Insert injection molding control system, method, device and medium

Abstract

The embodiments of the present specification provide an insert injection molding control system, method, device and medium, the system including a preheating unit for controlling the preheating device to heat the insert; a conveying unit, configured to place the insert into a mold; a plastic melting unit, configured to heat and melt the plastic raw material into molten plastic; an injection unit, configured to control the injection molding device to inject the molten plastic into the mold; a dynamic control unit, configured to control the temperature control device to adjust the temperature of the insert in the mold; a monitoring unit, configured to collect monitoring sensor data; a processor, configured to: based on the monitoring unit, obtain actual injection molding temperature data and mold temperature data; based on the actual injection molding temperature data, the mold temperature data and the insert parameter data sequence, determine the preheating parameters, and send the preheating parameters to the preheating unit; based on the monitoring sensor data and the preheating parameters, determine the control parameters and send them to the dynamic control unit.

Description

Technical Field

[0001] The present invention relates to the field of injection molding technology, and in particular to an insert injection molding control system and method. Background Art

[0002] Insert molding refers to the manufacturing process of placing the insert into the mold in advance, and then injecting the molten plastic into the mold through the injection molding machine to surround and cover the insert, and finally forming an injection molded product. Insert molding can integrate components of different materials (for example, metal, ceramic, etc.) into plastic parts, thereby expanding the application range of plastic products.

[0003] During the insert molding process, the material type, thermal expansion coefficient and other parameters of the insert and the plastic are often different, which makes it difficult for the molten plastic to solidify evenly when cooling, resulting in cracks, shrinkage holes and other phenomena, resulting in a decrease in the yield of the product.

[0004] Therefore, it is necessary to provide an insert injection molding control system and method, which can preheat the insert in a targeted manner and timely adjust the temperature of the insert during the injection molding process, thereby improving the yield of the injection molded product. Summary of the invention

[0005] One or more embodiments of the present specification provide an insert injection control system. The system includes: a preheating unit, configured to control the preheating device to heat the insert; a conveying unit, configured to control the robotic arm to put the insert into the mold; a plastic melting unit, configured to heat and melt the plastic raw material into molten plastic; an injection unit, configured to control the injection device to inject the molten plastic into the mold; a dynamic control unit, configured to control the temperature control device to adjust the temperature of the insert in the mold; a monitoring unit, configured to collect monitoring sensor data through sensors deployed in the mold; a processor, configured to: based on the monitoring unit, obtain actual injection temperature data and mold temperature data; based on the actual injection temperature data, the mold temperature data and the insert parameter data sequence, determine the preheating parameters, and send the preheating parameters to the preheating unit; based on the monitoring sensor data and the preheating parameters, determine the control parameters, and send the control parameters to the dynamic control unit.

[0006] One or more embodiments of the present specification provide an insert injection molding control method, comprising: based on a monitoring unit, obtaining actual injection molding temperature data and mold temperature data; based on the actual injection molding temperature data, the mold temperature data and the insert parameter data sequence, determining a preheating parameter, and sending the preheating parameter to the preheating unit; based on the monitoring sensor data and the preheating parameter, determining a control parameter, and sending the control parameter to the dynamic control unit.

[0007] One or more embodiments of the present specification provide an insert molding control device, including a processor, wherein the processor is used to execute the aforementioned insert molding control method.

[0008] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the aforementioned insert injection molding control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is a module schematic diagram of an insert injection molding control system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of an insert injection molding control method according to some embodiments of this specification;

[0012] Figure 3 is an exemplary schematic diagram of a parameter effect evaluation model according to some embodiments of this specification;

[0013] Figure 4 is an exemplary flow chart for determining preheating parameters according to some embodiments of this specification;

[0014] Figure 5 is an exemplary flow chart for determining a controlled heating sequence according to some embodiments of the present specification. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0019] Figure 1 It is a module schematic diagram of an insert injection molding control system shown in some embodiments of this specification.

[0020] In some embodiments, Figure 1 As shown, the insert injection molding control system 100 may include a preheating unit 110 , a conveying unit 120 , a plastic melting unit 130 , an injection molding unit 140 , a dynamic control unit 150 , a monitoring unit 160 and a processor 170 .

[0021] The preheating unit 110 is configured as a device for preheating the insert. In some embodiments, the preheating unit 110 may include a preheating device and a heat preservation device.

[0022] The preheating device refers to a device for heating the insert. In some embodiments, the preheating device may include but is not limited to a resistance heater, an infrared heater, a hot air furnace, and the like.

[0023] In some embodiments, when the insert is heated to a desired temperature, the insert may be transferred to a heat preservation device for heat preservation. The heat preservation device may include, but is not limited to, a vacuum insulation box, a thermostat, and the like.

[0024] In some embodiments, the heat preservation device may have a plurality of heat preservation chambers for respectively preserving inserts at different temperatures.

[0025] The conveying unit 120 is configured as a device for transferring the insert to the mold. In some embodiments, the conveying unit 120 may include a robot arm, and the insert is placed into the mold by the robot arm.

[0026] The plastic melting unit 130 is configured as a device for melting plastic raw materials. In some embodiments, the plastic melting unit 130 may include a plastic melting machine.

[0027] The injection molding unit 140 is configured as a device for injecting molten plastic into a mold. In some embodiments, the injection molding unit 140 may include an injection molding device, such as a mechanical injection molding machine, a hydraulic injection molding machine, and the like.

[0028] The dynamic control unit 150 is configured as a device for adjusting the temperature of the insert in the mold. The dynamic control unit 150 can adjust the temperature of the insert in the mold based on the controlled heating sequence. In some embodiments, the dynamic control unit 150 can include a temperature control device.

[0029] In some embodiments, the temperature regulating device can adjust the temperature of the insert in the mold in a variety of ways. For example, the temperature regulating device can adjust the temperature of the insert by microwave heating, infrared heating, etc. For another example, the temperature regulating device can directly contact the heating element such as a resistance heating belt and a heating block with the exposed part of the insert to adjust the temperature of the insert by heat conduction. For another example, the temperature regulating device can adjust the temperature of the insert by a heating element (e.g., a heating wire, a heating tube, etc.) pre-buried in the insert.

[0030] The monitoring unit 160 is configured as a device for collecting monitoring sensor data. In some embodiments, the monitoring unit 160 may include a sensor. For example, a temperature sensor. The temperature sensor deployed in the mold can obtain mold temperature data and monitoring sensor data. The temperature sensor deployed in the injection unit 140 can obtain actual injection temperature data.

[0031] In some embodiments, the monitoring unit 160 further includes environmental sensors distributed in the environment where the insert molding is located. The environmental sensors can obtain environmental sensing data.

[0032] The processor 170 is configured to coordinate and coordinate information transmission and cooperation between various units and provide control management functions for the insert molding control system 100. In some embodiments, the processor may include but is not limited to a central processing unit (CPU), a field programmable gate array (FPGA), etc.

[0033] In some embodiments, the insert injection molding control system 100 may further include an energy recovery unit 180. The energy recovery unit 180 is configured as a device for recovering thermal energy.

[0034] In some embodiments, the energy recovery unit 180 may include one or more thermal energy collection modules and thermal energy storage modules. The thermal energy collection module is a module for obtaining thermal energy, and may include a heat pipe, a heat pump, etc. The thermal energy collection module may be installed on a device with a higher temperature, such as a preheating unit, an injection molding unit, and a mold, to collect waste heat.

[0035] The thermal energy storage module refers to a module for storing thermal energy. In some embodiments, it may include a water thermal storage tank, a phase change material thermal storage tank, etc. When the thermal energy collection module is a thermocouple, the energy storage module may also be a battery, a capacitor, etc.

[0036] In some embodiments, when heat energy demanding units such as the preheating unit 110, the plastic melting unit 130, and the dynamic control unit 150 need to consume heat energy, the energy recovery unit 180 can provide the heat energy stored in advance to the heat energy demanding units to reduce energy consumption.

[0037] In some embodiments of the present specification, by using an energy recovery unit, the waste heat released when the molten plastic, inserts, molds and other components are cooled can be recovered, and the recovered heat energy can be used in the heating process of the molten plastic, inserts, molds and other components, thereby effectively reducing the energy consumption of the insert injection molding control system 100, saving energy and improving the production cost of the production process.

[0038] For more information about the functions of each of the above units / devices, see Figure 2-5 and its related description.

[0039] In some embodiments of the present specification, based on the coordinated operation of various units in the insert injection molding control system 100, real-time and flexible adjustment of the insert temperature can be achieved, thereby further reducing the risk of cracking, shrinkage, etc. of the injection molded product.

[0040] It should be understood that Figure 1 The system and its units shown can be implemented in various ways. For example, the preheating unit 110 can preheat the insert first, and then transfer the insert to the inside of the mold through the conveying unit 120. The conveying unit 120 can also transfer the insert to the inside of the mold first, and then preheat the insert through the preheating unit 110.

[0041] It should be noted that the above description of the insert injection molding control system and its units is only for convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1The preheating unit 110, the conveying unit 120, the plastic melting unit 130, the injection unit 140, the dynamic control unit 150, the monitoring unit 160, the processor 170 and the energy recovery unit 180 disclosed in the specification can be different units in a system, or a unit can realize the functions of two or more of the above units. For example, each unit can share a storage module, or each unit can have its own storage module. Such variations are all within the protection scope of this specification.

[0042] Figure 2 is an exemplary flow chart of an insert molding control method according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps 210 to 230. In some embodiments, the process 200 may be executed by a processor.

[0043] Step 210: Acquire actual injection temperature data and mold temperature data based on the monitoring unit.

[0044] The actual injection temperature data refers to the actual temperature of the molten plastic when the injection molding process begins (i.e., the process of injecting the molten plastic into the mold). The mold temperature data refers to the actual temperature of the mold when the injection molding process begins.

[0045] In some embodiments, the processor may obtain injection temperature data based on a temperature sensor installed in the injection unit 140. The processor may obtain mold temperature data based on a temperature sensor installed in the mold.

[0046] Step 220 , based on the actual injection temperature data, the mold temperature data and the insert parameter data sequence, determine the preheating parameters, and send the preheating parameters to the preheating unit.

[0047] The insert parameter data sequence refers to the insert parameter data of each insert in a group of inserts. A group of inserts refers to all the inserts that need to be placed in the mold during one insert injection molding process.

[0048] The insert parameter data may reflect the inherent properties of the insert. In some embodiments, the insert parameter data may include insert material parameters, insert property parameters, and insert shape parameters.

[0049] The insert material parameter may include the material type of the insert. In some embodiments, the material type may include metal, ceramic, fiberglass, and other materials.

[0050] When the insert includes more than one material (eg, alloy, composite material, etc.), the insert material parameter may also include the proportion of each material.

[0051] The insert property parameters refer to parameters that reflect the properties of the insert itself. In some embodiments, the insert property parameters may include the thermal expansion coefficient of the insert, the thermal conductivity of the insert, the specific heat capacity of the insert, the melting point of the insert, etc. Among them, the melting point of the insert is the highest critical temperature at which the insert cannot maintain its own shape due to thermal deformation.

[0052] The insert shape parameters may reflect the shape configuration of the insert. In some embodiments, the insert shape parameters may include the shape, structure, and surface area of ​​the insert.

[0053] In some embodiments, the processor 170 can obtain the insert parameter data corresponding to different inserts in a variety of ways. For example, the processor can obtain the factory report, instruction manual and other materials of the insert, and obtain the insert parameter data of the insert therefrom. For another example, the processor can also detect the insert with the help of instruments and equipment (for example, material analyzer, thermal parameter measuring instrument, structure scanner, etc.), and determine the corresponding parameters in the test results as the insert parameter data of the insert. Repeat the measurement of the insert parameter data of all inserts in a group of inserts to obtain an insert parameter data sequence.

[0054] The preheating parameters refer to parameters for controlling the preheating unit 110 to perform a preheating operation. In some embodiments, the preheating parameters may include a target preheating temperature sequence. The target preheating temperature sequence may include a target preheating temperature for each insert in a group of inserts.

[0055] In some embodiments, in order to reduce the temperature difference between the plastic and the insert, the target preheat temperature of the insert should be close to or slightly lower than the injection temperature of the molten plastic.

[0056] In some embodiments, the preheating parameters can be determined based on a first preset table. The processor 170 can construct a first preset table based on historical injection temperature data, historical mold temperature data, and historical insert parameter data sequences. The first preset table contains the correspondence between different historical injection temperature data, historical mold temperature data, and historical insert parameter data sequences and different historical preheating parameters. The processor can determine the current preheating parameters by querying the first preset table based on the current actual injection temperature data, mold temperature data, and insert parameter data sequence.

[0057] In some embodiments, the processor 170 may also determine the preheating parameters based on at least one set of candidate preheating temperature sequences, environmental sensor data, actual injection temperature data, mold temperature data, and insert parameter data sequences. Figure 3 and its related parts.

[0058] In some embodiments, the processor 170 may also determine the preheating parameters based on the injection molding required temperature data. Figure 4 and its related contents.

[0059] Step 230, determining control parameters based on the monitoring sensor data and the preheating parameters, and sending the control parameters to the dynamic control unit.

[0060] The monitoring sensor data refers to the data of the temperature change of the injection molded product over time during the injection molding process and the cooling process after the injection molding is completed. In some embodiments, the monitoring sensor data may include insert monitoring sensor data and plastic monitoring sensor data. The plastic monitoring sensor data refers to the monitoring sensor data reflecting the temperature change process of the molten plastic. The monitoring sensor data can be expressed in the form of a sequence.

[0061] Taking plastic monitoring sensor data as an example, when the temperatures of the molten plastic at 2s, 4s, and 6s after the start of the injection molding process are 180°C, 170°C, and 160°C respectively, the plastic monitoring sensor data can be expressed as [(2s: 180°C), (4s: 170°C), (6s: 160°C)].

[0062] The control parameter refers to the control parameter for controlling the temperature of the insert. In some embodiments, the control parameter may include a control heating sequence. The control heating sequence includes heating control parameters of different inserts, and the heating control parameters may include insert heating power and corresponding insert heating time. The heating control parameters may be expressed in the form of a target preheating working parameter sequence. For specific expression methods, see Figure 3 Relevant part.

[0063] The control parameters can be determined based on the second preset table. The processor 170 can construct a second preset table based on historical monitoring sensor data and historical preheating parameters. The second preset table contains the correspondence between different historical monitoring sensor data, historical preheating parameters and different historical control parameters. The processor can determine the current control parameters by querying the second preset table based on the current monitoring sensor data and preheating parameters.

[0064] In some embodiments, the processor 170 may also determine the control parameters of the dynamic control unit based on the insert temperature sequence, the molten plastic temperature sequence, the insert parameter data, and the target preheating temperature of the insert to be controlled. Figure 5 Relevant part.

[0065] In some embodiments, when the dynamic control unit receives the control parameters, the temperature of the insert may be adjusted according to the requirements of the control parameters, thereby ensuring that the actual insert temperature of the insert at different time points matches the target insert temperature.

[0066] In some embodiments of the present specification, by determining control parameters to dynamically control the temperature of the insert, the temperature difference between the insert and the molten plastic can be effectively reduced during the injection molding process and the cooling process, thereby avoiding the occurrence of cracks caused by excessive temperature difference, thereby improving the quality of the injection molded product and the qualified rate of the production process.

[0067] Figure 3 It is an exemplary schematic diagram of a parameter effect evaluation model according to some embodiments of this specification.

[0068] In some embodiments, processor 170 may determine at least one set of candidate preheating temperature sequences 311 based on insert parameter data sequence 310 .

[0069] The candidate preheating temperature sequence 311 refers to the preheating temperature sequence to be selected. The composition of the candidate preheating temperature sequence 311 is similar to that of the target preheating temperature sequence. Figure 2 Related content.

[0070] In some embodiments, when the number of inserts contained in a group of inserts is greater than 1, the processor 170 may perform a clustering operation on the group of inserts based on the insert parameter data sequence through a clustering algorithm to obtain at least one cluster, each cluster containing at least one insert. Inserts in the same cluster have the same or similar insert parameter data. There may be multiple types of clustering algorithms, for example, the clustering algorithm may include K-Means clustering, density-based clustering method (DBSCAN), etc. There is no limitation on the types of clustering algorithms herein.

[0071] In some embodiments, when multiple clusters are obtained, the processor 170 may determine the candidate category preheating temperature for each cluster.

[0072] In some embodiments, for a cluster, the processor 170 may randomly select an insert as a representative insert. The processor may construct a preheating feature vector of the insert based on the insert parameter data and the actual injection molding temperature data of the insert. The elements in the preheating feature vector may correspond to the values ​​of the insert parameter data and the actual injection molding temperature data. For example, the preheating feature vector may be (a, b, c, d), where a represents the insert material parameter, b represents the insert property parameter, c represents the insert shape parameter, and d represents the actual injection molding temperature data.

[0073] The first vector database may include multiple reference vectors and corresponding reference preheating temperatures. Each reference vector may be constructed based on historical insert parameter data and historical actual injection temperature data. The reference vector is constructed in a similar manner to the preheating feature vector. The reference preheating temperature may be constructed based on the historical preheating temperature corresponding to the reference vector. When there are multiple historical preheating temperatures, there may be multiple reference preheating temperatures.

[0074] In some embodiments, the processor 170 can determine the candidate category preheating temperature based on the similarity between the preheating feature vector and multiple reference vectors in the first vector database. For example, a reference vector whose similarity with the preheating feature vector satisfies a similarity preset condition is used as a target vector, and the reference preheating temperature corresponding to the target vector is used as the candidate category preheating temperature representing the insert. The similarity preset condition can be set according to the situation. For example, the similarity is maximum, or the similarity is greater than a threshold, etc. For another example, the vector distance is minimum.

[0075] In some embodiments, for a cluster, the processor 170 may determine the candidate category preheating temperature representing the insert as the candidate preheating temperature of all inserts contained in the cluster. For example, for cluster 1 including insert 1, insert 2, and insert 3, a vector query is performed based on the preheating feature vector constructed for insert 2 to obtain two candidate category preheating temperatures: 60°C and 61°C. Then the candidate preheating temperatures of cluster 1 are 60°C and 61°C. The processor 170 may repeat the above operation to obtain the candidate preheating temperatures of all clusters in a group of inserts.

[0076] In some embodiments, after obtaining the candidate preheating temperatures of all clusters in a group of inserts, the processor 170 can obtain a candidate preheating temperature sequence corresponding to the group of inserts by a permutation and combination method. For example, when a group of inserts includes cluster 1 (insert 1, insert 2, insert 3) and cluster 2 (insert 4, insert 5), the candidate preheating temperatures of cluster 1 are 60°C and 61°C, and the candidate preheating temperatures of cluster 2 are 55°C and 56°C. Then the candidate preheating temperature sequence of the group of inserts can include four groups, namely (60°C, 60°C, 60°C; 55°C, 55°C), (60°C, 60°C, 60°C; 56°C, 56°C), (61°C, 61°C, 61°C; 55°C, 55°C), (61°C, 61°C, 61°C; 56°C, 56°C).

[0077] In some embodiments, the processor 170 determines the preheating parameters 350 based on at least one set of candidate preheating temperature sequences 311 , environmental sensor data 312 , actual injection temperature data 313 , mold temperature data 314 , and insert parameter data sequence 310 .

[0078] The environmental sensing data 312 may reflect the environmental characteristics of the insert molding area. In some embodiments, the environmental sensing data 312 may include the temperature and humidity of the insert molding area. The processor may obtain the environmental sensing data 312 through the monitoring unit 160.

[0079] In some embodiments, the processor 170 may determine the injection molding effect scores 340 of different candidate preheating temperature sequences through the parameter effect evaluation model 300 , and determine the preheating parameters 350 based on the injection molding effect scores.

[0080] The injection molding effect score can evaluate the quality of the insert injection molding. In some embodiments, the injection molding effect score can be expressed as a numerical value or a grade. The higher the injection molding effect score, the better the insert injection molding effect, and the less likely the injection molded product will have cracks, shrinkage holes, etc.

[0081] The parameter effect evaluation model 300 is a prediction model for determining the injection molding effect score. Figure 3 In some embodiments, the parameter effect evaluation model 300 includes an effect evaluation layer 330. The effect evaluation layer 330 may be a machine learning model, for example, any one or combination of a recurrent neural network (RNN) model or other custom model structures.

[0082] In some embodiments, the input of the effect evaluation layer 330 may include at least one set of candidate preheating temperature sequences 311, environmental sensor data 312, actual injection temperature data 313, mold temperature data 314, insert parameter data sequence 310, plastic data 315, and mold shape parameters 316. The output of the effect evaluation layer 330 may include an injection effect score 340 corresponding to the at least one set of candidate preheating temperature sequences 311.

[0083] For more descriptions of the candidate preheating temperature sequence 311 , the environmental sensor data 312 , the actual injection temperature data 313 , the mold temperature data 314 , the insert parameter data sequence 310 , and the injection effect score 340 , please refer to the relevant parts above.

[0084] The plastic data 315 may reflect the relevant characteristics of the molten plastic used for injection molding. In some embodiments, the plastic data 315 may include melt flow rate (MFR), shear viscosity, molten plastic density, thermal expansion coefficient, etc. The melt flow rate is an indicator to measure the fluidity of the plastic melt under a certain temperature and pressure; the shear viscosity is an indicator to measure the viscosity of the plastic melt under the action of shear force, and the shear viscosity can affect the fluidity of the plastic.

[0085] In some embodiments, the processor 170 may obtain materials such as factory reports and test reports of the plastic raw materials and obtain the plastic data 315 therefrom.

[0086] The mold shape parameters 316 may reflect the shape characteristics of the mold used for injection molding. In some embodiments, the mold shape parameters may include the injection molded product projection area, the number of mold cavities, the shape and size of the mold cavities / cores, the mold wall thickness, etc. In some embodiments, the processor 170 may obtain materials such as the factory report and the instruction manual of the mold and obtain the mold shape parameters 316 therefrom.

[0087] In some embodiments, the input of the effect evaluation layer 339 further includes insert position parameters 321 , insert function parameters 322 , insert thermal stability 323 , and injection speed 324 and injection pressure 325 .

[0088] The insert position parameter 321 may reflect the distribution position of the insert in the mold, and the insert position parameter may affect the flow path and flow pattern of the molten plastic, thereby affecting the temperature distribution during preheating and injection molding. In some embodiments, the insert position parameter 321 may be expressed as the coordinates of the insert in the mold.

[0089] The insert function parameter 322 can reflect the contact between the insert and the molten plastic. Since different inserts are connected to the molten plastic in different ways, for example, some inserts need to be subjected to force and need to form a relatively firm connection with the molten plastic, the influence of the insert function parameter needs to be considered. In some embodiments, the insert function parameter can be expressed as the maximum limit temperature when the molten plastic contacts the insert.

[0090] The thermal stability 323 of the insert can reflect the stability of parameters such as the structure and performance of the insert when heated. The injection speed 324 and the injection pressure 325 refer to the flow rate and pressure of the molten plastic when injected into the mold, respectively. In some embodiments, since the molten plastic is injected into the mold at a high flow rate and high pressure, the mold can be filled quickly, but the plastic around the insert may be cooled too quickly, forming cracks and impacting the insert. When the molten plastic is injected into the mold at a low flow rate and low pressure, the mold may not be filled in time. Therefore, it is necessary to consider the impact of the injection speed 324 and the injection pressure 325 on the injection effect score.

[0091] In some embodiments of the present specification, by inputting parameters such as insert position parameters 321, insert function parameters 322, insert thermal stability 323, injection speed 324, injection pressure 325 into the effect evaluation layer 330, the data richness of the machine learning model can be improved, thereby improving the versatility of the model and the accuracy of the prediction results.

[0092] In some embodiments, the processor 170 may train the effect evaluation layer 330 based on a large number of first training samples with first labels. In some embodiments, the first training samples may include sample preheating temperature sequences, sample environmental sensing data, sample actual injection temperature data, sample mold temperature data, sample insert parameter data sequences, sample plastic data, and sample mold shape parameters. In some embodiments, the first training samples may also include sample insert position parameters, sample insert function parameters, sample insert thermal stability, sample injection speed, and sample injection pressure.

[0093] In some embodiments, the first label may be a sample injection molding effect score corresponding to the sample preheating temperature sequence. In some embodiments, the first training sample may be obtained based on historical data, and the first label corresponding to the first training sample may be obtained by manual annotation. For example, the processor 170 may obtain a historical inspection report of a historical injection molding product, evaluate the historical injection molding product from multiple dimensions such as dimensional accuracy, surface quality, internal quality, and mechanical properties, and obtain a historical injection molding effect score. The historical injection molding effect score is determined as the first label corresponding to the group of sample preheating temperature sequences.

[0094] In some embodiments, the processor 170 can perform training based on the first training sample and the first label by various methods. For example, training can be performed based on the gradient descent method. As an example only, multiple first training samples with first labels can be input into the initial effect evaluation layer, a loss function can be constructed by the first label and the result of the initial effect evaluation layer, and the parameters of the initial effect evaluation layer can be iteratively updated based on the loss function. When the loss function meets the preset conditions, the model training is completed and a trained effect evaluation layer is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0095] In some embodiments, for a group of inserts, when determining the injection molding effect scores corresponding to at least one group of candidate preheating temperature sequences, the processor 170 may select the candidate preheating temperature sequence with the highest injection molding effect score and determine it as the preheating temperature sequence for the group of inserts.

[0096] In some embodiments, in response to a historical control frequency of an insert at a certain position being greater than a preset control frequency threshold, processor 170 may adjust the target preheating temperature of subsequent inserts fixed at the position based on the historical control frequency of the insert at the position.

[0097] The historical control frequency refers to the frequency of temperature control of the insert by controlling the heating sequence within the historical time range. The historical time range can be preset based on prior experience or manual input, for example, the past day, the past week, etc. For more information about controlling the heating sequence, see Figure 5 Relevant part.

[0098] The preset control frequency threshold is a threshold used to determine whether the historical control frequency is too high. In some embodiments, the preset control frequency threshold can be determined based on prior experience.

[0099] In some embodiments, the processor 170 can obtain a historical control heating sequence within a historical time range based on historical data. Determine the historical control frequency and temperature adjustment average value of the insert at this position based on the historical control heating sequence. The processor can query the third preset table based on the temperature adjustment average value to determine the preheating temperature adjustment value of the insert. The processor can construct a third preset table based on the historical temperature adjustment average value and the historical preheating temperature adjustment value. The third preset table contains a correspondence between different historical temperature adjustment average values ​​and different historical preheating temperature adjustment values. Exemplarily, when the historical temperature adjustment average value of insert 2 is +5°C, and the preheating temperature adjustment value obtained by querying the third preset table is +3°C, the target preheating temperature of insert 2 should be increased by 3°C based on the original value.

[0100] In some embodiments of the present specification, when the historical control frequency is greater than a preset control frequency threshold, the target preheating temperature of the insert subsequently fixed at the position is adjusted, which can effectively reduce the number of additional adjustments made using the control heating sequence, thereby avoiding the negative impact of frequent adjustments to the insert temperature during the injection molding process and the cooling process.

[0101] In some embodiments, the preheating parameters 350 also include a target preheating working parameter sequence; the processor is also configured to include an insert parameter data sequence, a preheating working parameter, and a candidate preheating temperature sequence, determine the preheating working parameter sequence corresponding to the candidate preheating temperature sequence, and determine the target preheating temperature sequence and the target preheating working parameter sequence based on the preheating working parameter sequence corresponding to the candidate preheating temperature sequence and the injection molding effect score.

[0102] The target preheating working parameter sequence refers to a sequence consisting of multiple target preheating working parameters. The target preheating working parameters refer to working parameters for preheating the insert. In some embodiments, the target preheating working parameters may include preheating duration and target preheating power. For example, the preheating power of 0-100s is 1000w, and the preheating power of 100-150s is 500w. Then the target preheating working parameter sequence may be [(0-100s: 1000w), ((100-150s: 500w)].

[0103] In some embodiments, the parameter effect evaluation model 300 may further include a preheating working layer (not shown in the figure). The processor may determine the preheating working parameters corresponding to the candidate preheating temperature sequence through the preheating working layer, and determine the target preheating working parameter sequence based on the preheating working parameters.

[0104] The preheating working layer refers to an estimation model for predicting preheating working parameters. In some embodiments, in some embodiments, the reading prediction model can be a machine learning model. For example, any one or combination of a neural network (NN) model or other customized model structures. The input of the preheating working layer may include the output of the effect evaluation layer.

[0105] In some embodiments, the input of the preheating layer may include the injection effect score 349, the candidate preheating temperature sequence 311, the insert parameter data sequence 310, the preheating working parameters, and the insert initial temperature sequence output by the effect evaluation layer. The output may include the preheating working parameters corresponding to the candidate preheating temperature sequence.

[0106] The preheating working parameters may reflect the preheating capability of the preheating device of the preheating unit 110. In some embodiments, the preheating working parameters may include the maximum preheating power of the preheating device, the preheating temperature control accuracy, and the preheating method (radiation heating, convection heating, conduction heating, etc.). The insert initial temperature sequence refers to a sequence of the insert initial temperatures at the beginning of the injection molding process.

[0107] In some embodiments, the processor 170 may train the preheating working layer based on a large number of second training samples with second labels. In some embodiments, the second training samples may include sample injection molding effect scores of sample inserts, sample preheating temperature sequences, sample insert parameter data sequences, sample preheating working parameters, and sample insert initial temperature sequences. The second label may be the sample preheating working parameters corresponding to the sample preheating temperature sequences.

[0108] In some embodiments, the second training sample may be acquired based on historical data, and the second label corresponding to the second training sample may be acquired by a simulation experiment (eg, a simulated experiment, an actual experiment, etc.).

[0109] For example, for a group of sample inserts, the processor 170 may adopt different target preheating working parameter sequences for preheating, and select a group of target preheating working parameter sequences with the best preheating effect as the second label. The best preheating effect may mean that the insert has the least deformation, breakage, etc. after preheating, or the overall temperature of the insert is the most uniform. The processor may obtain several groups of second training samples and corresponding second labels by performing simulation experiments on multiple groups of inserts.

[0110] In some embodiments, the processor 170 may perform training based on the second training sample and the second label by various methods. For specific training steps, please refer to the relevant content of the training effect evaluation layer.

[0111] In some embodiments, for a candidate preheating temperature sequence having an injection effect score greater than an injection effect score threshold, the processor 170 may determine a target preheating operating parameter sequence by selecting an indicator based on the preheating operating parameters corresponding to the candidate preheating temperature sequence.

[0112] The injection molding effect score threshold is a judgment threshold for judging whether the injection molding effect is qualified. When the injection molding effect score is less than or equal to the injection molding effect score threshold, it means that the candidate preheating temperature sequence has a large defect and does not have practical application value. Only when the injection molding effect score is greater than the injection molding effect score threshold, the candidate preheating temperature sequence has practical application value and can be determined as the target preheating working parameter sequence. In some embodiments, the injection molding effect score threshold can be determined based on prior experience or manual input.

[0113] The selection index can reflect the quality of the preheating working parameters. The selection index can be expressed as a numerical value, and the larger the numerical value, the better the preheating working parameters. In some embodiments, the selection index can be positively correlated with the injection molding effect score and negatively correlated with the preheating time and the heat energy consumption.

[0114] For example, the selection index can be obtained based on the following formula (1):

[0115] G=k1×A+k2×B+k3×C (1)

[0116] Among them, G represents the selection index, A represents the injection effect score, B represents the preheating time, and C represents the heat energy consumption. k1, k2, and k3 are coefficients, and k1 is greater than zero, and k2 and k3 are less than zero. The values ​​of coefficients k1, k2, and k3 can be determined based on prior experience; the heat energy consumption C can be determined based on the preheating time B and the corresponding preheating power.

[0117] In some embodiments, the processor may determine the preheating operating parameter sequence with the largest selection index as the target preheating operating parameter sequence.

[0118] In some embodiments of the present specification, during the preheating process of the insert, using a larger preheating power can reduce the preheating time, but it may cause the insert to heat up at an inconsistent rate, which may cause the insert to melt or deform. Using a smaller preheating power can ensure the overall temperature rise of the insert and reduce the temperature difference. However, it will result in more heat energy consumption and a longer preheating time. Therefore, it is necessary to determine the appropriate preheating working parameters through the preheating working layer, so as to obtain a suitable insert preheating scheme, while ensuring the preheating effect, while minimizing heat energy consumption and reducing the preheating time.

[0119] Figure 4 FIG. 1 is an exemplary flow chart for determining preheating parameters according to some embodiments of this specification. Figure 4As shown, the process 400 includes the following steps 410 to 430. In some embodiments, the process 400 may be executed by the processor 170.

[0120] Step 410 , determining the mold complexity based on the mold shape parameters.

[0121] The complexity of the mold can reflect the complexity of the mold. The more sharp angles, deep cavities, thin walls, and complex three-dimensional surfaces the mold contains, the more complex the mold is. The more complex the mold is, the better the fluidity of the molten plastic is required to obtain qualified injection molded products.

[0122] In some embodiments, the processor 170 can determine the complexity of the mold in a variety of ways. For example, the processor can analyze the mold structure through modeling and analysis software to obtain the mold complexity. Modeling and analysis software may include PTC Creo, Autodesk Revit, and BricsCAD, etc. For another example, the processor can determine the complexity of the mold by querying the mold database. The mold database contains several reference molds and corresponding reference complexities. The reference complexity can be determined based on manual annotation. When it is necessary to determine the complexity of the current mold, the processor can select the most similar reference mold in the mold database through similarity matching, and determine the reference complexity of the reference mold as the mold complexity of the current mold.

[0123] In some embodiments, mold complexity is also related to the number of inserts and the sequence of insert complexity. The processor 170 can determine the adjustment range of the mold complexity based on the number of inserts and the insert complexity, and perform an increase or decrease adjustment on the mold complexity.

[0124] The insert complexity sequence refers to a sequence of insert complexities corresponding to each insert in a group of inserts. In some embodiments, the processor 170 may determine the insert complexity with reference to the method for determining mold complexity described above, thereby obtaining the insert complexity sequence. The processor may count the insert complexity sequence to obtain the insert complexity mean.

[0125] In some embodiments, the processor 170 can also establish a fourth preset table based on the historical insert complexity sequence and the historical insert complexity mean. The fourth preset table includes the correspondence between the historical insert complexity mean, the historical insert complexity mean, and the adjustment amplitude and adjustment direction (for example, upward or downward) of different historical mold complexity. The processor can determine the adjustment amplitude of the current mold complexity according to the number of inserts of the current mold and the insert complexity mean by consulting the fourth preset table. The corresponding relationship can be that the more the number of inserts, the greater the insert complexity mean, and the greater the adjustment amplitude of the mold complexity.

[0126] In some embodiments of the present specification, the mold complexity is adjusted by the number of inserts and the sequence of insert complexity, so that the influence of the inserts contained in the mold can be considered while determining the mold complexity, thereby improving the accuracy of the mold complexity.

[0127] Step 420 , determining injection molding required temperature data based on plastic data, mold complexity, environmental sensor data, and mold shape parameters.

[0128] The injection molding required temperature data refers to the ideal temperature of the molten plastic during injection molding. In some embodiments, the injection molding required temperature needs to be higher than the plastic melting temperature to ensure that the plastic begins to soften and transform into a flowable molten state. The injection molding required temperature needs to be lower than the plastic decomposition temperature to ensure that the plastic does not begin to decompose and produce gas, thereby affecting product quality and safety.

[0129] In some embodiments, the processor 170 can construct an injection molding feature vector based on the plastic data 315, the mold complexity, the environmental sensor data 312, and the mold shape parameter 316. The method of constructing the injection molding feature vector is similar to the steps of constructing the preheating feature vector, which can be seen in Figure 3 Relevant part.

[0130] The second vector database includes a plurality of reference injection molding feature vectors and corresponding reference injection molding required temperature data. The second vector database can be constructed based on historical data or prior experience.

[0131] In some embodiments, the processor may use a reference injection molding feature vector whose similarity with the injection molding feature vector satisfies a preset similarity condition as a target vector, and use the reference injection molding required temperature data corresponding to the target vector as the injection molding required temperature data. For more information about the preset similarity condition, see Figure 3 part.

[0132] Step 430 : determining preheating parameters based on the injection molding required temperature data.

[0133] In some embodiments, the processor can determine the ideal temperature of the molten plastic based on the injection molding required temperature data. The processor can use the ideal temperature of the molten plastic as the actual injection molding temperature data, referring to Figure 3 Based on the actual injection temperature data, the effect evaluation layer 330 determines the relevant method of the preheating parameters to determine the target preheating temperature sequence in the preheating parameters.

[0134] In some embodiments of the present specification, a target preheating temperature sequence is determined based on injection molding required temperature data, so that the target preheating temperature can be obtained before plastic melting begins, and then the preheating process of the insert can be started, thereby achieving synchronization between the insert preheating process and the plastic melting process, thereby reducing waiting time and heat energy consumption.

[0135] Figure 5 is an exemplary flow chart for determining and regulating a heating sequence according to some embodiments of this specification. Figure 5 As shown, the process 500 includes the following steps 510 to 530. In some embodiments, the process 500 may be executed by the processor 170.

[0136] Step 510, determining the insert temperature sequence and the molten plastic temperature sequence based on the monitoring sensor data.

[0137] The insert temperature sequence may reflect how the insert temperature changes over time from the start of the injection molding process. The molten plastic temperature sequence may reflect how the molten plastic temperature changes over time from the start of the injection molding process. In some embodiments, the processor 170 may obtain monitoring sensor data through the monitoring unit 160 to determine the insert temperature sequence and the molten plastic temperature sequence.

[0138] Step 520, determining the insert to be regulated based on the temperature data sequence and the molten plastic temperature.

[0139] The insert to be regulated refers to the insert that needs to be temperature regulated by the dynamic control unit 150. In some embodiments, for an insert, the processor 170 can use the insert as the origin and determine the area within a preset radius as the target area. The processor can determine the temperature change rate of the insert based on the insert temperature sequence. The processor can determine the temperature change rate of the molten plastic in the target area based on the molten plastic temperature sequence.

[0140] When the difference between the temperature change rate of the insert and the temperature change rate of the molten plastic in the target area is greater than a preset difference threshold, the processor can determine the insert as an insert to be regulated. The preset radius and the preset difference threshold can be determined based on prior experience or historical data. The processor can determine all the inserts to be regulated included in a group of inserts by repeating the above method.

[0141] The difference can reflect the difference between two data. In some embodiments, the difference can be expressed as the absolute value of the difference. For example, | insert temperature change rate - molten plastic temperature change rate |. The difference can also be expressed as a relative error, that is, There is no limitation on the specific calculation method of the difference degree.

[0142] Step 530 , determining the control parameters of the dynamic control unit based on the insert temperature sequence of the insert to be controlled, the molten plastic temperature sequence, the insert parameter data, and the target preheating temperature.

[0143] In some embodiments, the processor 170 may determine the control parameters of the dynamic control unit through a temperature control model based on the temperature characteristic map.

[0144] The temperature characteristic map refers to a knowledge map that represents the temperature characteristics of the insert and the molten plastic. The temperature characteristic map can reflect the temperature changes of the insert and the molten plastic.

[0145] The temperature characteristic map may be composed of at least one node and at least one edge, and the node further includes a node attribute corresponding to the node. In some embodiments, the node includes an insert node and a sensor node. The insert node corresponds one-to-one to the insert, and the sensor node corresponds one-to-one to the temperature sensor inside the mold.

[0146] In some embodiments, the node attributes of the insert node may include insert temperature sequence, insert parameter data, target preheating temperature, whether it is an insert to be regulated, etc. The node attributes of the sensor node may include molten plastic temperature sequence, plastic data, injection temperature, etc.

[0147] For more information on plastic data, see Figure 3 For more information on target preheating temperature and injection temperature, see Figure 2 Relevant part.

[0148] In some embodiments, any two nodes are connected by an edge. The edge is an undirected edge, and the edge feature is the length of the edge. The length of the edge can reflect the path distance between the two nodes. The processor 170 can determine the path distance between the two nodes by a distance calculation method based on the coordinates of the insert or temperature sensor corresponding to different nodes. The distance calculation method can be a method such as the Pythagorean theorem.

[0149] The temperature control model is a prediction model for determining the control heating sequence. In some embodiments, the temperature control model can be a machine learning model. For example, any one or combination of a graph neural network (GNN) model or other custom model structures.

[0150] In some embodiments, the input of the temperature control model includes the temperature characteristic map of the insert to be controlled, the mold shape parameters and the environmental sensor data, and the output is the control heating sequence of the insert node of the insert to be controlled. For more information about environmental sensor data and mold shape parameters, please refer to Figure 3 For more information on controlling the heating sequence, see Figure 2 part.

[0151] In some embodiments, the processor 170 can obtain a temperature control model through training based on a large number of third training samples with third labels. The third training samples can include sample temperature characteristic maps, sample mold shape parameters, and sample environmental sensor data. The third label can be a sample control heating sequence corresponding to the third training sample.

[0152] In some embodiments, the third training sample can be obtained through historical data, and the third label can be obtained through simulation experiments. For example, the processor can perform multiple insert injection molding experiments, use multiple sets of different control heating sequences, heat the inserts of the same type and the same preheating temperature, and select a set of control heating sequences with the best heating effect as the third label. The temperature characteristic map, mold shape parameters and environmental sensor data of the insert injection molding experiment are used as the third training sample.

[0153] The processor may repeat the above experiment to obtain several groups of third training samples with third labels. The best heating effect may mean that the number of defects such as bubbles, cracks, holes, etc. in the injection molded product obtained by using the group of controlled heating sequences is the least, or the structural strength of the injection molded product is the highest. The method for determining the best heating effect may also include other methods, which are not specifically limited here.

[0154] The training steps of the temperature control model and the effect evaluation layer 330 of the parameter effect evaluation model 300 are similar, and can be seen in Figure 4 Relevant part.

[0155] In some embodiments of this specification, by using temperature characteristic maps to represent the temperature change characteristics of molten plastics in different inserts and different positions, the potential correlation between different information can be effectively mined in the complex data. By using the temperature control model to determine the control heating sequence in the control parameters, the data processing and data analysis capabilities of the model can be fully utilized to obtain accurate and reliable control parameters in a short time, thereby saving computing power consumption without delaying the production of injection molding products.

[0156] In some embodiments, the processor 170 may also sample the cooled injection molded product to obtain at least one sample plastic part based on the sampling parameters; determine casting quality data based on the at least one sample plastic part; and dynamically adjust and control the heating sequence based on the casting quality data.

[0157] Sampling parameters refer to parameters for sampling injection molded products. In some embodiments, the sampling parameters can be determined based on manual input or historical data. For example, sampling is performed on manually selected injection molded products. The injection molded products selected by sampling can be called sample plastic parts.

[0158] In some embodiments, the sampling parameters may include sampling frequency, sampling interval, and sampling quantity. The sampling frequency may reflect the frequency of sampling of injection molded products (e.g., every hour, every day), the sampling interval may reflect the sampling method for a single sampling, and the sampling quantity may reflect the number of sample plastic parts for a single sampling. For example, when the sampling interval is 5 pieces and the sampling quantity is 3, the processor 170 may extract the 1st, 6th, and 11th injection molded products to obtain 3 sample plastic parts.

[0159] In some embodiments, the sampling parameters can be determined based on a fifth preset table. The processor 170 can construct a fifth preset table based on the historical control frequency and the average poor quality frequency. The fifth preset table contains the correspondence between different historical control frequencies and average poor quality frequencies and different sampling parameters. The processor can determine the current sampling parameters by querying the fifth preset table based on the current historical control frequency and the average poor quality frequency. For more information about the historical control frequency, please refer to Figure 3 and its related contents.

[0160] The correspondence between different historical control frequencies and average inferior frequencies and different sampling parameters can be that the greater the average historical control frequency of all inserts included in the injection molded product and the greater the average inferior frequency, the more frequent the sampling frequency of the sampling parameters, the smaller the sampling interval, and the greater the number of samples. The average inferior frequency refers to the average frequency of inferior inserts in the injection molded product. The processor can determine the frequency of occurrence of different inferior inserts through manual inspection and other methods, and then determine the average inferior frequency of the injection molded product. Among them, when the position of the insert is offset, the insert is in poor contact with the plastic, etc. It can be regarded as an inferior insert.

[0161] In some embodiments of the present specification, sampling parameters are determined based on historical control frequency and average inferior quality frequency, so that when quality problems frequently occur in injection molded products, sample plastic parts can be frequently taken to facilitate subsequent troubleshooting and problem analysis; when the quality of injection molded products is good and stable, the frequency of taking sample plastic parts can be reduced, thereby saving costs and reducing waste caused by frequent sampling.

[0162] In some embodiments, when the at least one sample molded part is acquired, the processor 170 may determine casting quality data.

[0163] The casting quality data can reflect the overall injection molding quality of the sample plastic part. The casting quality data can be represented by a score. In some embodiments, the fewer defects (i.e., cracks, deformations, holes, etc.) of the sample plastic part, the tighter the connection between the sample plastic part and the insert. The better the score of the casting quality data. The casting quality data of the sample plastic part can be determined by methods such as manual re-inspection.

[0164] In some embodiments, when the casting quality data is less than the frequency of the preset casting quality data and exceeds the preset frequency threshold, the processor 170 can dynamically adjust the control heating sequence based on the casting quality data. For example, the processor determines the control amplitude of the control heating sequence based on querying the sixth preset table. The processor can construct a sixth preset table based on historical casting quality data and historical control amplitudes. The sixth preset table contains the correspondence between different historical casting quality data and different historical control amplitudes. The correspondence between different historical casting quality data and different historical control amplitudes can be: the worse the historical casting quality data, the larger the historical control amplitude.

[0165] In some embodiments of this specification, the casting quality data of the sample plastic parts are obtained by sampling, and the heating sequence is dynamically adjusted based on the casting quality data. The quality fluctuation of the injection molded product can be timely known during the production process, so that dynamic adjustments can be made in time to effectively improve the product yield of the injection molding production process.

[0166] In some embodiments, the control parameters further include injection speed control parameters and injection pressure control parameters; the processor 170 can also control the injection speed control parameters and injection pressure control parameters based on the insert temperature sequence and the molten plastic temperature sequence.

[0167] The injection speed control parameter refers to the parameter used to control the injection speed. The injection pressure control parameter refers to the parameter used to control the injection pressure. The injection speed / injection pressure control parameter can be expressed as the control range and control direction of the injection speed / injection pressure. For example, increase by 3% or decrease by 5%.

[0168] In some embodiments, the processor can obtain the difference of the insert based on the insert temperature sequence and the molten plastic temperature sequence. When the difference is greater than a preset difference threshold, the processor can determine the adjustment range of the injection speed and the injection pressure based on the difference. For example, the greater the difference, the greater the adjustment range of the injection speed and the injection pressure. For more information about the difference, please refer to the above.

[0169] In some embodiments of the present specification, when the difference is too large, it means that the insert and the molten plastic are too large. At this time, if a higher injection speed and injection pressure are used, the shear rate of the melt in the mold will increase, thereby generating more shear heat. The temperature rise of the molten plastic is accelerated, thereby aggravating the temperature difference between the insert and the molten plastic, resulting in performance degradation of the insert product. Therefore, the injection speed control parameters and injection pressure control parameters of the injection speed and injection pressure can be determined based on the difference. Thereby minimizing the impact of the injection speed and injection pressure on the performance of the insert product.

[0170] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0171] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0172] In addition, unless explicitly stated in the claims, the order of processing elements and sequences, the use of alphanumeric characters, or the use of other names in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0173] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0174] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0175] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0176] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An insert injection molding control system, characterized in that: The system comprises: a preheating unit configured to control the preheating device to heat the insert; a conveying unit configured to control the robot arm to place the insert into the mold; A plastic melting unit, configured to heat and melt the plastic raw material into molten plastic; An injection unit configured to control an injection device to inject the molten plastic into the mold; a dynamic control unit configured to control a temperature control device to adjust the temperature of the insert in the mold; A monitoring unit is configured to collect monitoring sensor data through sensors deployed in the mold; and to obtain environmental sensor data based on environmental sensors; The processor is configured as: Based on the monitoring unit, actual injection temperature data and mold temperature data are obtained; Based on the insert parameter data sequence, at least one set of candidate preheating temperature sequences is determined; based on the at least one set of candidate preheating temperature sequences, the environmental sensor data, the actual injection temperature data, the mold temperature data and the insert parameter data sequence, the preheating parameters are determined, and the preheating parameters are sent to the preheating unit; or based on the mold shape parameters, the mold complexity is determined; based on the plastic data, the mold complexity, the environmental sensor data and the mold shape parameters, the injection molding required temperature data is determined, and based on the injection molding required temperature data, the preheating parameters are determined and sent to the preheating unit; Determining an insert temperature sequence and a molten plastic temperature sequence based on the monitoring sensor data; Determining the insert to be regulated based on the temperature data sequence and the temperature of the molten plastic; Based on the insert temperature sequence, the molten plastic temperature sequence, the insert parameter data and the target preheating temperature of the insert to be regulated, the regulation parameters are determined and sent to the dynamic regulation unit.

2. An insert injection molding control method, characterized in that: Executed by a processor of the insert molding control system according to claim 1, comprising: Based on the monitoring unit, the actual injection temperature data and mold temperature data are obtained; Determine preheating parameters based on the actual injection temperature data, the mold temperature data and the insert parameter data sequence, and send the preheating parameters to the preheating unit; Based on the monitoring sensor data and the preheating parameters, control parameters are determined, and the control parameters are sent to the dynamic control unit.

3. The method according to claim 2, characterized in that The determining of the preheating parameters based on the actual injection temperature data, the mold temperature data and the insert parameter data sequence comprises: Determining at least one set of candidate preheating temperature sequences based on the insert parameter data sequence; Preheating parameters are determined based on the at least one set of candidate preheating temperature sequences, the environmental sensor data, the actual injection temperature data, the mold temperature data, and the insert parameter data sequence.

4. The method according to claim 3, characterized in that The method further comprises: Determine the complexity of the mold based on the mold shape parameters; Determining injection molding required temperature data based on plastic data, the mold complexity, environmental sensor data, and the mold shape parameters; The preheating parameters are determined based on the injection molding required temperature data.

5. The method according to claim 2, characterized in that: The determining of the control parameters based on the monitoring sensor data and the preheating parameters includes: Determining an insert temperature sequence and a molten plastic temperature sequence based on the monitoring sensor data; Determining the insert to be regulated based on the temperature data sequence and the temperature of the molten plastic; The control parameters of the dynamic control unit are determined based on the insert temperature sequence, the molten plastic temperature sequence, the insert parameter data and the target preheating temperature of the insert to be controlled.

6. An insert injection molding control device, comprising a processor, wherein the processor is used to execute the insert injection molding control method according to any one of claims 2 to 5.

7. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the insert injection molding control method according to any one of claims 2 to 5.

Images