Full-automatic injection molding optimization method, device and equipment based on digital twinning

Abstract

The invention relates to a full-automatic injection molding optimization method, device and equipment based on digital twinning, and belongs to the technical field of intelligent manufacturing equipment. Inputting the sensor data into a digital twin model to construct equipment dynamic response simulation, and synchronously comparing the actual mode locking force with the offset of a preset pressure threshold; generating compensation data of mold locking pressure according to the offset, and dynamically correcting an acceleration curve of a servo motor in a glue injection stage on the basis of the displacement of a screw rod; in hot runner control, a thermal interference compensation coefficient is calculated according to a temperature difference value of adjacent temperature zones, and an output power gradient signal of each heating ring is adjusted; the corrected parameter information is transmitted to an equipment PLC through an industrial bus to execute control, and a compensation coefficient threshold value is iteratively updated according to a product weight fluctuation value in the next forming period; closed-loop data interaction of an equipment control system is achieved, and the injection molding process is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing equipment, and particularly relates to an optimization method, device and equipment for full-automatic injection molding based on digital twin. Background Art

[0002] In the injection molding process, the stability of the clamping force, the uniformity of the melt filling, and the control accuracy of the hot runner temperature are the core factors affecting the quality of the product. Traditional methods rely on manual experience to set fixed process parameters, and it is difficult to respond in real time to problems such as the fluctuation of the clamping force during the injection stage and the temperature drift caused by the thermal interference in the hot runner temperature zone. In the prior art, although there are local parameter adjustment schemes based on sensor feedback, there is a lack of global simulation ability for the dynamic response of the equipment, resulting in compensation lag and the failure of multivariable coupling control. For example, the pressure compensation of the clamping cylinder and the servo control of the screw often adopt independent PID regulation, without considering the reverse influence of the cavity deformation on the melt flow; the regulation of the hot runner temperature zone is mostly based on single-point temperature feedback, and it is impossible to suppress the heat conduction interference between adjacent heating coils. In addition, most of the existing digital twin models focus on offline simulation and fail to achieve closed-loop data interaction with the equipment control system, resulting in the disconnection between process optimization and execution. Summary of the Invention

[0003] To achieve the above object, the optimization method for full-automatic injection molding based on digital twin provided by the present invention includes the following steps: Real-time collect sensor data through sensors installed on the clamping mechanism, screw and hot runner, and the sensor data includes the clamping force fluctuation value, the screw displacement amount, and the temperature data of each section; Input the sensor data into the digital twin model to construct a dynamic response simulation of the equipment, and synchronously compare the offset between the actual clamping force and the preset pressure threshold; Generate compensation data for the clamping pressure according to the offset, and dynamically correct the servo motor acceleration curve during the injection stage based on the screw displacement amount; In the hot runner control, calculate the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones, and adjust the output power gradient signal of each heating coil; Transmit the corrected parameter information to the equipment PLC for execution control through the industrial bus, and iteratively update the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle, where the parameter information includes the compensation data, the servo motor acceleration curve, and the output power gradient signal.

[0004] Further, the step of inputting the sensor data into the digital twin model to construct a dynamic response simulation of the equipment includes: Perform adaptive sliding average filtering on the clamping force fluctuation value, and fuse the time series change amount of the screw displacement amount to obtain the dynamic curve of the melt filling rate; Establish a stiffness parameter library for the mold clamping mechanism in the digital twin model, and update the thermal conductivity matrix of the hot runner in combination with the section temperature data collected in real time; Input the dynamic curve and the thermal conductivity matrix into the melt rheology equation to generate a material relationship table for the pressure gradient distribution in the mold cavity; Calculate the material threshold range according to the joint relationship between the pressure gradient of the material relationship table and the mold clamping force fluctuation value, and use the material threshold range as the real-time offset comparison benchmark.

[0005] Further, the step of synchronously comparing the offset between the actual mold clamping force and the preset pressure threshold includes: Take the upper and lower limits of the actual mold clamping force corresponding to the material threshold range, and take the absolute values of the upper and lower limits; Compare the absolute value with the preset pressure threshold to obtain the offset.

[0006] Further, the step of generating compensation data for the mold clamping pressure according to the offset and dynamically correcting the servo motor acceleration curve in the injection stage based on the screw displacement includes: At a certain moment, input the offset into a preset compensation database, match the pressure compensation coefficient corresponding to the current injection stage, and generate a stepped pressure increase sequence for mold clamping; At the same moment, based on the screw displacement obtained in real time, calculate the dynamic deviation between the melt propulsion speed and the preset injection curve, and generate a broken line correction function for the servo motor acceleration; According to the coupling relationship between the stepped pressure increase sequence and the broken line correction function, inject corresponding pressure compensation signals and acceleration correction parameters in segments during the injection stage.

[0007] Further, in the hot runner control, the step of calculating the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones and adjusting the output power gradient signal of each heating coil includes: Real-time monitor the temperature difference between adjacent temperature zones, and extract the temperature zone combinations where the temperature difference exceeds the preset tolerance threshold; Based on the duration of the temperature difference and the temperature interval distance, generate a thermal interference transfer coefficient, and calculate the initial weight of the compensation coefficient in combination with the thermal inertia parameters of the heating coil; Compare the initial weight with the power gradient stability index in the historical data to generate a segmented power adjustment command sequence for each heating coil.

[0008] Further, the step of transmitting the corrected parameter information to the device PLC for execution control through the industrial bus includes: Convert the compensation data, servo motor acceleration curve, and power gradient signal into a control instruction set compatible with the industrial bus protocol and encapsulate it into an instruction data packet synchronized with the timestamp; Divide the instruction execution priorities according to the current working stage of the injection molding machine, and generate a segmented instruction distribution sequence that matches the timing of the injection and holding pressure stages; When sending the instruction sequence to the PLC through the industrial bus, synchronously inject the device status verification code to ensure the timing alignment between the control instruction and the actual operating status of the device.

[0009] Further, the step of iteratively updating the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle includes: In the next molding cycle, collect the product weight fluctuation value in real time through a weighing device, and extract the abnormal fluctuation interval where the weight difference between adjacent cycles exceeds the preset stability threshold; Calibrate the past timestamps of the abnormal fluctuation interval, and calculate the correlation weight between the compensation coefficient threshold and the weight deviation through the data information of the past timestamps; Write the correlation weight into the corresponding section of the parameter self-learning module of the digital twin model for correction.

[0010] The present invention proposes a full-automatic injection molding optimization device based on digital twin, including: A collection unit for collecting sensor data in real time through sensors installed on the mold clamping mechanism, screw, and hot runner. The sensor data includes the mold clamping force fluctuation value, screw displacement, and temperature data of each section; A model unit for inputting the sensor data into the digital twin model to construct a device dynamic response simulation, and synchronously comparing the offset between the actual mold clamping force and the preset pressure threshold; A first compensation unit for generating compensation data for the mold clamping pressure according to the offset and dynamically correcting the servo motor acceleration curve in the injection stage based on the screw displacement; A second compensation unit for calculating the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones in the hot runner control and adjusting the output power gradient signal of each heating coil; A correction unit for transmitting the corrected parameter information to the device PLC for execution control through the industrial bus, and iteratively updating the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle, where the parameter information includes the compensation data, the servo motor acceleration curve, and the output power gradient signal.

[0011] The present invention also provides a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps of the above-mentioned full-automatic injection molding optimization method based on digital twin are implemented.

[0012] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned fully automatic injection molding optimization method based on digital twin are realized.

[0013] The fully automatic injection molding optimization method, device and equipment based on digital twin provided by the present invention have the following beneficial effects: (1) By driving the digital twin model in real time with sensor data, a dynamic coupling simulation of the stiffness of the clamping mechanism, heat transfer of the hot runner and melt rheology is constructed, the deformation threshold of the mold cavity is accurately predicted, and the synchronization efficiency of the compensation instruction and the equipment action is realized; (2) Based on the clamping force offset, a stepped pressure boosting instruction is generated, and the acceleration curve of the servo motor is dynamically corrected by coupling the screw displacement, effectively suppressing the melt front velocity fluctuation in the injection stage and reducing the defect rates of product flash and short shot.

[0014] (3) By real-time analysis of the temperature difference between adjacent temperature zones, a reverse compensation power pulse is generated to accurately offset the heat conduction interference, ensure the matching of the multi-segment temperature gradient and the material curing rate, and improve the dimensional consistency of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic flow chart of a fully automatic injection molding optimization method based on digital twin in an embodiment of the present invention; Figure 2 is a structural block diagram of a fully automatic injection molding optimization device based on digital twin in an embodiment of the present invention; Figure 3 is a schematic structural block diagram of a computer device in an embodiment of the present invention.

[0016] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to 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 used to limit the present invention.

[0018] Referring to Figure 1 , a schematic flow chart of a fully automatic injection molding optimization method based on digital twin, the method includes the following steps: S1, sensor data is collected in real time through sensors installed on the clamping mechanism, screw and hot runner, and the sensor data includes the clamping force fluctuation value, screw displacement and temperature data of each section; S2. Input the sensor data into the digital twin model to construct a dynamic response simulation of the device, and synchronously compare the offset between the actual clamping force and the preset pressure threshold; S3. Generate compensation data for the clamping pressure according to the offset, and dynamically correct the servo motor acceleration curve during the injection stage based on the screw displacement; S4. In the hot runner control, calculate the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones, and adjust the output power gradient signal of each heating coil; S5. Transmit the corrected parameter information to the device PLC for execution control through the industrial bus, and iteratively update the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle, where the parameter information includes the compensation data, the servo motor acceleration curve, and the output power gradient signal.

[0019] In step S1, install high-response pressure sensors on the moving platen and tie bars to monitor the clamping force fluctuation in real time to obtain the above-mentioned clamping force fluctuation value; measure the screw displacement by both a magnetic grating ruler and an encoder, calculate the melt propulsion rate, and obtain the screw displacement; and arrange thermocouples and infrared probes in each temperature zone to monitor the temperature difference between adjacent temperature zones in real time to obtain the temperature data of each section.

[0020] In the embodiment of step S2, specifically, the step of inputting the sensor data into the digital twin model to construct a dynamic response simulation of the device includes: Perform adaptive sliding average filtering on the clamping force fluctuation value, and fuse the time-series change amount of the screw displacement to obtain the dynamic curve of the melt filling rate; Establish a stiffness parameter library of the clamping mechanism in the digital twin model, and update the hot runner thermal conductivity matrix in combination with the section temperature data collected in real time; Input the dynamic curve and the thermal conductivity matrix into the melt rheology equation to generate a material relationship table of the pressure gradient distribution in the mold cavity; Calculate the material threshold range according to the joint relationship between the pressure gradient in the material relationship table and the clamping force fluctuation value, and use the material threshold range as the real-time offset comparison benchmark.

[0021] The specific implementation of step S2 is achieved through a four-step closed-loop of data preprocessing - model update - dynamic prediction - threshold calculation, which is gradually explained according to the above text, where: In the above-mentioned sub-step of performing adaptive sliding average filtering on the clamping force fluctuation value and fusing the time-series change amount of the screw displacement to obtain the dynamic curve of the melt filling rate, the purpose is to eliminate noise interference, extract the effective clamping force signal, and correlate the melt flow state; dynamically adjust the filtering window width according to the clamping force fluctuation characteristics, and the window calculation formula is:

[0022] Where ΔP is the pressure difference between adjacent sampling points, with the unit of kN; when ΔP suddenly increases, the window automatically widens to smooth high-frequency noise; a specific case is if then (a 7-point sliding window is adopted). The dynamic curve of the melt filling rate is obtained by fusing the time-sequential change of the screw displacement. The screw displacement is measured by the above-mentioned magnetic grating ruler and encoder. Taking the screw displacement as the Y-axis and time as the X-axis, the first curve of the time-sequential change of the screw is obtained; then, taking the first curve as the Y-axis and the filling volume as the X-axis, the second curve of the dynamic curve is obtained.

[0023] In the above-mentioned sub-step of establishing the stiffness parameter library of the clamping mechanism in the digital twin model and updating the thermal runner thermal conductivity matrix in combination with the section temperature data collected in real time, the purpose is to establish a dynamic simulation basis for the physical characteristics of the equipment; the stiffness parameter library of the clamping mechanism includes parameters such as the elastic modulus of the moving platen, the stiffness coefficient of the tie rod, and the friction coefficient of the mold contact surface. The initial values are calibrated through no-load tests of the equipment and material mechanics experiments; updating the thermal runner thermal conductivity matrix based on the section temperature data collected in real time uses the formula:

[0024] Where is the equivalent thermal conductivity from temperature zone i to j, is the temperature zone spacing, and are the temperature values of the corresponding partitions.

[0025] In the above-mentioned sub-step of inputting the dynamic curve and the thermal conductivity matrix into the melt rheology equation to generate a material relationship table of the pressure gradient distribution in the mold cavity, the purpose is to predict the influence of melt flow on the deformation of the mold cavity; the pressure value in the mold cavity is calculated through the melt rheology equation, and the melt rheology equation is:

[0026] Where is the pressure value in the mold cavity, is the above-mentioned dynamic curve, is the melt viscosity of the corresponding material, and T is the temperature value. By recording the obtained pressure value in the mold cavity and the corresponding material, the relevant information is recorded in the material relationship table. It can be understood that the material relationship table carries various types of materials, material parameters, melt viscosity, screw transmission efficiency, and the pressure value in the mold cavity.

[0027] In the above-mentioned sub-step of calculating the material threshold range according to the joint relationship between the pressure gradient of the material relationship table and the clamping force fluctuation value and using the material threshold range as the real-time offset comparison benchmark, the purpose is to convert the simulation result into a quantitative benchmark for clamping force control; the joint relationship uses the formula , where b is a preset fixed deviation, is the clamping force fluctuation value of the material relationship table, The pressure gradient of the material relationship table. For the calculation of the material threshold range, only the upper limit needs to be determined, because the lower limit only needs to set the minimum clamping force based on the material properties to prevent short shots. The upper limit is calculated by the formula , where k is the set cavity deformation transfer coefficient. For example, when injecting a certain automotive connector, predicting the maximum pressure gradient , the upper limit of the dynamic threshold is calculated .

[0028] In a specific process, the step of synchronously comparing the offset between the actual clamping force and the preset pressure threshold includes: taking the upper and lower limits of the actual clamping force corresponding to the material threshold range, and taking the absolute value of the upper and lower limits; comparing the absolute value with the preset pressure threshold to obtain the offset.

[0029] In the embodiment of step S3, specifically, the step of generating compensation data for the clamping pressure based on the offset and dynamically correcting the servo motor acceleration curve in the injection stage includes: At a certain moment, input the offset into a preset compensation database, match the pressure compensation coefficient corresponding to the current injection stage, and generate a stepped pressure increase sequence for clamping; At the same moment, based on the screw displacement obtained in real time, calculate the dynamic deviation between the melt propulsion speed and the preset injection curve, and generate a broken line correction function for the servo motor acceleration; According to the coupling relationship between the stepped pressure increase sequence and the broken line correction function, inject the corresponding pressure compensation signal and acceleration correction parameters in segments during the injection stage.

[0030] The core of the specific implementation step S3 lies in synchronously generating clamping pressure compensation and servo acceleration correction instructions to achieve multi-variable coordinated control in the injection stage. It will be gradually explained according to the above text, where: In the above sub-step of inputting the offset into a preset compensation database at a certain moment, matching the pressure compensation coefficient corresponding to the current injection stage, and generating a stepped pressure increase sequence for clamping, its purpose is to adjust the clamping cylinder pressure in real time according to the clamping force offset to suppress excessive cavity deformation; input the offset obtained in real time into the compensation database, and match the pressure compensation coefficient of the current injection stage , so as to calculate the stepped pressure increase sequence through the formula . .

[0031] In a calculation case, such as (Filling the middle period with a displacement of 45 mm), then . It is divided into 5 boosting steps with a maximum step of 80 kN (375 ÷ 80 ≈ 4.69 → rounded up to 5 steps, 75 kN per step).

[0032] Referring to Table 1, the preset database contains pressure compensation coefficients for different injection stages (such as the initial, middle, and final filling stages), which are calibrated through historical process data.

[0033]

[0034] In the above-mentioned sub-step of generating a broken-line correction function for the servo motor acceleration by calculating the dynamic deviation between the melt propulsion speed and the preset injection curve based on the screw displacement obtained in real time at the same moment, the purpose is to dynamically adjust the servo acceleration according to the screw displacement to ensure a stable melt propulsion rate. Among them, calculating the melt propulsion speed is to perform a first-order difference on the screw displacement , specifically:

[0035] The dynamic deviation is to compare the melt propulsion speed and the dynamic curve to obtain the deviation between the curves.

[0036] Based on the dynamic deviation, using the correction function, to command the acceleration of the servo motor , the correction function uses the following formula:

[0037] When measuring (when overspeed), then the servo motor acceleration is corrected, , and the servo motor runs according to the corrected acceleration, so that returns to the preset curve within 200 ms.

[0038] In the above-mentioned sub-step of injecting the corresponding pressure compensation signal and acceleration correction parameters in different time periods during the injection stage according to the coupling relationship between the stepped boosting sequence and the broken-line correction function, the purpose is to coordinate the mold clamping boosting and servo acceleration actions to avoid control conflicts.

[0039] Referring to Table 2, with a control period of 10 ms, the stepped boosting sequence and the broken-line correction function are aligned on the t-axis:

[0040] In the embodiment of step S4, specifically, in the hot runner control, the step of calculating the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones and adjusting the output power gradient signal of each heating coil includes: Monitor the temperature difference between adjacent temperature zones in real time, and extract the combination of temperature zones where the temperature difference exceeds the preset tolerance threshold; Generate a heat interference transfer coefficient based on the duration for which the temperature difference persists and the temperature interval distance, and calculate the initial weight of the compensation coefficient in combination with the thermal inertia parameters of the heating coil; Compare the initial weight with the power gradient stability index in historical data to generate a segmented power adjustment instruction sequence for each heating coil.

[0041] In the specific implementation step S4, by arranging thermocouples and infrared probes in each temperature zone set in the mold cavity, monitor the temperature difference between adjacent temperature zones in real time, and extract the temperature zones where the temperature difference exceeds the preset tolerance threshold; if the temperature zone exceeds the preset tolerance threshold for the corresponding time, generate the heat interference transfer coefficient between the temperature zones. The transfer coefficient is obtained from the values fed back by each thermocouple. In combination with the heating coils corresponding to each temperature zone, design the weights for the data units of the heating instructions for each heating coil. During the process of verifying the weight design, compare with the historical data to determine whether the heating instructions are stable when the data units under the corresponding weights are issued. If there is no historical data, issue the heating instructions in the form of a gradient. The instructions in this gradient form adopt a sequence. This temperature gradient formula is a simple formula, that is, perform a gradient on the expected temperature value and the current temperature value.

[0042] In the embodiment of step S5, specifically, the step of transmitting the corrected parameter information to the device PLC for execution control through the industrial bus includes: Convert the compensation data, servo motor acceleration curve, and power gradient signal into a control instruction set compatible with the industrial bus protocol, and encapsulate it into an instruction data packet synchronized with the time stamp; Divide the instruction execution priority according to the current working stage of the injection molding machine, and generate a segmented instruction distribution sequence that matches the timing of the injection and holding pressure stages; When sending the instruction sequence to the PLC through the industrial bus, synchronously inject the device status verification code to ensure the timing alignment of the control instructions with the actual operating status of the device.

[0043] In another embodiment, the step of iteratively updating the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle includes: In the next molding cycle, collect the product weight fluctuation value in real time through a weighing device, and extract the abnormal fluctuation interval where the weight difference between adjacent cycles exceeds the preset stability threshold; Calibrate the past time stamp of the abnormal fluctuation interval, and calculate the correlation weight between the compensation coefficient threshold and the weight deviation through the data information of the past time stamp; Write the correlation weight into the corresponding section of the parameter self-learning module of the digital twin model for correction.

[0044] In this embodiment, a weighing device is used to collect the weight value of a single product in real time, determine the difference between the weight value and the fluctuation value of this batch of products, and set a stable fluctuation range for the same batch; if one or more products exceed the preset stable threshold, the time stamp when the abnormal product is produced is associated, and the weight under this time stamp is optimized in the next cycle for compensation.

[0045] Reference appendix Figure 2 The device block diagram of an automatic injection molding optimization device based on digital twin according to the present invention is as follows. The device includes: An acquisition unit, configured to collect sensor data in real time through sensors installed on the mold clamping mechanism, screw, and hot runner. The sensor data includes the mold clamping force fluctuation value, screw displacement amount, and temperature data of each section. A model unit, configured to input the sensor data into a digital twin model to construct a dynamic response simulation of the device, and synchronously compare the offset between the actual mold clamping force and the preset pressure threshold. A first compensation unit, configured to generate compensation data for the mold clamping pressure according to the offset, and dynamically correct the servo motor acceleration curve in the injection stage based on the screw displacement amount. A second compensation unit, configured to calculate a thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones in the hot runner control, and adjust the output power gradient signal of each heating coil. A correction unit, configured to transmit the corrected parameter information to the device PLC for execution control through an industrial bus, and iteratively update the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle. The parameter information includes the compensation data, the servo motor acceleration curve, and the output power gradient signal.

[0046] Refer to Figure 3 , in the embodiment of the present invention, a computer device is further provided. The computer device may be a server, and its internal structure may be as Figure 3 shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0047] Those skilled in the art can understand, Figure 3The structure shown is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0048] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0049] In summary, by installing sensors on the mold clamping mechanism, screw, and hot runner to collect sensor data in real time, the sensor data includes the mold clamping force fluctuation value, screw displacement, and temperature data of each section; inputting the sensor data into the digital twin model construction device for dynamic response simulation, and synchronously comparing the offset between the actual mold clamping force and the preset pressure threshold; generating compensation data for the mold clamping pressure according to the offset, and dynamically correcting the servo motor acceleration curve in the injection stage based on the screw displacement; in the hot runner control, calculating the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones, and adjusting the output power gradient signal of each heating coil; transmitting the corrected parameter information to the device PLC through the industrial bus for execution control, and iteratively updating the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle, where the parameter information includes the compensation data, the servo motor acceleration curve, and the output power gradient signal; realizing the closed-loop data interaction of the device control system and optimizing the injection molding process.

[0050] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided by the present invention and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, etc.

[0051] It should be noted that in this article, the terms "including", "comprising", or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, apparatus, article, or method including such element.

[0052] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An optimization method for fully automatic injection molding based on digital twin, characterized in that, It includes the following steps: Collect sensor data in real time through sensors installed on the mold clamping mechanism, screw, and hot runner. The sensor data includes mold clamping force fluctuation values, screw displacement amounts, and temperature data of each section; Input the sensor data into the digital twin model to construct a dynamic response simulation of the device, and synchronously compare the offset between the actual mold clamping force and the preset pressure threshold; Generate compensation data for the mold clamping pressure according to the offset, and dynamically correct the servo motor acceleration curve in the injection stage based on the screw displacement amount; In the hot runner control, calculate the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones, and adjust the output power gradient signal of each heating coil; Transmit the corrected parameter information to the device PLC through the industrial bus for execution control, and iteratively update the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle. Among them, the parameter information includes the compensation data, the servo motor acceleration curve, and the output power gradient signal.

2. The fully automatic injection molding optimization method based on digital twin according to claim 1, wherein, The step of inputting the sensor data into the digital twin model to construct a dynamic response simulation of the device includes: Perform adaptive sliding average filtering on the mold clamping force fluctuation value, and fuse the time series change amount of the screw displacement amount to obtain the dynamic curve of the melt filling rate; Establish a stiffness parameter library of the mold clamping mechanism in the digital twin model, and update the thermal conductivity coefficient matrix of the hot runner in combination with the section temperature data collected in real time; Input the dynamic curve and the thermal conductivity coefficient matrix into the melt rheology equation to generate a material relationship table of the pressure gradient distribution in the mold cavity; Calculate the material threshold range according to the joint relationship between the pressure gradient of the material relationship table and the mold clamping force fluctuation value, and use the material threshold range as the real-time offset comparison benchmark.

3. The fully automatic injection molding optimization method based on digital twin according to claim 2, characterized in that The step of synchronously comparing the offset between the actual mold clamping force and the preset pressure threshold includes: Take the upper and lower limits of the actual mold clamping force corresponding to the material threshold range, and take the absolute value of the upper and lower limits; Compare the absolute value with the preset pressure threshold to obtain the offset.

4. The fully automatic injection molding optimization method based on digital twin according to claim 1, characterized in that The step of generating compensation data for the mold clamping pressure according to the offset and dynamically correcting the servo motor acceleration curve in the injection stage based on the screw displacement amount includes: At a moment, input the offset into a preset compensation database, match the pressure compensation coefficient corresponding to the current injection stage, and generate a stepped pressurization sequence for mold clamping; At the same moment, based on the screw displacement amount obtained in real time, calculate the dynamic deviation between the melt propulsion speed and the preset injection curve, and generate a broken line correction function for the servo motor acceleration; According to the coupling relationship between the stepped pressurization sequence and the broken line correction function, inject corresponding pressure compensation signals and acceleration correction parameters in segments during the injection stage.

5. The fully automatic injection molding optimization method based on digital twin according to claim 1, wherein The step of calculating the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones and adjusting the output power gradient signal of each heating coil in the hot runner control includes: Monitor the temperature difference between adjacent temperature zones in real time, and extract the temperature zone combinations where the temperature difference exceeds the preset tolerance threshold; Based on the duration of the temperature difference and the temperature interval distance, generate a thermal interference transfer coefficient, and calculate the initial weight of the compensation coefficient in combination with the thermal inertia parameters of the heating coil; Compare the initial weights with the power gradient stability index in historical data to generate a segmented power adjustment instruction sequence for each heating coil.

6. The fully automatic injection molding optimization method based on digital twin according to claim 1, characterized in that The steps of transmitting the corrected parameter information to the device PLC for execution control through the industrial bus include: Convert the compensation data, servo motor acceleration curve, and power gradient signal into a control instruction set compatible with the industrial bus protocol, and encapsulate it into an instruction data packet synchronized with the timestamp; Divide the instruction execution priority according to the current working stage of the injection molding machine, and generate a segmented instruction distribution sequence that matches the timing of the injection and holding pressure stages; When sending the instruction sequence to the PLC through the industrial bus, synchronously inject the device status verification code to ensure the timing alignment of the control instruction and the actual operating status of the device.

7. The fully automatic injection molding optimization method based on digital twin according to claim 1, wherein, The steps of iteratively updating the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle include: In the next molding cycle, collect the product weight fluctuation value in real time through the weighing device, and extract the abnormal fluctuation interval where the weight difference between adjacent cycles exceeds the preset stability threshold; Calibrate the past timestamp of the abnormal fluctuation interval, and calculate the correlation weight between the compensation coefficient threshold and the weight deviation through the data information of the past timestamp; Write the correlation weight into the corresponding section of the parameter self-learning module of the digital twin model for correction.

8. An automatic injection molding optimization device based on digital twin, characterized in that, Include: An acquisition unit for collecting sensor data in real time through sensors installed on the mold clamping mechanism, screw, and hot runner. The sensor data includes the mold clamping force fluctuation value, screw displacement, and temperature data of each section; A model unit for inputting the sensor data into the digital twin model to construct a device dynamic response simulation, and synchronously comparing the offset between the actual mold clamping force and the preset pressure threshold; A first compensation unit for generating compensation data for the mold clamping pressure according to the offset, and dynamically correcting the servo motor acceleration curve in the injection stage based on the screw displacement; A second compensation unit for calculating the thermal interference compensation coefficient according to the temperature difference between adjacent temperature zones in the hot runner control, and adjusting the output power gradient signal of each heating coil; A correction unit for transmitting the corrected parameter information to the device PLC for execution control through the industrial bus, and iteratively updating the compensation coefficient threshold according to the product weight fluctuation value in the next molding cycle, where the parameter information includes the compensation data, the servo motor acceleration curve, and the output power gradient signal.

9. A computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, characterized in that, When the processor executes the computer program, it implements the steps of the digital twin-based full-automatic injection molding optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the digital twin-based full-automatic injection molding optimization method according to any one of claims 1 to 7.

Images