selected.

[0052] Then, a machine learning model is trained to identify the key factors affecting the mold design performance. The model can be expressed as: , where y is the mold design performance, are the selected key features.

[0053] Use the model's feature importance assessment to determine the extent to which each feature affects the performance of the mold design.

[0054] Based on the assessed feature importance, the design data is automatically extracted. This step can be achieved by building a feature extraction model, which can be a neural network, for learning from historical data how to extract design data based on key features.

[0055] Finally, the extracted design data is combined with the predictions of the machine learning model to generate a preliminary design solution. This can be achieved through optimization algorithms, such as particle swarm optimization (PSO), which finds the optimal solution by simulating the foraging process of a flock of birds. The results predicted by the model are compared with the actual performance data, and the model is continuously improved iteratively to improve the accuracy of the prediction.

[0056] In the above embodiment, a system based on machine learning is constructed, which can automatically identify the key factors affecting the design performance of the mold, and automatically extract design data based on these factors to generate a preliminary design solution. This method not only improves the efficiency of the design, but also helps to optimize the performance of the mold.

[0057] In one embodiment, the finite element analysis method is used to simulate the performance of the mold under actual working conditions, predict possible problems and adjust the preliminary design scheme, including: Import the mold geometry model into a finite element analysis system, such as ANSYS. This can be achieved through the two-way mutual import function between the software and the CAD tool, ensuring that all features are retained and not lost in the model.

[0058] According to the actual working environment of the mold, the displacement and pressure boundary parameters are set to simulate the real injection molding environment; including the setting of cavity pressure and clamping force.

[0059] Meshing the entire mold to divide the complex geometry into a limited number of small cells for numerical calculations; Finite element analysis is used to calculate the overall deformation and stress distribution of the mold, so as to determine the size of the deformation and stress, as well as the location of the maximum / minimum stress and strain, and to check the structural strength of the mold in the working state.

[0060] In addition, ANSYS multi-condition analysis can be used to calculate the maximum clamping force and injection pressure that cause plastic strain in the mold to predict the limit working conditions of the mold. Optimization analysis can be performed based on molds of different sizes. The optimal mold size can be obtained while meeting the working requirements, saving material and manufacturing costs.

[0061] By effectively utilizing the finite element analysis method as described above to simulate the performance of the mold under actual working conditions, the mold design can be optimized and the mold service life and manufacturing efficiency can be improved.

[0062] Further, the process comes to step S104: heating the proportioned raw materials in the heating cylinder of the injection molding machine to a molten state to obtain molten plastic.

[0063] In order to accurately control the melting process of plastic materials in the heating cylinder of the injection molding machine, temperature control, back pressure control, and temperature and pressure monitoring of the molten plastic can be adopted. The specific temperature control can set the temperature curve of the heating cylinder according to the characteristics of the plastic material. The temperature curve usually includes several stages: preheating, melting, insulation and back pressure.

[0064] set up are the temperatures of the preheating, melting and holding stages, respectively. The corresponding time respectively.

[0065] The temperature curve can be expressed as: , Among them, T(t) is the temperature at time t, ensuring that the plastic material gradually melts during the heating process.

[0066] In back pressure control, back pressure B is crucial to improve melt density and uniformity. The back pressure setting can be expressed by the following formula: , where k is the proportionality coefficient and ΔP is the pressure difference between the screw and the barrel. Appropriate back pressure can improve the temperature and quality of the melt.

[0067] In the quality control of molten plastics, the flow properties of molten plastics can be evaluated by online detection systems, such as the melt flow index (MFI).

[0068] , Where M is the mass of the melt passing through a standard die under a certain time and pressure, and t is the time. The MFI value can be used to determine whether the molten plastic is suitable for injection molding.

[0069] Through the above control process, the melting process of the plastic material in the heating cylinder of the injection molding machine can be accurately controlled to ensure high-quality molten plastic and lay a solid foundation for subsequent injection molding.

[0070] In one embodiment, the proportioned materials are heated to a molten state in a heating cylinder of an injection molding machine, wherein the heating temperature is controlled at 190-260°C.

[0071] After obtaining the molten plastic, the process further proceeds to step S105: firmly clamping the mold together. This step can be performed by a clamping system, including a base, a clamping plate, and a fixed plate. The clamping plate is moved by, for example, a screw and a bearing to clamp the mold. The clamping effect of the clamped mold can be achieved by calculating the clamping force, determining the screw preload, calculating the moving distance of the clamping plate, analyzing the stability of the clamping device, and even an automated clamping control system. The clamping effect is verified by experiments to ensure the stability of the mold during the injection molding process. Specifically, destructive testing can be used to verify the performance of the clamping device under extreme conditions.

[0072] Improve production efficiency and product quality by ensuring the mold is firmly clamped together during the injection molding process.

[0073] Further, step S106: injecting the molten plastic into the cavity of the mold under a predetermined pressure.

[0074] In order to inject the molten plastic into the mold cavity under a predetermined pressure, the injection molding process needs to be precisely controlled to ensure that the plastic fills the mold cavity uniformly and completely. The following is a scenario description combined with an embodiment: Injection pressure P is the key parameter for pushing molten plastic into the cavity and can be calculated by the following formula: , where F is the injection force and A is the gate area. The injection force F can be calculated from the cylinder force and piston area of ​​the injection molding machine.

[0075] The injection speed v is very important for controlling plastic flow and reducing bubbles, and can be controlled by the following formula: , where d is the injection stroke and t is the injection time. The injection speed needs to be adjusted according to the fluidity of the plastic and the complexity of the cavity.

[0076] Fill time is the time required for the molten plastic to completely fill the cavity and can be estimated by the following formula: Filling time , where V is the volume of the cavity and Q is the injection flow rate. The flow rate Q can be calculated from the injection speed and the gate area.

[0077] Sensors are used to monitor the pressure, temperature, and speed of the injection molding process in real time to ensure the stability and consistency of the injection molding process. In addition, machine learning algorithms can be used to optimize injection molding parameters based on historical data and real-time monitoring data to improve product quality and production efficiency. Product quality checks can also be performed after injection molding, such as dimensional accuracy, surface quality, etc., and the results can be fed back into injection molding parameter optimization.

[0078] In one embodiment, the molten plastic is injected into the cavity of the mold under a predetermined pressure, and the predetermined pressure may be 70-120 bar.

[0079] According to the above embodiments of the present invention, during production, polyethylene, temperature-variable masterbatch, color masterbatch, flame retardant, and UV masterbatch can be mixed evenly, and then the blades can be injection molded at 190-260°C and 70-120 bar pressure. Then, polyethylene, UV masterbatch, color masterbatch, and flame retardant can be mixed evenly, and then the base plate can be injection molded at 190-280°C and 80-150 bar pressure. Finally, the injection molded blades are inserted into the base plate to form a complete simulated plant.

[0080] Further, step S107: maintaining a predetermined pressure in the cavity for a preset time.

[0081] The holding pressure is to compensate for the shrinkage of the plastic during the cooling process and can be calculated by the following formula: Holding pressure: ,in, It is the increase in pressure caused by the shrinkage of the plastic.

[0082] In one embodiment scenario, the factors affecting the predetermined pressure at the preset time include one or more of the following: plastic material, mold design, product shape and size, environmental conditions, injection molding machine parameters, field efficiency, and quality standards.

[0083] In the process of injection molding, the setting of holding time is very critical to ensure product quality. In actual production, the holding time can be determined by experiments, and it should not be too long or too short. If the holding time is too long, it will not only extend the molding cycle, but also make the residual pressure in the mold cavity too large, making it difficult to demold, or even unable to open the mold; it also increases energy consumption. The optimal holding time should be to make the residual pressure in the mold cavity zero when the mold is opened. Generally, the molding holding time of nylon 1010 injection molding parts is 4 to 50 seconds. The holding time must be at least until the sprue solidifies, which is generally about 30% of the cooling time. Therefore, the specific length of the holding time needs to be determined according to the specific material and product requirements, but it is usually between a few seconds and tens of seconds.

[0084] The predetermined pressure is maintained in the cavity for a preset time. The length of the holding time can be dynamically adjusted using historical data and real-time feedback to ensure product dimensional stability and reduce internal stress.

[0085] Further, in step S108: the material in the mold is cooled and solidified to form the shape of the mold.

[0086] When the molten plastic is injected into the cavity, the material in the mold begins to cool and solidify, forming the shape of the mold. The cooling time is the time required for the plastic to drop from the injection temperature to the solidification temperature. It depends on the specific type of plastic and the size of the product, and usually takes a few tens of seconds to a few minutes. The specific formula for calculating the cooling time can be: , in, is the specific heat capacity of the plastic, m is the mass of the plastic, k is the thermal conductivity of the plastic, is the cooling area.

[0087] Cools and solidifies the material in the mold to form the shape of the mold. The cooling system can be optimized through intelligent analysis, and more uniform and efficient cooling can be achieved by analyzing the flow and temperature distribution of the coolant.

[0088] Further, in step S109: the mold is opened to obtain a molded artificial plant. After cooling and solidification, the mold is opened and the part is usually ejected with the help of an ejector pin. The finished part is taken out of the mold and any excess material, such as runners or flash, is trimmed off.

[0089] The mold opens to obtain the molded artificial plant. The demoulding process can be controlled by monitoring and analysis to reduce the risk of product deformation and damage.

[0090] In summary, the present invention optimizes the raw material ratio by using a deep learning algorithm through historical mixing data and material performance data, thereby improving the anti-aging performance of the material and extending the service life of the product. By adding titanium dioxide and hydroxymethylated lignin to the raw materials, the light resistance of the simulated plants is improved, and fading under long-term light exposure is prevented, which helps to maintain the color stability of the product and enhance its durability for outdoor use. During the injection molding process, by precisely controlling the temperature and pressure conditions, it helps to reduce the thermal degradation of the material and improve the aging resistance of the product. And by precisely controlling the injection pressure and injection speed, the injection overpressure phenomenon can be effectively avoided, the injection effect can be improved, and thus the production efficiency and product quality can be improved.

[0091] Therefore, through the key steps of optimizing the raw material ratio, accurately controlling the injection molding process, improving light resistance and flame retardancy, reducing energy consumption, optimizing mold design, and accelerating material performance optimization using AI technology provided by the technical solution of the present invention, the service life, safety, energy saving effect and environmental friendliness of the anti-aging simulated plant are improved. Through the implementation of the injection molding method embodiment provided by the present invention, the injection molding method of the anti-aging simulated plant can be made more efficient, environmentally friendly and economical.

[0092] Although multiple embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art may conceive of many changes, modifications, and alternatives without departing from the thought and spirit of the present invention. It should be understood that in the process of practicing the present invention, various alternatives to the embodiments of the present invention described herein may be adopted. The appended claims are intended to define the scope of protection of the present invention, and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. An injection molding method for anti-aging simulated plants, characterized in that: include: Prepare raw materials, the raw materials including base material: polyethylene (PE), and one or more of the following additives: intelligent temperature-regulating masterbatch, anti-aging additive, color masterbatch, temperature-changing masterbatch, UV masterbatch or flame retardant; According to a set material ratio model, the raw materials are mixed evenly to obtain an anti-aging ratio raw material exceeding a preset threshold; According to the shape and size of the simulated plant, the design data is extracted and a design mold is generated through a system integrating an intelligent design engine; the mold includes a cavity; The raw materials are heated in a heating cylinder of an injection molding machine until they are molten to obtain molten plastic; clamping the molds securely together; injecting the molten plastic into the cavity of the mold under a predetermined pressure; maintaining a predetermined pressure in the cavity for a predetermined time; Cooling and solidifying the material in the mold to form the shape of the mold; The mold is opened to obtain a formed simulated plant.

2. The injection molding method according to claim 1, characterized in that: The preparation of the intelligent temperature-regulating masterbatch comprises: Phase change material and shell material monomer aqueous solution are added to an organic solvent containing a surfactant to form an inverse emulsion. After the reverse phase emulsion is heated for reaction, phase change microcapsules with hydrophobic surface are obtained by separation.

3. The injection molding method according to claim 1, characterized in that: The steps of constructing the material ratio model include: Collect historical mix data and material performance data; According to the deep learning algorithm, the historical mixing data and the material performance data are used to perform performance learning training on the material proportioning model to obtain the material proportioning model; The trained material ratio model is used to simulate different mixing ratios to obtain an anti-aging raw material ratio that exceeds a preset threshold.

4. The injection molding method according to claim 1, characterized in that: The ratio of the anti-aging raw materials exceeding the preset threshold includes: polyethylene: 35-75 parts, temperature-change masterbatch: 20-50 parts, color masterbatch: 1-3 parts, UV masterbatch: 1-3 parts, flame retardant: 1-5 parts; wherein, The temperature-changing masterbatch includes temperature-sensitive microcapsules, preservatives, and dispersants; The UV masterbatch comprises a light stabilizer and an ultraviolet light absorber.

5. The injection molding method according to claim 1, characterized in that: The system integrating the intelligent design engine comprises: Collect historical mold design data; Through historical mold design data, using machine learning algorithms, identify and predict key factors that affect mold design performance; According to the key factors, the design data is automatically extracted and a preliminary design scheme is generated; By using the finite element analysis method, the performance of the mold under actual working conditions is simulated, problems that will arise are predicted and adjustments are made to the preliminary design scheme.

6. The injection molding method according to claim 5, characterized in that: The method uses historical mold design data and machine learning algorithms to identify and predict key factors that affect mold design performance, including: Using a feature selection method, key features that affect mold performance are screened out from the historical mold design data; Train a deep learning model to predict mold performance under different operating conditions.

7. The injection molding method according to claim 5, characterized in that: The finite element analysis method is used to simulate the performance of the mold under actual working conditions, predict possible problems and adjust the preliminary design scheme, including: Import the geometric model of the mold into the finite element analysis system; According to the actual working environment of the mold, set the displacement and pressure boundary parameters to simulate the real injection molding environment; Meshing the entire mold to divide the complex geometry into a limited number of small cells for numerical calculations; The overall deformation and stress distribution of the mold are calculated through finite element analysis, and the structural strength of the mold under working conditions is checked.

8. The injection molding method according to claim 1, characterized in that: The proportioned materials are heated in a heating cylinder of an injection molding machine to a molten state, wherein the heating temperature is controlled at 190°C-260°C.

9. The injection molding method according to claim 1, characterized in that: The molten plastic is injected into the cavity of the mold under a predetermined pressure, wherein the predetermined pressure is 70-120 bar.

10. The injection molding method according to claim 1, characterized in that: The factors affecting the predetermined pressure at the preset time include one or more of the following: plastic material, mold design, product shape and size, environmental conditions, injection molding machine parameters, field efficiency, and quality standards.

Images