Plastic part production system driven by advanced technology

Abstract

The present invention relates to the field of advanced filling control technology, specifically a plastic part production system driven by advanced processes. The plastic part production system driven by advanced processes includes a real-time melt property analysis module, an ultrasonic parameter setting module, a microstructure adjustment strategy module, a flow path optimization module, a quality inspection module, and a performance adjustment implementation module. In the present invention, the system adopts an integrated data processing and dynamic path optimization strategy, significantly improving the accuracy and efficiency of plastic part production. It can refine the injection channel design according to the melt properties and ultrasonic parameters to ensure that the material fills the mold along the optimal path, reducing material waste and significantly lowering the defect rate during the production process. It also improves the automation level of the production line, significantly improving the dimensional accuracy and surface quality of plastic parts. At the same time, it reduces energy consumption and production costs, bringing a new management and operation mode to plastic part production.

Description

Technical Field

[0001] The present invention relates to the field of advanced filling control technology, and particularly to a plastic part production system driven by advanced processes. Background Art

[0002] Advanced filling control technology is mainly applied in the production process of plastic products, especially in the injection molding stage. The core lies in achieving precise control over the process of filling a mold with plastic material to improve the quality and production efficiency of products. In injection molding, uniform filling of the material is crucial for manufacturing high-quality plastic parts with precise dimensions and consistent performance. By using advanced sensors, real-time monitoring and feedback mechanisms, and intelligent algorithms to optimize the filling process, it is ensured that the material fills the mold in the best way, thereby significantly improving the overall quality of the product and the efficiency of the production line.

[0003] Among them, a plastic part production system driven by advanced processes is a system integrating a variety of innovative technologies and methods, aiming to comprehensively improve the performance of the plastic injection molding process. The purpose is to achieve the effects of improving production efficiency, reducing costs, and enhancing product quality by optimizing each link in the production process, including material preparation, mold filling, cooling, and forming, etc. Considering the variability and complexity in the manufacturing process, the system uses advanced control technology, automation, and data analysis to achieve fine management of the production process.

[0004] Traditional systems lack the ability of real-time monitoring and fine control of the dynamic characteristics of melt flow, and it is difficult to make immediate adjustments during the production process, resulting in limited production efficiency and plastic part quality. The lack of precise flow path optimization and real-time data analysis mechanisms leads to inconsistent plastic part sizes, poor surface quality, and unstable physical properties, increasing the costs of post-processing and correction. In addition, the low efficiency of resource utilization in the production process increases additional energy consumption and material costs, affecting the economic benefits and environmental friendliness of enterprises, and there are obvious limitations in meeting the requirements of modern high-efficiency and high-quality production. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose a plastic part production system driven by advanced processes.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: The plastic part production system driven by advanced processes includes:

[0007] A melt property real-time analysis module analyzes the dynamic characteristics of the melt, including flow rate, viscosity, and temperature, combines with fluid dynamics for simulation, preliminarily adjusts the geometric shape of the injection channel, and generates comprehensive melt property data;

[0008] The ultrasonic parameter setting module performs acoustic simulation based on the comprehensive melt property data, reveals the optimal ultrasonic frequency and power, optimizes the melt fluidity, and generates ultrasonic excitation parameters;

[0009] The microstructure adjustment strategy module analyzes the melt microstructure using optical and electron microscopy techniques based on the comprehensive melt property data, predicts the orientation and distribution of polymer chains, and generates a microstructure adjustment plan;

[0010] The flow path optimization module applies the particle swarm optimization algorithm to dynamically adjust the geometry of the injection channel based on the comprehensive melt property data, ultrasonic excitation parameters, and microstructure adjustment plan, optimizes the melt filling path, reduces the flow resistance, and generates the optimal flow path design result;

[0011] The quality inspection module performs injection molding based on the optimal flow path design result, comprehensively evaluates the dimensional accuracy, surface quality, and physical properties of the plastic part, analyzes the product quality, and generates a quality inspection record;

[0012] The performance adjustment implementation module finally adjusts the physical and mechanical properties of the plastic part based on the quality inspection record, including adjusting the temperature and pressure to match the design requirements, and generates the performance adjustment implementation result.

[0013] As a further aspect of the present invention, the comprehensive melt property data includes real-time flow rate data of the melt, temperature distribution of the melt, and viscosity change of the melt. The ultrasonic excitation parameters are specifically the operating frequency of the ultrasonic generator, the power output of the ultrasonic wave, and the duration of the ultrasonic action. The microstructure adjustment plan includes optimization measures for polymer chain orientation, adjustment strategies for molecular spacing, and morphological characteristics of the target microstructure. The optimal flow path design result includes the actual value of the channel width adjustment, the optimized value of the injection channel length, and the new shape of the channel curvature after adjustment. The quality inspection record includes the measurement results of the dimensional accuracy of the plastic part, the surface finish rating, and the performance indicators obtained from physical property tests. The performance adjustment implementation result is specifically the material flow performance after temperature adjustment, the impact of pressure adjustment on hardness, and the improvement of material heat resistance.

[0014] As a further aspect of the present invention, the real-time melt property analysis module includes a flow rate analysis sub-module, a viscosity analysis sub-module, and a temperature analysis sub-module;

[0015] The flow rate analysis sub-module measures and analyzes the flow rate of the melt during the injection process based on the real-time monitoring of the dynamic melt properties, and generates a flow rate analysis result;

[0016] The viscosity analysis sub-module measures the viscosity of the melt based on the flow rate analysis result, and combines the effects of temperature and pressure on viscosity to generate viscosity adjustment data;

[0017] Based on the viscosity adjustment data, the temperature analysis sub-module monitors the melt temperature in real time and formulates adjustment strategies. It uses hydrodynamic simulation to preliminarily adjust the geometry of the injection channel, optimize the temperature uniformity of the melt during injection, and generate comprehensive melt characteristic data.

[0018] As a further solution of the present invention, the ultrasonic parameter setting module includes an acoustic data analysis sub-module, a frequency optimization sub-module, and a power setting sub-module;

[0019] Based on the comprehensive melt characteristic data, the acoustic data analysis sub-module conducts acoustic simulation, analyzes the response of melt fluidity to different ultrasonic frequencies and powers, and generates an acoustic response analysis result;

[0020] Based on the acoustic response analysis result, the frequency optimization sub-module conducts optimization analysis to reveal the ultrasonic frequency that can maximize the improvement of melt fluidity and generates an optimal set frequency;

[0021] According to the optimal set frequency, the power setting sub-module adjusts the power output of the ultrasonic generator to ensure that the melt fluidity is optimized at the optimal frequency and generates ultrasonic excitation parameters.

[0022] As a further solution of the present invention, the microstructure adjustment strategy module includes a microstructure analysis sub-module, a polymer chain prediction sub-module, and an adjustment strategy formulation sub-module;

[0023] Based on the comprehensive melt characteristic data, the microstructure analysis sub-module uses optical and electron microscopy techniques to analyze the microstructure of the melt, including the arrangement and density of molecular chains, and generates basic microstructure data;

[0024] Based on the basic microstructure data, the polymer chain prediction sub-module uses statistical analysis techniques to predict the potential orientation and distribution of polymer chains in the melt and generates a polymer chain distribution prediction result;

[0025] The statistical analysis technique uses the formula:

[0026]

[0027] Calculate the free energy change of the polymer chain distribution to generate a polymer chain distribution prediction result, where ΔF′ is the free energy change, R is the gas constant, T is the absolute temperature, φ p is the volume fraction of the polymer, φ s is the volume fraction of the solvent, and r′ is the correction ratio parameter. is the interaction parameter dependent on the specific interaction strength between temperature, polymer and solvent, λ is the parameter of the non-linear effect of intermolecular interaction, and ò is the strength parameter of the specific interaction between polymer and solvent.

[0028] The adjustment strategy formulation sub-module formulates a targeted adjustment strategy based on the prediction result of the polymer chain distribution, optimizes the orientation and distribution of the polymer chains, and generates a microstructure adjustment plan.

[0029] As a further solution of the present invention, the flow path optimization module includes a data integration sub-module, a path simulation sub-module, and a shape adjustment sub-module;

[0030] The data integration sub-module collects comprehensive melt property data, ultrasonic excitation parameters and microstructure adjustment plans, unifies and summarizes the data, and generates an integrated data result;

[0031] The path simulation sub-module performs iterative simulation using the particle swarm optimization algorithm based on the integrated data result, reveals the injection channel shape that can reduce flow resistance and optimize the melt filling path, and generates a simulated optimization path result;

[0032] The particle swarm optimization algorithm, according to the formula:

[0033] v id (t + 1) = w·v id (t) + c 1 ·rand 1 ()·(p id - x id (t))·D f ·T m

[0034] + c 2 ·rand 2 ()·(p gd - x id (t))·P c ·S v

[0035] Calculates the velocity and position update of the particles to generate an optimized injection channel shape value, where v id (t + 1) is the new velocity value of particle i in dimension d, w is the inertia weight, v id (t) is the current velocity value of particle i in dimension d, c 1 and c 2 are learning factors, rand 1 (), rand 2 () are random numbers in the interval [0, 1], p id is the historical optimal position of particle i, x id(t) is the current position of particle i in dimension d, and p gd is the global optimal position, and D f is the flow resistance coefficient, and T m is the melt temperature, and P c is the pressure control factor, and S v , is the speed adjustment variable;

[0036] The shape adjustment sub-module dynamically adjusts the geometry of the injection channel based on the simulation optimization path result, reveals the optimal melt flow path, and generates the optimal flow path design result.

[0037] As a further solution of the present invention, the quality inspection module includes a dimensional accuracy inspection sub-module, a surface quality evaluation sub-module, and a physical property test sub-module;

[0038] The dimensional accuracy inspection sub-module performs product injection molding based on the optimal flow path design result, collects the actual dimensional data of the plastic part after injection molding is completed, compares with the design dimensions, including length, width, and height, identifies the dimensional deviation, and obtains the dimensional parameter data;

[0039] The surface quality evaluation sub-module uses the dimensional parameter data to detect the surface finish and defects of the plastic part by using an optical microscope and a surface roughness measuring instrument, and generates surface inspection data;

[0040] The performance test sub-module performs tensile, compression, and impact tests on the plastic part according to the surface inspection data, evaluates its strength, toughness, and hardness, and generates a quality inspection record.

[0041] As a further solution of the present invention, the performance adjustment implementation module includes a temperature adjustment sub-module, a pressure adjustment sub-module, and a performance matching sub-module;

[0042] The temperature adjustment sub-module analyzes the physical and mechanical property deviations indicated in the quality inspection record, adjusts the temperature setting in the injection molding process, optimizes the molding conditions of the plastic part, and obtains the adjusted temperature parameters;

[0043] The pressure adjustment sub-module uses the adjusted temperature parameters to adjust the pressure setting of the injection molding machine, optimizes the uniformity of the internal structure of the plastic part, and obtains the adjusted pressure parameters;

[0044] The performance matching sub-module continuously monitors the injection molding process according to the adjusted pressure parameters, analyzes the quality of the plastic part and performs final performance adjustment to match the design requirements, and generates the performance adjustment implementation result.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In the present invention, by adopting an integrated data processing and dynamic path optimization strategy, the accuracy and efficiency of plastic part production are significantly improved. It can refine the injection channel design according to the melt characteristics and ultrasonic parameters, ensure that the material fills the mold along the optimal path, reduce material waste, and significantly reduce the defect rate during the production process. It also improves the automation level of the production line, significantly improves the dimensional accuracy and surface quality of plastic parts, while reducing energy consumption and production costs, bringing a new management and operation mode for plastic part production. Description of the Drawings

[0047] Figure 1 It is the system flowchart of the present invention;

[0048] Figure 2 It is the schematic diagram of the system framework of the present invention;

[0049] Figure 3 It is the flowchart of the real-time melt characteristics analysis module of the present invention;

[0050] Figure 4 It is the flowchart of the ultrasonic parameter setting module of the present invention;

[0051] Figure 5 It is the flowchart of the microstructure adjustment strategy module of the present invention;

[0052] Figure 6 It is the flowchart of the flow path optimization module of the present invention;

[0053] Figure 7 It is the flowchart of the quality inspection module of the present invention;

[0054] Figure 8 It is the flowchart of the performance adjustment implementation module of the present invention. Detailed Embodiments

[0055] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. In addition, in the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0057] Example 1

[0058] Please refer to Figure 1 and Figure 2 , the plastic part production system driven by advanced processes includes a real-time melt property analysis module, an ultrasonic parameter setting module, a microstructure adjustment strategy module, a flow path optimization module, a quality inspection module, and a performance adjustment implementation module.

[0059] The real-time melt property analysis module analyzes the dynamic properties of the melt, including flow rate, viscosity, and temperature, simulates using fluid dynamics, preliminarily adjusts the geometry of the injection channel, and generates comprehensive melt property data.

[0060] The ultrasonic parameter setting module performs acoustic simulation based on the comprehensive melt property data, reveals the optimal ultrasonic frequency and power, optimizes the melt fluidity, and generates ultrasonic excitation parameters.

[0061] The microstructure adjustment strategy module analyzes the microstructure of the melt using optical and electron microscopy techniques based on the comprehensive melt property data, predicts the orientation and distribution of polymer chains, and generates a microstructure adjustment plan.

[0062] The flow path optimization module dynamically adjusts the geometry of the injection channel using the particle swarm optimization algorithm based on the comprehensive melt property data, ultrasonic excitation parameters, and microstructure adjustment plan, optimizes the melt filling path, reduces flow resistance, and generates the optimal flow path design result.

[0063] The quality inspection module performs injection molding based on the optimal flow path design result, comprehensively evaluates the dimensional accuracy, surface quality, and physical properties of the plastic part, analyzes the product quality, and generates a quality inspection record.

[0064] The performance adjustment implementation module finally adjusts the physical and mechanical properties of the plastic part based on the quality inspection record, including adjusting temperature and pressure to match the design requirements, and generates a performance adjustment implementation result.

[0065] The comprehensive melt property data includes the real-time flow rate data of the melt, the temperature distribution of the melt, and the viscosity change of the melt. The ultrasonic excitation parameters are specifically the operating frequency of the ultrasonic generator, the power output of the ultrasonic wave, and the duration of the ultrasonic action. The microstructure adjustment plan includes the optimization measures for polymer chain orientation, the adjustment strategy for molecular spacing, and the morphological characteristics of the target microstructure. The optimal flow path design result includes the actual value of the channel width adjustment, the optimized value of the injection channel length, and the new shape after the channel curvature adjustment. The quality inspection record includes the measurement results of the dimensional accuracy of the plastic part, the surface finish rating, and the performance indicators obtained from the physical property tests. The implementation result of the performance adjustment is specifically the material flow performance after the temperature adjustment, the influence of the pressure adjustment on the hardness, and the improvement of the material heat resistance.

[0066] In the real-time melt property analysis module, by collecting the real-time data during the melt flow, including the flow rate, viscosity, and temperature, and using the principles of fluid dynamics for simulation analysis. The geometric shape of the injection channel is preliminarily adjusted and designed to ensure that the melt can fill the mold more evenly, improving the quality and production efficiency of the plastic part. The finally generated comprehensive melt property data provides accurate input information for the subsequent modules, making it possible to optimize and precisely control the entire system.

[0067] In the ultrasonic parameter setting module, acoustic simulation is performed based on the comprehensive melt property data to reveal the optimal ultrasonic frequency and power settings under specific melt properties. This process not only relies on the real-time monitoring data of the melt fluidity but also combines acoustic principles to determine the optimal ultrasonic excitation parameters, thereby optimizing the melt fluidity and reducing the possible defects during the plastic part production process.

[0068] In the microstructure adjustment strategy module, by analyzing the comprehensive melt property data and using optical and electron microscopy techniques to detailedly observe the microstructure of the melt in the mold. Through this method, the orientation and distribution of polymer chains can be predicted, and then a targeted microstructure adjustment plan can be formulated. Effectively improving the internal quality of the plastic part, making the final product have more excellent physical and mechanical properties.

[0069] In the flow path optimization module, based on the comprehensive melt property data, ultrasonic excitation parameters, and microstructure adjustment plan, the particle swarm optimization algorithm is used to precisely and dynamically adjust the geometric shape of the injection channel. Through this algorithm, the injection channel shape that can reduce the flow resistance and optimize the melt filling path can be effectively revealed. The optimization strategy directly affects the melt filling efficiency and the quality of the plastic part, and the generated optimal flow path design result provides a reliable basis for producing high-quality plastic parts.

[0070] In the quality inspection module, after injection molding based on the optimal flow path design results, a comprehensive evaluation of the dimensional accuracy, surface quality, and physical properties of the plastic parts is carried out. The evaluation process covers from precise measurement of dimensions to detailed inspection of surface defects, and then to strict testing of physical properties, ensuring that each plastic part can meet or exceed the design requirements. The generated quality inspection records not only provide feedback for the production process but also serve as a basis for the implementation of performance adjustment.

[0071] In the performance adjustment implementation module, based on the quality inspection records, the final performance adjustment of the plastic parts is carried out. This includes adjusting the temperature and pressure settings during the injection molding process to ensure that the physical and mechanical properties of each plastic part can meet the design requirements. Through this series of meticulous adjustments, the performance adjustment implementation results ensure that the plastic parts not only have no defects in appearance but also reach the optimal state in terms of performance.

[0072] Please refer to Figure 2 and Figure 3 , the melt property real-time analysis module includes a flow rate analysis sub-module, a viscosity analysis sub-module, and a temperature analysis sub-module;

[0073] Based on the real-time monitoring of the dynamic characteristics of the melt, the flow rate analysis sub-module measures and analyzes the flow rate of the melt during the injection process and generates flow rate analysis results;

[0074] In the flow rate analysis sub-module, based on the real-time monitoring of the dynamic characteristics of the melt, the multiple regression analysis method is adopted, and the data is processed using the SciPy library in Python to refine the implementation of the flow rate analysis sub-module. First, the pressure data of the melt during the injection process is collected through a pressure sensor, and the melt temperature data at the corresponding time points is collected using a temperature sensor. Then, taking the pressure data and temperature data as independent variables and the flow rate as the dependent variable, the linregress function in the SciPy library is used, specifying the parameter x as the combination of pressure and temperature data, and y as the corresponding flow rate data, to perform linear regression analysis. The linregress function automatically calculates the relationship coefficients between the flow rate and pressure, temperature, and generates the flow rate analysis results.

[0075] Based on the flow rate analysis results, the viscosity analysis sub-module measures the viscosity of the melt, combines the influence of temperature and pressure on viscosity, and generates viscosity adjustment data;

[0076] In the viscosity analysis sub-module, based on the flow rate analysis results, the viscosity is measured using the Arrhenius equation, and the Arrhenius equation is numerically solved using the NumPy library. To refine the implementation of the viscosity analysis sub-module, first, the melt flow rate data is obtained according to the flow rate analysis results. Then, using the temperature and pressure data of the melt, through the exp function in the NumPy library, the activation energy Ea parameter in the Arrhenius equation is set to a specific constant value for the melt, and the temperature T parameter is set to the melt temperature monitored in real time. The exp function is used to solve the Arrhenius equation to calculate the melt viscosity under the current temperature and pressure conditions, and viscosity adjustment data is generated.

[0077] Based on the viscosity adjustment data, the temperature analysis sub-module conducts real-time monitoring of the melt temperature and formulates adjustment strategies. Using fluid dynamics for simulation, the geometric shape of the injection channel is initially adjusted to optimize the temperature uniformity of the melt during injection, and comprehensive melt characteristic data is generated.

[0078] In the temperature analysis sub-module, based on the viscosity adjustment data, the computational fluid dynamics (CFD) simulation method is used, and the ANSYS Fluent software is used to conduct real-time monitoring of the melt temperature and formulate adjustment strategies. To refine the implementation of the temperature analysis sub-module, first, the viscosity adjustment data is input into the ANSYS Fluent software, and the boundary conditions for the simulation are set, including the inlet velocity of the injection channel being the value calculated according to the viscosity adjustment data and the temperature being the melt temperature monitored in real time. Then, the k-epsilon turbulence model in ANSYS Fluent is used to conduct simulation calculations of fluid flow and heat transfer. Through the simulation calculations, detailed information on the melt temperature distribution during injection is obtained. According to the temperature distribution results, the geometric shape of the injection channel is initially adjusted to make the melt temperature distribution more uniform during injection, and comprehensive melt characteristic data is generated.

[0079] Please refer to Figure 2 and Figure 4 , the ultrasonic parameter setting module includes an acoustic data analysis sub-module, a frequency optimization sub-module, and a power setting sub-module.

[0080] Based on the comprehensive melt characteristic data, the acoustic data analysis sub-module conducts acoustic simulations to analyze the response of melt fluidity to different ultrasonic frequencies and powers, and generates acoustic response analysis results.

[0081] In the acoustic data analysis sub-module, based on the comprehensive melt property data, the finite element analysis (FEA) method is used, and the COMSOL Multiphysics software is utilized for acoustic simulation to analyze the response of melt fluidity to different ultrasonic frequencies and powers. First, the comprehensive melt property data, including parameters such as the density, viscosity, and temperature of the melt, is imported into COMSOL Multiphysics. Then, the physical field of sound wave propagation is set as the pressure acoustic field in the acoustic module. The source frequency range is defined from 20 kHz to 100 kHz, and the power range is from 10 W to 100 W. Using the "parameter sweep" function in COMSOL, the responses of the melt at different frequencies and powers are scanned. Through the numerical simulation of the interaction between sound wave propagation and melt flow, the changes in melt fluidity at each frequency and power are calculated, and the acoustic response analysis results are generated.

[0082] Based on the acoustic response analysis results, the frequency optimization sub-module conducts optimization analysis to reveal the ultrasonic frequency that can maximize the improvement of melt fluidity and generates the optimal set frequency.

[0083] In the frequency optimization sub-module, based on the acoustic response analysis results, the genetic algorithm is adopted, and the Global Optimization Toolbox of MATLAB is used for optimization analysis to reveal the ultrasonic frequency that can maximize the improvement of melt fluidity. First, the melt fluidity improvement index in the acoustic response analysis results is used as the input of the fitness function. The population size of the genetic algorithm is set to 100, the crossover rate is 0.8, and the mutation rate is 0.1. Using the ga function in MATLAB, the parameters of the genetic algorithm, including the population size, crossover rate, and mutation rate, are specified. The genetic algorithm is executed. Through multiple generations of iteration, the ultrasonic frequency that maximizes the melt fluidity improvement index is found, and the optimal set frequency is generated.

[0084] According to the optimal set frequency, the power setting sub-module adjusts the power output of the ultrasonic generator to ensure the optimization of melt fluidity at the optimal frequency and generates the ultrasonic excitation parameters.

[0085] In the power setting sub-module, according to the optimal set frequency, the PID control strategy is adopted, and the LabVIEW software is used to adjust the power output of the ultrasonic generator to ensure the optimization of melt fluidity at the optimal frequency. First, the optimal set frequency and the expected improvement effect of melt fluidity are used as the inputs of the PID controller. The proportional (P), integral (I), and derivative (D) parameters of the PID controller are set to the values determined in advance through experiments. Using the PID control module in LabVIEW, the PID parameters are set, and the PID control is executed. Through the real-time monitoring of the melt fluidity feedback, the output power of the ultrasonic generator is adjusted until the melt fluidity reaches the expected improvement effect, and the ultrasonic excitation parameters are generated.

[0086] Please refer to Figure 2 and Figure 5 , the microstructure adjustment strategy module includes a microstructure analysis sub-module, a polymer chain prediction sub-module, and an adjustment strategy formulation sub-module;

[0087] Based on the comprehensive melt property data, the microstructure analysis sub-module analyzes the microstructure of the melt, including the arrangement and density of molecular chains, using optical and electron microscopy techniques to generate basic microstructure data;

[0088] In the microstructure analysis sub-module, based on the comprehensive melt property data, transmission electron microscopy (TEM) and scanning electron microscopy (SEM) techniques are used to analyze the microstructure of the melt. First, prepare a melt sample and perform ultra-thin sectioning for TEM analysis. At the same time, perform appropriate sample gold plating for SEM analysis. Set the acceleration voltage of TEM to 80 kV and analyze the arrangement of molecular chains through high-resolution imaging. Set the acceleration voltage of SEM to 5 kV and analyze the microstructure and density distribution on the surface and inside of the melt through secondary electron and backscattered electron imaging modes. Through these steps, collect image data of the melt microstructure and perform qualitative and quantitative analysis to generate basic microstructure data.

[0089] Based on the basic microstructure data, the polymer chain prediction sub-module uses statistical analysis techniques to predict the potential orientation and distribution of polymer chains in the melt, generating a polymer chain distribution prediction result;

[0090] The statistical analysis technique uses the formula:

[0091]

[0092] Calculate the free energy change of the polymer chain distribution to generate a polymer chain distribution prediction result, where αF′ is the free energy change considering more factors after improvement, R is the gas constant, T is the absolute temperature, φ p is the volume fraction of the polymer, φ s is the volume fraction of the solvent, r′ is the correction ratio parameter considering the rigidity of the polymer chain, is the interaction parameter considering the dependence of temperature and the specific interaction strength between the polymer and the solvent, λ is the parameter of the non-linear effect of intermolecular interaction, is the strength parameter of the specific interaction between the polymer and the solvent.

[0093] The execution process is as follows:

[0094] Parameter estimation and collection, collect basic data such as the volume fractions of the polymer and the solvent, polymer molecular weight, temperature, etc., and estimate the values of the improvement parameters (r′, λ);

[0095] Improve the formula application, substitute all parameter values into the improved formula, and calculate the free energy change ΔF′ of the polymer solution;

[0096] Result analysis, by comparing the free energy changes under different conditions, predict the potential orientation and distribution of polymer chains in the melt, and generate the prediction results of polymer chain distribution.

[0097] Through this method, the potential orientation and distribution of polymer chains in the melt can be predicted more accurately, providing theoretical support for the design and processing of polymer materials. The introduced new parameters r′, and λ and their calculation methods make the model more in line with the actual situation, improving the prediction accuracy and application universality.

[0098] The adjustment strategy formulation sub-module formulates targeted adjustment strategies based on the polymer chain distribution prediction results, optimizes the orientation and distribution of polymer chains, and generates a microstructure adjustment plan;

[0099] In the adjustment strategy formulation sub-module, based on the polymer chain distribution prediction results, an optimization algorithm is adopted, specifically the particle swarm optimization (PSO) algorithm. Use MATLAB software to perform optimization analysis on the orientation and distribution of polymer chains and formulate a microstructure adjustment plan. First, use the polymer chain distribution prediction results as the input data of the PSO algorithm, including the potential orientation and distribution of polymer chains. Then, set the parameters of the PSO algorithm, including the number of particles as 50, the number of iterations as 100, and the learning factor in the velocity and position update formulas as 2.0. Use the particleswarm function in MATLAB to execute the PSO algorithm. By simulating the search behavior of particles in the solution space, find the conditions that can make the orientation and distribution of polymer chains reach the optimal state, and accordingly formulate the adjustment strategy for the orientation and distribution of polymer chains and generate a microstructure adjustment plan.

[0100] Please refer to Figure 2 and Figure 6 , the flow path optimization module includes a data integration sub-module, a path simulation sub-module, and a shape adjustment sub-module;

[0101] The data integration sub-module collects comprehensive melt property data, ultrasonic excitation parameters, and microstructure adjustment plans, unifies and summarizes the data, and generates the integrated data results;

[0102] In the data integration sub-module, comprehensive data on melt properties, ultrasonic excitation parameters, and microstructure adjustment schemes are collected. Using data fusion technology and the Pandas library in Python for data unification and summarization. First, import the comprehensive data on melt properties, including parameters such as temperature, flow rate, and viscosity. Import the ultrasonic excitation parameters, including ultrasonic frequency and power. Import the microstructure adjustment schemes, including optimization strategies for the orientation and distribution of polymer chains. Then, use the DataFrame object in the Pandas library to integrate these three parts of data into a data framework, and use the merge and concat functions to perform data unification and summarization processing to ensure data consistency and integrity. Through these steps, the integrated data results are generated.

[0103] Based on the integrated data results, the path simulation sub-module applies the particle swarm optimization algorithm for iterative simulation to reveal the injection channel shape that can reduce flow resistance and optimize the melt filling path, and generates the simulated optimization path results;

[0104] The particle swarm optimization algorithm, according to the formula:

[0105] v id (t + 1) = w·v id (t) + c 1 ·rand 1 ()·(p id -x id (t))·D f ·T m

[0106] +c 2 ·rand 2 ()·(p gd -x id (t))·P c ·S v

[0107] Calculate the velocity and position update of the particles to generate the optimized injection channel shape values. Among them, v id (t + 1) is the new velocity value of particle i in dimension d, w is the inertia weight, which controls the maintenance of the particle velocity and helps the algorithm balance between global search and local search. v id (t) is the current velocity value of particle i in dimension d, c 1 and c 2 are the learning factors, representing the influence weights of the individual experience and group experience of the particles respectively. rand 1 (), rand 2 () are random numbers within the interval [0, 1], introducing randomness to avoid the algorithm prematurely converging to the local optimal solution, p idis the historical best position of particle i, i.e., the individual best solution, x id (t) is the current position of particle i in dimension d, p gd is the global best position, i.e., the best solution found by all particles in the population, D f is the flow resistance coefficient, reflecting the resistance conditions during melt flow, T m is the melt temperature, affecting the fluidity of the melt, P c is the pressure control factor, considering the influence of pressure during the injection process, S v , is the velocity adjustment variable, providing additional flexibility for the algorithm to adjust the particle velocity.

[0108] The execution process is as follows:

[0109] Initialize the particle swarm, assign a random initial position and velocity to each particle, and set the initial estimates of the flow resistance coefficient D f , melt temperature T m , pressure control factor P c and velocity adjustment variable S v according to specific simulation requirements;

[0110] Start the iterative loop. For each particle, calculate its new velocity using the improved velocity update formula, update the position information of each particle, evaluate the fitness (i.e., the quality of the solution) of each particle at the new position based on its new velocity value, and update the individual best position p id and the global best position p gd ;

[0111] Check the iteration condition to determine whether the iteration stop condition (reaching the maximum number of iterations or the fitness reaching the predetermined threshold) is satisfied. If not, continue the iteration; if satisfied, end the iteration process;

[0112] Output the optimal solution. After the iteration ends, output the global best position p gd , as the optimal solution to the problem.

[0113] By introducing creative parameters, the complexity and accuracy of the simulation are increased, meeting the optimization requirements under different injection molding conditions, enabling the algorithm to more accurately simulate and optimize the shape of the injection channel, thereby reducing the flow resistance and optimizing the melt filling path.

[0114] The shape adjustment sub-module dynamically adjusts the geometric shape of the injection channel based on the simulation optimization path results, reveals the optimal melt flow path, and generates the optimal flow path design results;

[0115] In the shape adjustment sub-module, based on the results of the simulation optimization path, dynamic adjustment technology is adopted, and 3D printing technology is used to adjust the geometric shape of the injection channel, revealing the optimal melt flow path. First, the results of the simulation optimization path are imported into 3D modeling software, such as SolidWorks, and the geometric shape of the injection channel is adjusted according to the optimization results, including parameters such as the width, bending angle, and length of the channel. Then, using 3D printing technology, a new injection channel mold is printed according to the adjusted model parameters. Through these steps, the geometric shape of the injection channel is dynamically adjusted, the optimal melt flow path is revealed, and the optimal flow path design result is generated.

[0116] Please refer to Figure 2 and Figure 7 , the quality inspection module includes a dimensional accuracy inspection sub-module, a surface quality evaluation sub-module, and a physical property test sub-module;

[0117] Based on the optimal flow path design result, the dimensional accuracy inspection sub-module performs product injection molding, collects the actual dimension data of the plastic part after injection molding is completed, compares the design dimensions, including length, width, and height, identifies the dimensional deviation, and obtains the dimensional parameter data;

[0118] In the dimensional accuracy inspection sub-module, based on the optimal flow path design result, product injection molding is carried out, and a digital caliper and a laser rangefinder are used to collect the actual dimension data of the plastic part after injection molding is completed. First, the digital caliper is used to measure the length and width of the plastic part, and the accuracy of the digital caliper is set to 0.01 mm to ensure the accuracy of the measurement data. Then, the laser rangefinder is used to measure the height of the plastic part, and the measurement range of the laser rangefinder is set to 0.02 mm to 100 m. By comparing the actual dimension data with the design dimensions, data comparison and analysis are carried out using Excel software, and the deviation values of length, width, and height are calculated. Through these steps, the dimensional deviation is identified, and the dimensional parameter data is generated.

[0119] The surface quality evaluation sub-module uses the dimensional parameter data and uses an optical microscope and a surface roughness measuring instrument to detect the surface finish and defects of the plastic part, generating surface inspection data;

[0120] In the surface quality evaluation sub-module, using the dimensional parameter data, an optical microscope and a surface roughness measuring instrument are used to detect the surface finish and defects of the plastic part. First, the optical microscope is used to observe whether there are defects such as scratches, depressions, or bubbles on the surface of the plastic part, and the magnification range of the optical microscope is set to 10X to 100X. Then, the surface roughness measuring instrument is used to measure the surface roughness of the plastic part, and the probe travel length of the measuring instrument is set to 4 mm, and the probe speed is set to 1 mm / s. Through these steps, a comprehensive evaluation of the surface finish and defects of the plastic part is carried out, generating surface inspection data.

[0121] The performance test sub-module conducts tensile, compression, and impact tests on plastic parts based on the surface inspection data, evaluates their strength, toughness, and hardness, and generates quality inspection records;

[0122] In the physical performance test sub-module, based on the surface inspection data, tensile, compression, and impact tests are conducted on plastic parts to evaluate their strength, toughness, and hardness. First, a universal material testing machine is used for the tensile test. The tensile speed is set at 5 mm / min, and the fracture strength of the plastic part is measured. Then, a compression testing machine is used for the compression test. The compression speed is set at 2 mm / min, and the compression strength of the plastic part is measured. Then, an impact testing machine is used for the impact test. The impact energy is set at 2 J, and the impact toughness of the plastic part is measured. Through these steps, the physical performance of the plastic part is evaluated, and quality inspection records are generated.

[0123] Please refer to Figure 2 and Figure 8 , the performance adjustment implementation module includes a temperature adjustment sub-module, a pressure adjustment sub-module, and a performance matching sub-module;

[0124] The temperature adjustment sub-module analyzes the physical and mechanical performance deviations indicated in the quality inspection records, adjusts the temperature settings in the injection molding process, optimizes the plastic part forming conditions, and obtains the adjusted temperature parameters;

[0125] In the temperature adjustment sub-module, the physical and mechanical performance deviations indicated in the quality inspection records are analyzed, and the feedback control algorithm is used to adjust the temperature settings in the injection molding process. A PID controller is adopted, and the MATLAB software is used to adjust and optimize the temperature control parameters. First, the quality inspection record data, including indicators such as the strength, toughness, and hardness of the plastic part, is imported. Then, based on these physical and mechanical performance deviations, the pidTuner tool in MATLAB is used to adjust the proportional (P), integral (I), and derivative (D) parameters of the PID controller to optimize the temperature control of the plastic part forming conditions. Through iterative simulation, a set of optimal PID parameters is found, making the physical and mechanical performance of the plastic part close to the design requirements, and the adjusted temperature parameters are obtained.

[0126] The pressure adjustment sub-module uses the adjusted temperature parameters to adjust the pressure settings of the injection molding machine, optimizes the uniformity of the internal structure of the plastic part, and obtains the adjusted pressure parameters;

[0127] In the pressure adjustment sub-module, the adjusted temperature parameter is utilized to adjust the pressure setting of the injection molding machine by means of a numerical optimization method. The genetic algorithm is applied, and the optimization calculation of the pressure parameter is carried out using the Python language and the SciPy library. First, the adjusted temperature parameter and the physical property deviation in the quality inspection record are used as the input conditions of the genetic algorithm. Then, the population size of the genetic algorithm is set to 50, the number of iterations is set to 100, the crossover rate and the mutation rate are set to 0.8 and 0.1 respectively. The ga function in the SciPy library is used to execute the genetic algorithm according to the set parameters. Through the optimization process, the optimal pressure setting parameter is searched to optimize the uniformity of the internal structure of the plastic part and obtain the adjusted pressure parameter.

[0128] The performance matching sub-module continuously monitors the injection molding process based on the adjusted pressure parameter, analyzes the quality of the plastic part and makes the final performance adjustment to match the design requirements, and generates the implementation result of the performance adjustment.

[0129] In the performance matching sub-module, based on the adjusted pressure parameter, the injection molding process is continuously monitored. The real-time data analysis method is adopted, and the LabVIEW software is used for data acquisition and analysis. The quality of the plastic part is continuously monitored and the final performance adjustment is made. First, the adjusted pressure parameter is set into the injection molding machine, and the LabVIEW software is used for real-time data acquisition, including key parameters such as pressure, temperature and cooling time during the injection molding process. Then, the real-time acquired data is analyzed, compared with the design requirements and the previous quality inspection record. Through the data processing module in LabVIEW, it is judged whether further adjustment of the injection molding parameters is needed to ensure that the performance of the plastic part completely matches the design requirements. Through this series of operations, the implementation result of the performance adjustment is generated.

[0130] The above is only the preferred embodiment of the present invention, and it does not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. Advanced process driven plastic parts production system, characterized by: The advanced process-driven plastic parts production system includes: The real-time melt characteristics analysis module analyzes the dynamic characteristics of the melt, including flow rate, viscosity and temperature, combines fluid dynamics for simulation, preliminarily adjusts the geometry of the injection channel, and generates comprehensive melt characteristics data; The ultrasonic parameter setting module performs acoustic simulation based on the comprehensive data of melt characteristics, reveals the optimal ultrasonic frequency and power, optimizes melt fluidity, and generates ultrasonic excitation parameters; The microstructure adjustment strategy module uses optical and electron microscopy techniques to analyze the melt microstructure based on the melt property comprehensive data, predicts the orientation and distribution of polymer chains, and generates a microstructure adjustment plan; The flow path optimization module uses a particle swarm optimization algorithm based on the melt characteristic comprehensive data, ultrasonic excitation parameters and microstructure adjustment scheme to dynamically adjust the geometry of the injection channel, optimize the melt filling path, reduce flow resistance, and generate an optimal flow path design result; The quality inspection module performs injection molding based on the optimal flow path design result, comprehensively evaluates the dimensional accuracy, surface quality and physical properties of the plastic parts, analyzes the product quality, and generates quality inspection records; The performance adjustment implementation module makes final adjustments to the physical and mechanical properties of the plastic part based on the quality inspection records, including adjusting the temperature and pressure to match the design requirements and generate performance adjustment implementation results; The microstructure adjustment strategy module includes a microstructure analysis submodule, a polymer chain prediction submodule, and an adjustment strategy formulation submodule; The microstructure analysis submodule uses optical and electron microscopy techniques to analyze the microstructure of the melt, including the arrangement and density of molecular chains, based on the comprehensive data of melt characteristics, and generates basic microstructure data; The polymer chain prediction submodule predicts the potential orientation and distribution of polymer chains in the melt based on the microstructure basic data and uses statistical analysis technology to generate polymer chain distribution prediction results; The statistical analysis technique uses the formula: ； Calculate the free energy change of polymer chain distribution and generate polymer chain distribution prediction results, where is the free energy change, is the gas constant, is the absolute temperature, is the volume fraction of the polymer, is the volume fraction of the solvent, is the correction ratio parameter, is the interaction parameter for the temperature-dependent specific interaction strength between polymer and solvent, is the parameter of the nonlinear effect of intermolecular interaction, is the strength parameter of the specific interaction between polymer and solvent; The adjustment strategy formulation submodule formulates a targeted adjustment strategy based on the polymer chain distribution prediction results, optimizes the orientation and distribution of the polymer chain, and generates a microstructure adjustment plan; The flow path optimization module includes a data integration submodule, a path simulation submodule, and a shape adjustment submodule; The data integration submodule collects comprehensive melt property data, ultrasonic excitation parameters and microstructure adjustment schemes, unifies and summarizes the data, and generates integrated data results; The path simulation submodule uses a particle swarm optimization algorithm to perform cyclic iterative simulation based on the integrated data results, reveals the injection channel shape that can reduce flow resistance and optimize the melt filling path, and generates simulation optimization path results; The particle swarm optimization algorithm is based on the formula: ； Calculate the particle velocity and position update to generate the optimized injection channel shape value, where is the new velocity value of particle i in dimension d, is the inertia weight, is the current velocity value of particle i in dimension d, and is the learning factor, , is a random number in the interval [0,1], is the historical optimal position of particle i, is the current position of particle i in dimension d, is the global optimal position, is the flow resistance coefficient, is the melt temperature, is the pressure control factor, is the speed adjustment variable; The shape adjustment submodule dynamically adjusts the geometric shape of the injection channel based on the simulation optimization path results, reveals the optimal melt flow path, and generates the optimal flow path design results.

2. The advanced process driven plastic parts production system according to claim 1, characterized in that: The comprehensive melt characteristic data includes the real-time flow rate data of the melt, the temperature distribution of the melt and the viscosity change of the melt. The ultrasonic excitation parameters are specifically the operating frequency of the ultrasonic generator, the power output of the ultrasonic wave and the duration of the ultrasonic action. The microstructure adjustment plan includes the optimization measures of the polymer chain orientation, the adjustment strategy of the molecular spacing and the morphological characteristics of the target microstructure. The optimal flow path design result includes the actual value of the channel width adjustment, the optimized value of the injection channel length and the new shape after the channel curvature is adjusted. The quality inspection record includes the measurement results of the dimensional accuracy of the plastic parts, the surface finish rating and the performance indicators obtained from the physical property test. The performance adjustment implementation results are specifically the material flow properties after temperature adjustment, the effect of pressure adjustment on hardness and the improvement of material heat resistance.

3. The advanced process driven plastic parts production system according to claim 1, characterized in that: The melt characteristics real-time analysis module includes a flow rate analysis submodule, a viscosity analysis submodule, and a temperature analysis submodule; The flow rate analysis submodule measures and analyzes the flow rate of the melt during the injection process based on real-time monitoring of the dynamic characteristics of the melt, and generates flow rate analysis results; The viscosity analysis submodule measures the viscosity of the melt based on the flow rate analysis results, and generates viscosity adjustment data by combining the effects of temperature and pressure on viscosity; The temperature analysis submodule performs real-time monitoring of the melt temperature and formulates adjustment strategies based on the viscosity adjustment data, uses fluid dynamics simulation to preliminarily adjust the geometry of the injection channel, optimizes the temperature uniformity of the melt during the injection process, and generates comprehensive melt characteristic data.

4. The advanced process driven plastic parts production system according to claim 1, characterized in that: The ultrasonic parameter setting module includes an acoustic data analysis submodule, a frequency optimization submodule, and a power setting submodule; The acoustic data analysis submodule performs acoustic simulation based on the comprehensive data of melt characteristics, analyzes the response of melt fluidity to differential ultrasonic frequency and power, and generates acoustic response analysis results; The frequency optimization submodule performs optimization analysis based on the acoustic response analysis results, reveals the ultrasonic frequency that can maximize the improvement of melt fluidity, and generates the optimal setting frequency; The power setting submodule adjusts the power output of the ultrasonic generator according to the optimal setting frequency to ensure that the melt fluidity is optimized at the optimal frequency and generate ultrasonic excitation parameters.

5. The advanced process driven plastic parts production system according to claim 1, characterized in that: The quality inspection module includes a dimensional accuracy inspection submodule, a surface quality assessment submodule, and a physical performance test submodule; The dimensional accuracy detection submodule performs product injection molding based on the optimal flow path design result, collects actual dimensional data of the plastic part after injection molding, compares the designed dimensions, including length, width and height, identifies dimensional deviations, and obtains dimensional parameter data; The surface quality assessment submodule uses the dimensional parameter data, an optical microscope and a surface roughness measuring instrument to detect the surface finish and defects of the plastic part, and generates surface inspection data; The performance testing submodule performs tensile, compression and impact tests on plastic parts based on surface inspection data, evaluates their strength, toughness and hardness, and generates quality inspection records.

6. The advanced process driven plastic parts production system according to claim 1, characterized in that: The performance adjustment implementation module includes a temperature adjustment submodule, a pressure adjustment submodule, and a performance matching submodule; The temperature adjustment submodule analyzes the physical and mechanical property deviations indicated in the quality inspection records, adjusts the temperature settings of the injection molding process, optimizes the molding conditions of the plastic parts, and obtains the adjusted temperature parameters; The pressure adjustment submodule uses the adjusted temperature parameters to adjust the pressure setting of the injection molding machine, optimize the uniformity of the internal structure of the plastic part, and obtain the adjusted pressure parameters; The performance matching submodule continuously monitors the injection molding process according to the adjusted pressure parameters, analyzes the quality of the plastic parts, performs final performance adjustments, matches the design requirements, and generates performance adjustment implementation results.

Images