Injection molding quality prediction method and system for automotive plastic parts based on machine learning

Abstract

The present invention is applicable to the field of injection molding quality management, and provides a method and system for predicting the injection molding quality of automotive plastic parts based on machine learning. The system includes: a data acquisition and parameter collection module, an electrostatic accumulation modeling module, a virtual production process reproduction module, and a real-time electrostatic analysis and quality assessment module. The simulation capability of digital twin technology enables enterprises to test different production parameters and conditions in a virtual environment, evaluate their impact on static electricity accumulation and the quality of injection molded parts, and thus provide a basis for actual production. This flexible experimental method not only reduces the cost and time of physical testing, but also improves the efficiency of product design and process development. The combination of digital twin technology and the electrostatic accumulation model not only improves product quality and production efficiency, but also enhances the company's ability to control the production process.

Description

Technical Field

[0001] The present invention belongs to the field of injection molding quality management, and in particular relates to a method and system for predicting the injection molding quality of automobile plastic parts based on machine learning. Background Art

[0002] The field of injection molding quality management refers to a comprehensive system that ensures that the quality of the final product meets the design and customer requirements through a series of management and technical means during the injection molding production process. First of all, material management is the foundation of this field. It is crucial to select the right raw materials. The specifications, composition and physical properties of the raw materials must be strictly controlled to ensure their stable performance during the processing. Secondly, process control is also key. By optimizing the injection molding process parameters such as temperature, pressure, injection speed and cooling time, the molding accuracy can be improved and defects can be reduced.

[0003] Humidity and temperature changes in the injection molding production environment have a great impact on static electricity, but companies may fail to effectively monitor and adjust environmental conditions, resulting in instability in static electricity control. The presence of static electricity may cause defects on the surface of injection molded parts, such as scratches, stains or bubbles. These defects not only affect the appearance quality of the product, but may also affect its physical properties. The discharge phenomenon caused by static electricity may cause tiny depressions or uneven melting on the surface of the injection molded part, resulting in reduced strength and durability of the product. In addition, static electricity can cause material particles to aggregate, affecting the fluidity of the molten plastic, resulting in uneven filling, which in turn affects the dimensional accuracy and consistency of the product. Summary of the invention

[0004] The purpose of the present invention is to provide a method for predicting the injection molding quality of automotive plastic parts based on machine learning, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0005] The present invention is implemented by a method for predicting the injection molding quality of automobile plastic parts based on machine learning, the method comprising:

[0006] Acquire completed injection molding production data and collect production influencing parameters, including: environmental parameters, material parameters and production process parameters;

[0007] Establish a static electricity accumulation model, combine the current production influencing parameters, simulate the static electricity accumulation process, calculate and evaluate the static electricity risk, and predict the static electricity voltage change;

[0008] Establish a virtual production model, use the collected injection molding production data and production influencing parameters to virtually reproduce the production process, introduce electrostatic discharge factors into the model, simulate the quality changes under different electrostatic conditions, and determine the critical conditions for electrostatic discharge and its impact on injection molded parts;

[0009] The static electricity accumulation model is integrated into the virtual production model, and the production influencing parameters of this production are substituted to simulate the static electricity changes in real time. The changes of injection molded parts in the current electrostatic discharge environment are analyzed, and the quality loss of injection molded parts under this electrostatic discharge condition is quantified.

[0010] As a further solution of the present invention, the establishment of the static electricity accumulation model, combined with the current production influencing parameters, simulates the static electricity accumulation process, calculates and evaluates the static electricity risk, and predicts the static electricity voltage change, specifically includes:

[0011] Establish the relationship between electrostatic voltage and factors such as material contact and friction, consider the effects of temperature and humidity on static electricity accumulation, establish a static electricity accumulation model, and simulate the static electricity accumulation process;

[0012] Based on historical data and simulation results, the critical value of electrostatic risk is determined, and based on the simulation results of electrostatic voltage changes, the electrostatic voltage changes under different initial electrostatic conditions are judged.

[0013] As a further solution of the present invention, the static electricity accumulation model is established to simulate the static electricity accumulation process, specifically:

[0014] ;

[0015] in ， is the final electrostatic voltage in volts, is the initial electrostatic voltage in volts, is the electrostatic voltage in volts, is the total charge accumulation in coulombs, is the voltage adjustment due to environmental influences;

[0016] in:

[0017] ;

[0018] For the The amount of charge transferred when the two materials come into contact, For the The triboelectric potential difference between the two materials, in volts;

[0019] ;

[0020] is a constant related to the properties of the contact material, in coulombs / meter 2 , is the contact area in meters 2 , is the voltage generated when contact is made, in volts, is a constant related to friction characteristics, with the unit of coulomb / meter, is the friction displacement, in meters;

[0021] ;

[0022] is the initial voltage in volts, is the empirical coefficient of the effect of temperature on electrostatic voltage, is the current temperature in degrees Celsius, is the reference temperature, is the empirical coefficient of the effect of humidity on electrostatic voltage, is the current humidity in percentage, For reference humidity.

[0023] As a further solution of the present invention, the virtual production model is established, the production process is virtually reproduced using the collected injection molding production data and production influencing parameters, and the electrostatic discharge factor is introduced into the model to simulate the quality change under different electrostatic conditions, and determine the critical conditions for the occurrence of electrostatic discharge and the impact on injection molded parts, specifically including:

[0024] Establish a virtual production model and digitize the production process;

[0025] Integrate the electrostatic discharge model into the virtual production model and set up the mechanism of static electricity accumulation and release;

[0026] Run scenario simulations of different electrostatic voltage conditions through the virtual production model to obtain the production results of each production scenario, analyze the impact of static electricity on the production process, and record changes in the performance indicators of injection molded parts;

[0027] Compare the production results under different electrostatic voltage conditions, analyze the impact of static electricity on the quality of injection molded parts, determine under what electrostatic voltage conditions the quality of injection molded parts begins to decline, and obtain the critical value.

[0028] As a further solution of the present invention, the static electricity accumulation model is integrated into the virtual production model, the production influencing parameters of this production are substituted, the static electricity changes are simulated in real time, and the changes of the injection molded parts in the current electrostatic discharge environment are analyzed, and the quality loss of the injection molded parts under this electrostatic discharge condition is quantified, which specifically includes:

[0029] Obtain the injection molding production data and production influencing parameters set for this production, and import them into the virtual production model;

[0030] Integrate the static electricity accumulation model into the virtual production model, run real-time simulation in the virtual production model, monitor and record the changes in static electricity voltage;

[0031] Based on the electrostatic state calculated in real time by the model, the quality change of injection molded parts under the current electrostatic conditions is simulated to evaluate the impact of electrostatic discharge on quality;

[0032] Define the quality indicators of injection molded parts and quantify the quality loss of injection molded parts under this production condition based on simulation results.

[0033] Another object of the present invention is to provide an automotive plastic parts injection molding quality prediction system based on machine learning, the system comprising:

[0034] The data acquisition and parameter collection module is used to obtain the completed injection molding production data and collect production-influencing parameters, including environmental parameters, material parameters, and production process parameters;

[0035] The static electricity accumulation modeling module is used to establish a static electricity accumulation model, combine the current production influencing parameters, simulate the static electricity accumulation process, calculate and evaluate the static electricity risk, and predict the static electricity voltage change;

[0036] The virtual production process reproduction module is used to establish a virtual production model, use the collected injection molding production data and production influencing parameters to virtually reproduce the production process, and introduce electrostatic discharge factors into the model to simulate the quality changes under different electrostatic conditions, determine the critical conditions for electrostatic discharge and its impact on injection molded parts;

[0037] The real-time electrostatic analysis and quality assessment module is used to integrate the electrostatic accumulation model in the virtual production model, substitute the production influencing parameters of this production, simulate the electrostatic changes in real time, analyze the changes of injection molded parts in the current electrostatic discharge environment, and quantify the quality loss of injection molded parts under this electrostatic discharge condition.

[0038] As a further solution of the present invention, the electrostatic accumulation modeling module includes:

[0039] The static electricity accumulation model building unit is used to establish the relationship between static electricity voltage and factors such as material contact and friction, consider the influence of temperature and humidity on static electricity accumulation, establish a static electricity accumulation model, and simulate the static electricity accumulation process;

[0040] The electrostatic assessment and analysis unit is used to determine the critical value of the electrostatic risk based on historical data and simulation results, and to judge the electrostatic voltage change under different electrostatic initial conditions based on the simulation results of the electrostatic voltage change.

[0041] As a further solution of the present invention, the virtual production process reproduction module includes:

[0042] The production model processing unit is used to establish a virtual production model and digitally process the production process;

[0043] The static electricity mechanism setting unit is used to integrate the static electricity discharge model into the virtual production model and set the mechanism of static electricity accumulation and release;

[0044] The injection molded parts performance recording unit is used to run scenario simulations of different electrostatic voltage conditions through a virtual production model, obtain the production results of each production scenario, analyze the impact of static electricity on the production process, and record changes in injection molded parts performance indicators;

[0045] The injection molded part variation analysis unit is used to compare production results under different electrostatic voltage conditions, analyze the impact of static electricity on the quality of injection molded parts, determine under what electrostatic voltage conditions the quality of injection molded parts begins to decline, and obtain the critical value.

[0046] As a further solution of the present invention, the real-time electrostatic analysis and quality assessment module includes:

[0047] The production data import unit is used to obtain the injection molding production data and production influencing parameters set for this production, and import them into the virtual production model;

[0048] The actual production monitoring unit is used to integrate the static electricity accumulation model into the virtual production model, run real-time simulation in the virtual production model, and monitor and record the changes in static electricity voltage;

[0049] The quality impact recording unit is used to simulate the quality changes of injection molded parts under the current electrostatic conditions according to the electrostatic state calculated in real time by the model, and to evaluate the impact of electrostatic discharge on quality;

[0050] The quality loss quantification unit is used to define the quality indicators of injection molded parts and quantify the quality loss of injection molded parts under the current production conditions based on the simulation results.

[0051] The beneficial effects of the present invention are:

[0052] Digital twin technology can virtually reproduce the production process in real time, allowing engineers and operators to monitor the differences between actual production and virtual models, so as to quickly identify problems and deviations and adjust production parameters in time to optimize the process. This real-time feedback helps to improve production flexibility and responsiveness. At the same time, through simulation testing in a virtual environment, the impact of different parameters on the quality of injection molded parts can be evaluated, reducing the cost and time of physical testing.

[0053] In addition, the establishment of a static electricity accumulation model allows the impact of static electricity on injection molded parts to be quantified. With this quantification capability, companies can deeply understand the role of static electricity in the production process and optimize production conditions such as humidity, temperature and material selection, thereby reducing the negative impact of static electricity on product quality. This model can also provide early warning for the production process, helping operators take preventive measures before potential static electricity problems occur, reducing quality losses and production stagnation caused by static electricity.

[0054] The simulation capability of digital twin technology enables companies to test different production parameters and conditions in a virtual environment, evaluate their impact on static electricity accumulation and injection molded parts quality, and provide a basis for actual production. This flexible experimental method not only reduces the cost and time of physical testing, but also improves the efficiency of product design and process development. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flowchart of a method for predicting the injection molding quality of automotive plastic parts based on machine learning provided in an embodiment of the present invention;

[0056] Figure 2 A flow chart of simulating the static electricity accumulation process, calculating and evaluating the static electricity risk, and predicting the static electricity voltage change provided by an embodiment of the present invention;

[0057] Figure 3 A flow chart of simulating mass changes under different electrostatic conditions provided by an embodiment of the present invention;

[0058] Figure 4 A flowchart for analyzing changes in injection molded parts in a current electrostatic discharge environment and quantifying the quality loss of injection molded parts under this electrostatic discharge condition provided by an embodiment of the present invention;

[0059] Figure 5 A structural block diagram of an automotive plastic parts injection molding quality prediction system based on machine learning provided in an embodiment of the present invention;

[0060] Figure 6 A structural block diagram of a static electricity accumulation modeling module provided in an embodiment of the present invention;

[0061] Figure 7 A structural block diagram of a virtual production process reproduction module provided by an embodiment of the present invention;

[0062] Figure 8 This is a structural block diagram of a real-time electrostatic analysis and quality assessment module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0064] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0065] Figure 1 A flowchart of a method for predicting the injection molding quality of automotive plastic parts based on machine learning provided in an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0066] S100, obtaining completed injection molding production data and collecting production influencing parameters, wherein the production influencing parameters include: environmental parameters, material parameters and production process parameters;

[0067] In the step, the collected production data include the operation records of the injection molding machine, process parameters, material batch information, mold usage, etc. These data usually include but are not limited to injection speed, injection pressure, holding time, cooling time, temperature setting and actual temperature, etc. These parameters directly affect the fluidity and solidification characteristics of the molten plastic during the injection molding process, and have an important impact on the quality of the final injection molded parts.

[0068] At the same time, this step also involves collecting environmental parameters. These parameters usually include the temperature, humidity, air quality, and static environment of the production workshop. Changes in environmental parameters may affect the performance of the material, especially in the case of static electricity. Changes in humidity may promote or inhibit the accumulation of static electricity, thereby affecting the quality of the injection molded parts.

[0069] S200, establishes a static electricity accumulation model, combines the current production influencing parameters, simulates the static electricity accumulation process, calculates and evaluates static electricity risks, and predicts static electricity voltage changes;

[0070] This step aims at the generation mechanism of electrostatic voltage. Through experimental research and literature research, we systematically collect the electrostatic voltage data generated by different materials during contact and friction. These data lay the foundation for the establishment of a mathematical model. The model correlates the electrostatic voltage with factors such as the contact mode, friction coefficient, and contact area of ​​the material, thereby revealing the electrostatic characteristics of different material combinations.

[0071] Secondly, the impact of temperature and humidity on static electricity accumulation cannot be ignored. Studies have shown that under low humidity conditions, the accumulation of static electricity is more obvious, while high temperature may change the conductivity of the material and affect static electricity release. Based on this, temperature and humidity are introduced as dynamic variables in the model, and corresponding relationship functions are constructed to more realistically reflect the impact of the production environment on the change of static electricity voltage. In addition, historical data mining can also be used to analyze the change law of static electricity voltage under different environmental conditions to provide data support for subsequent model optimization.

[0072] By analyzing historical data and simulation results, the critical value of electrostatic risk is determined in order to identify quality problems that may arise under different production conditions. In this link, the introduction of machine learning algorithms enables the model to self-learn and optimize, improving the accuracy and stability of predictions. In addition, the model also compares the simulation results of electrostatic voltage changes with actual production data to determine the changes in electrostatic voltage under different initial conditions, analyze its impact on injection molding quality, and ensure the efficiency and stability of the production process.

[0073] This step not only improves the accuracy of quality prediction, but also dynamically adapts to changes in the production environment and enhances the adaptability of the model to different production conditions. In addition, clarifying the critical value of static electricity risk can provide early warning of possible quality problems, reduce production risks, and avoid waste of resources. By continuously iterating and optimizing the static electricity accumulation model, the performance of the prediction model can be continuously improved, promoting the optimization and improvement of the production process.

[0074] like Figure 2 As shown, the static electricity accumulation model is established, combined with the current production influencing parameters, to simulate the static electricity accumulation process, calculate and evaluate the static electricity risk, and predict the static electricity voltage change, specifically including:

[0075] S210, establish the relationship between electrostatic voltage and factors such as material contact and friction, consider the influence of temperature and humidity on static electricity accumulation, establish a static electricity accumulation model, and simulate the static electricity accumulation process;

[0076] S220, determining a critical value of the electrostatic risk based on historical data and simulation results, and judging the electrostatic voltage change under different electrostatic initial conditions based on the simulation results of the electrostatic voltage change.

[0077] In this step, the static electricity accumulation model is established to simulate the static electricity accumulation process, specifically:

[0078] ;

[0079] in ， is the final electrostatic voltage in volts, is the initial electrostatic voltage in volts, is the electrostatic voltage in volts, is the total charge accumulation in coulombs, is the voltage adjustment due to environmental influences;

[0080] in:

[0081] ;

[0082] For the The amount of charge transferred when the two materials come into contact, For the The triboelectric potential difference between the two materials, in volts;

[0083] ;

[0084] is a constant related to the properties of the contact material, in coulombs / meter 2 , is the contact area in meters 2 , is the voltage generated when contact is made, in volts, is a constant related to friction characteristics, with the unit of coulomb / meter, is the friction displacement, in meters;

[0085] ;

[0086] is the initial voltage in volts, is the empirical coefficient of the effect of temperature on electrostatic voltage, is the current temperature in degrees Celsius, is the reference temperature, is the empirical coefficient of the effect of humidity on electrostatic voltage, is the current humidity in percentage, For reference humidity.

[0087] S300, establish a virtual production model, use the collected injection molding production data and production influencing parameters to virtually reproduce the production process, introduce electrostatic discharge factors into the model, simulate the quality change under different electrostatic conditions, determine the critical conditions for electrostatic discharge and its impact on injection molded parts;

[0088] The primary goal of this step is to provide an integrated simulation platform for all factors that affect production quality, so that various parameters can be regulated and analyzed in a virtual environment. By simulating the actual production process, the virtual production model can not only reproduce the real production conditions, but also conduct in-depth analysis of potential electrostatic effects.

[0089] In the process of establishing a virtual production model, the collected injection molding production data and production influencing parameters (such as ambient temperature, humidity, material properties, machine adjustment, etc.) need to be input into the system first. These parameters will form an important basis for the model to ensure the accuracy and reliability of the simulation. Next, the electrostatic discharge model is integrated into the virtual production model, and the mechanism of static electricity accumulation and release is set up to enable it to reflect the dynamic changes of static electricity in the injection molding production process. This mechanism not only includes the generation process of static electricity, but also involves the release of static electricity and feedback to the environment, ensuring that the static electricity behavior in the model is consistent with the actual situation.

[0090] Subsequently, by running scenario simulations of different electrostatic voltage conditions through the virtual production model, the production results of each production scenario can be obtained. This process will help analyze the impact of static electricity on the production process and record the changes in the performance indicators of injection molded parts. By comparing the production results under different electrostatic voltage conditions, the model will reveal the extent of the impact of static electricity on the quality of injection molded parts. For example, when the electrostatic voltage exceeds a certain critical value, the injection molded parts may have quality defects, such as reduced surface gloss, increased dimensional deviation, and reduced strength.

[0091] The construction of digital twins makes it possible to visualize and control the production process. Production personnel can test and optimize production parameters in a safe virtual environment without taking risks in actual production. Secondly, the virtual production model with integrated electrostatic discharge model can analyze static electricity changes and their potential impact on production quality in real time, providing a scientific basis for production decisions. In addition, through a large number of scenario simulations, the critical value of static electricity impact can be systematically identified, providing reference data for subsequent quality control and improvement.

[0092] like Figure 3 As shown, the virtual production model is established, the production process is virtually reproduced using the collected injection molding production data and production influencing parameters, and the electrostatic discharge factor is introduced into the model to simulate the quality change under different electrostatic conditions, and determine the critical conditions for the occurrence of electrostatic discharge and the impact on injection molded parts, specifically including:

[0093] S310, establish a virtual production model and digitize the production process;

[0094] S320, integrating the electrostatic discharge model into the virtual production model and setting up the mechanism of static electricity accumulation and release;

[0095] S330, runs scenario simulations of different electrostatic voltage conditions through a virtual production model, obtains production results for each production scenario, analyzes the impact of static electricity on the production process, and records changes in performance indicators of injection molded parts;

[0096] S340, compares the production results under different electrostatic voltage conditions, analyzes the impact of static electricity on the quality of injection molded parts, determines under what electrostatic voltage conditions the quality of injection molded parts begins to decline, and obtains the critical value.

[0097] S400 integrates the static electricity accumulation model in the virtual production model, substitutes the production influencing parameters of this production, simulates the static electricity changes in real time, analyzes the changes of injection molded parts in the current electrostatic discharge environment, and quantifies the quality loss of injection molded parts under this electrostatic discharge condition.

[0098] This step will obtain the specific data of this injection molding production, including machine settings, mold type, injection cycle, material batch and other information. At the same time, it is also necessary to collect environmental parameters (such as temperature, humidity), material parameters (such as material conductivity, friction coefficient, etc.) and production process parameters (such as injection pressure, cooling time, etc.). These data will be used as input and imported into the virtual production model to provide a basis for subsequent simulation. Ensuring that the input data is accurate and complete is the key to a successful simulation.

[0099] Next, the established static electricity accumulation model is integrated into the virtual production model to form a comprehensive simulation system. The static electricity accumulation model will monitor the changes in static electricity voltage during the injection molding process in real time, and consider the effects of factors such as material friction, contact, temperature and humidity changes on static electricity generation. This model can not only calculate the static electricity voltage in real time, but also reflect the dynamic changes of static electricity, ensuring the real-time and accuracy of the simulation results. In the virtual production model, run real-time simulation to monitor the static electricity status during the injection molding process.

[0100] Through sensor simulation and data acquisition, the changes in electrostatic voltage are recorded and real-time data logs are generated for subsequent analysis. This process will include the accumulation and release mechanism of static electricity, as well as the timing and conditions when electrostatic discharge may occur. According to the electrostatic state calculated in real time by the model, the quality changes of injection molded parts under the current electrostatic conditions are simulated, and how static electricity affects the physical and chemical properties of the product under different voltage conditions, such as surface gloss, strength, dimensional accuracy, etc. By setting a series of quality indicators (such as dimensional tolerance, mechanical strength, surface defect rate, etc.), the impact of electrostatic discharge on the quality of injection molded parts is evaluated and the quality loss of the product is quantified.

[0101] Based on the simulation results, statistical analysis methods are used to quantify the quality loss of injection molded parts under this production condition. This can be done by establishing a loss function, combining historical data for prediction and comparison, and finding out the specific value and trend of quality loss. The results will provide intuitive data for production personnel to adjust production parameters in time to reduce quality loss.

[0102] This step enables real-time monitoring of the injection molding process, allowing production personnel to identify static electricity problems in a timely manner and make dynamic adjustments, thereby reducing the negative impact of static electricity on production quality. By quantifying the impact of electrostatic discharge on product quality, companies can make decisions based on scientific data and optimize production parameters, such as adjusting injection speed, material selection, or equipment configuration to improve production efficiency and product quality. Integrate the static electricity accumulation model with the virtual production model to build a digital twin and promote the intelligent transformation of the production process. Through digital simulation, companies can test and optimize production processes in a virtual environment and reduce the cost and time of physical testing. By pre-evaluating the impact of electrostatic discharge and quality loss, companies can take measures in advance to reduce potential quality risks and reduce rework and scrap costs caused by quality problems.

[0103] like Figure 4 As shown, the static electricity accumulation model is integrated into the virtual production model, the production influencing parameters of this production are substituted, the static electricity changes are simulated in real time, and the changes of the injection molded parts in the current electrostatic discharge environment are analyzed, and the quality loss of the injection molded parts under this electrostatic discharge condition is quantified, including:

[0104] S410, obtaining the injection molding production data and production influencing parameters set for this production, and importing them into the virtual production model;

[0105] S420, integrating the static electricity accumulation model into the virtual production model, running real-time simulation in the virtual production model, and monitoring and recording changes in the static electricity voltage;

[0106] S430, based on the electrostatic state calculated in real time by the model, simulates the quality change of the injection molded parts under the current electrostatic conditions and evaluates the impact of electrostatic discharge on the quality;

[0107] S440, define the quality index of the injection molded parts, and quantify the quality loss of the injection molded parts under the current production conditions based on the simulation results.

[0108] Figure 5 The structural block diagram of the automobile plastic parts injection molding quality prediction system based on machine learning provided by an embodiment of the present invention is as follows: Figure 5 As shown, the system comprises:

[0109] The data acquisition and parameter collection module 100 is used to obtain the completed injection molding production data and collect production-influencing parameters, which include: environmental parameters, material parameters, and production process parameters;

[0110] The static electricity accumulation modeling module 200 is used to establish a static electricity accumulation model, combine the current production influencing parameters, simulate the static electricity accumulation process, calculate and evaluate the static electricity risk, and predict the static electricity voltage change;

[0111] The virtual production process reproducing module 300 is used to establish a virtual production model, use the collected injection molding production data and production influencing parameters to virtually reproduce the production process, introduce electrostatic discharge factors into the model, simulate the quality change under different electrostatic conditions, and determine the critical conditions for electrostatic discharge and its impact on injection molded parts;

[0112] The real-time electrostatic analysis and quality assessment module 400 is used to integrate the electrostatic accumulation model in the virtual production model, substitute the production influencing parameters of this production, simulate the electrostatic changes in real time, and analyze the changes of the injection molded parts in the current electrostatic discharge environment, and quantify the quality loss of the injection molded parts under this electrostatic discharge condition.

[0113] like Figure 6 As shown, the static electricity accumulation modeling module 200 includes:

[0114] The static electricity accumulation model building unit 210 is used to establish the relationship between the static electricity voltage and factors such as material contact and friction, consider the influence of temperature and humidity on static electricity accumulation, establish a static electricity accumulation model, and simulate the static electricity accumulation process;

[0115] The static electricity evaluation and analysis unit 220 is used to determine the critical value of the static electricity risk according to the historical data and the simulation results, and to judge the static electricity voltage change under different static electricity initial conditions according to the simulation results of the static electricity voltage change.

[0116] like Figure 7 As shown, the virtual production process replay module 300 includes:

[0117] The production model processing unit 310 is used to establish a virtual production model and digitally process the production process;

[0118] The static electricity mechanism setting unit 320 is used to integrate the static electricity discharge model into the virtual production model and set the mechanism of static electricity accumulation and release;

[0119] The injection molded part performance recording unit 330 is used to run scenario simulations of different electrostatic voltage conditions through a virtual production model, obtain production results for each production scenario, analyze the impact of static electricity on the production process, and record changes in injection molded part performance indicators;

[0120] The injection molded part variation analysis unit 340 is used to compare production results under different electrostatic voltage conditions, analyze the impact of static electricity on the quality of injection molded parts, determine under what electrostatic voltage condition the quality of injection molded parts begins to decline, and obtain a critical value.

[0121] like Figure 8 As shown, the real-time electrostatic analysis and quality assessment module 400 includes:

[0122] The production data importing unit 410 is used to obtain the injection molding production data and production influencing parameters set for this production, and import them into the virtual production model;

[0123] The actual production monitoring unit 420 is used to integrate the static electricity accumulation model into the virtual production model, run real-time simulation in the virtual production model, monitor and record the change of static electricity voltage;

[0124] The quality impact recording unit 430 is used to simulate the quality change of the injection molded part under the current electrostatic condition according to the electrostatic state calculated in real time by the model, and to evaluate the impact of electrostatic discharge on the quality;

[0125] The quality loss quantification unit 440 is used to define the quality index of the injection molded part and quantify the quality loss of the injection molded part under the current production conditions based on the simulation results.

[0126] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0127] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0128] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0130] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting the injection molding quality of automotive plastic parts based on machine learning, characterized in that: The method comprises: Acquire completed injection molding production data and collect production influencing parameters, including: environmental parameters, material parameters and production process parameters; Establish a static electricity accumulation model, combine the current production influencing parameters, simulate the static electricity accumulation process, calculate and evaluate the static electricity risk, and predict the static electricity voltage change; Establish a virtual production model, use the collected injection molding production data and production influencing parameters to virtually reproduce the production process, introduce electrostatic discharge factors into the model, simulate the quality changes under different electrostatic conditions, and determine the critical conditions for electrostatic discharge and its impact on injection molded parts; Integrate the static electricity accumulation model into the virtual production model, substitute the production influencing parameters of this production, simulate the static electricity changes in real time, analyze the changes of injection molded parts in the current static discharge environment, and quantify the quality loss of injection molded parts under this static discharge condition; The static electricity accumulation model is established to simulate the static electricity accumulation process, specifically: ； in ， is the final electrostatic voltage in volts, is the initial electrostatic voltage in volts, is the electrostatic voltage in volts, is the total charge accumulation in coulombs, is the voltage adjustment due to environmental influences; in: ； For the The amount of charge transferred when the two materials come into contact, For the The triboelectric potential difference between the two materials, in volts; ； is a constant related to the properties of the contact material, in coulombs / meter 2 , is the contact area in meters 2 , is the voltage generated when contact is made, in volts, is a constant related to friction characteristics, with the unit of coulomb / meter, is the friction displacement, in meters; ； is the initial voltage in volts, is the empirical coefficient of the effect of temperature on electrostatic voltage, is the current temperature in degrees Celsius, is the reference temperature, is the empirical coefficient of the effect of humidity on electrostatic voltage, is the current humidity in percentage, is the reference humidity; The virtual production model is established, the production process is virtually reproduced using the collected injection molding production data and production influencing parameters, and the electrostatic discharge factor is introduced into the model to simulate the quality change under different electrostatic conditions, and determine the critical conditions for the occurrence of electrostatic discharge and the impact on injection molded parts, specifically including: Establish a virtual production model and digitize the production process; Integrate the electrostatic discharge model into the virtual production model and set up the mechanism of static electricity accumulation and release; Run scenario simulations of different electrostatic voltage conditions through the virtual production model to obtain the production results of each production scenario, analyze the impact of static electricity on the production process, and record changes in the performance indicators of injection molded parts; Compare the production results under different electrostatic voltage conditions, analyze the impact of static electricity on the quality of injection molded parts, determine under what static voltage conditions the quality of injection molded parts begins to decline, and obtain the critical value; The static electricity accumulation model is integrated into the virtual production model, the production influencing parameters of this production are substituted, static electricity changes are simulated in real time, and changes in injection molded parts in the current static electricity discharge environment are analyzed to quantify the quality loss of injection molded parts under this static electricity discharge condition, specifically including: Obtain the injection molding production data and production influencing parameters set for this production, and import them into the virtual production model; Integrate the static electricity accumulation model into the virtual production model, run real-time simulation in the virtual production model, monitor and record the changes in static electricity voltage; Based on the electrostatic state calculated in real time by the model, the quality change of injection molded parts under the current electrostatic conditions is simulated to evaluate the impact of electrostatic discharge on quality; Define the quality indicators of injection molded parts and quantify the quality loss of injection molded parts under this production condition based on simulation results.

2. The method according to claim 1, characterized in that The static electricity accumulation model is established, combined with the current production influencing parameters, to simulate the static electricity accumulation process, calculate and evaluate the static electricity risk, and predict the static electricity voltage change, specifically including: Establish the relationship between electrostatic voltage and material contact and friction factors, consider the effects of temperature and humidity on static electricity accumulation, establish a static electricity accumulation model, and simulate the static electricity accumulation process; Based on historical data and simulation results, the critical value of electrostatic risk is determined, and based on the simulation results of electrostatic voltage changes, the electrostatic voltage changes under different initial electrostatic conditions are judged.

3. The injection molding quality prediction system for automotive plastic parts based on machine learning is characterized by: The system comprises: The data acquisition and parameter collection module is used to obtain the completed injection molding production data and collect production-influencing parameters, including environmental parameters, material parameters, and production process parameters; The static electricity accumulation modeling module is used to establish a static electricity accumulation model, combine the current production influencing parameters, simulate the static electricity accumulation process, calculate and evaluate the static electricity risk, and predict the static electricity voltage change; The virtual production process reproduction module is used to establish a virtual production model, use the collected injection molding production data and production influencing parameters to virtually reproduce the production process, and introduce electrostatic discharge factors into the model to simulate the quality changes under different electrostatic conditions, determine the critical conditions for electrostatic discharge and its impact on injection molded parts; The real-time static analysis and quality assessment module is used to integrate the static accumulation model into the virtual production model, substitute the production influencing parameters of this production, simulate the static change in real time, and analyze the changes of injection molded parts in the current static discharge environment, and quantify the quality loss of injection molded parts under this static discharge condition; The electrostatic accumulation modeling module includes: The static electricity accumulation model building unit is used to establish the relationship between static electricity voltage and material contact and friction factors, consider the influence of temperature and humidity on static electricity accumulation, establish a static electricity accumulation model, and simulate the static electricity accumulation process; The static electricity assessment and analysis unit is used to determine the critical value of static electricity risk based on historical data and simulation results, and to judge the static electricity voltage change under different static electricity initial conditions based on the simulation results of the static electricity voltage change; The virtual production process reproduction module includes: The production model processing unit is used to establish a virtual production model and digitally process the production process; The static electricity mechanism setting unit is used to integrate the static electricity discharge model into the virtual production model and set the mechanism of static electricity accumulation and release; The injection molded parts performance recording unit is used to run scenario simulations of different electrostatic voltage conditions through a virtual production model, obtain the production results of each production scenario, analyze the impact of static electricity on the production process, and record changes in injection molded parts performance indicators; The injection molded part change analysis unit is used to compare the production results under different electrostatic voltage conditions, analyze the impact of static electricity on the quality of injection molded parts, determine under what electrostatic voltage conditions the quality of injection molded parts begins to decline, and obtain the critical value; The real-time electrostatic analysis and quality assessment module includes: The production data import unit is used to obtain the injection molding production data and production influencing parameters set for this production, and import them into the virtual production model; The actual production monitoring unit is used to integrate the static electricity accumulation model into the virtual production model, run real-time simulation in the virtual production model, and monitor and record the changes in static electricity voltage; The quality impact recording unit is used to simulate the quality changes of injection molded parts under the current electrostatic conditions according to the electrostatic state calculated in real time by the model, and to evaluate the impact of electrostatic discharge on quality; The quality loss quantification unit is used to define the quality indicators of injection molded parts and quantify the quality loss of injection molded parts under the current production conditions based on the simulation results.

Images