A mold temperature change control system, method, device and storage medium

Abstract

The embodiments of the present application provide a mold temperature change control system, method, device and storage medium. The mold temperature change control system includes: an injection molding device, a processor, a controller and a storage device; the injection molding device includes an injection mold and multiple heating units; the injection mold is connected to multiple heating units; the multiple heating units are configured to heat the injection mold; the processor is configured to: obtain mold information, raw material information and heating unit information from the storage device; determine mold partition information based on the mold information; determine target temperature distribution based on the raw material information and the mold partition information; and determine heating control parameters based on the target temperature distribution and the heating unit information, and send the heating control parameters to the controller; the controller is configured to control the multiple heating units to heat the injection mold with the heating control parameters.

Description

Technical Field

[0001] The present application relates to the field of injection molding temperature control technology, and in particular to a mold temperature change control system, method, device and storage medium. Background Art

[0002] Injection molding, also commonly known as injection molding, is a technology widely used in plastic processing. Its core is to heat thermoplastic or thermosetting plastics to a molten state, accurately inject them into the injection mold, and finally form the desired plastic parts through cooling and hardening.

[0003] During the injection molding process, the temperature of the injection mold will directly affect the plastic die, the shaping of the plastic part, the molding cycle and the quality of the plastic part. However, due to the characteristics of different plastic materials, melt fluidity, injection mold structure and other reasons, during injection molding, it is not necessary to keep the temperature of each position of the injection mold consistent, but it is necessary to maintain different temperatures according to the actual situation. At the same time, unreasonable temperatures at each position of the injection mold will lead to problems such as insufficient filling of the cavity, surface defects of the product, mold sticking and extended molding cycle.

[0004] Therefore, it is necessary to provide a mold temperature change control system and method that can accurately determine the target temperature distribution of the mold, thereby determining the heating control parameters to control the temperature of each heating unit on the injection mold to heat the injection mold, so that the injection mold can have the best molding effect and save heating resources. Summary of the invention

[0005] One or more embodiments of the present specification provide a mold temperature change control system, the system comprising: an injection molding device, a processor, a controller and a storage device; the injection molding device comprises an injection mold and a plurality of heating units; the injection mold is connected to the plurality of heating units; the plurality of heating units are configured to heat the injection mold; the processor is configured to: obtain mold information, raw material information and heating unit information from the storage device; determine mold partition information based on the mold information; determine a target temperature distribution based on the raw material information and the mold partition information; and determine heating control parameters based on the target temperature distribution and the heating unit information, and send the heating control parameters to the controller; the controller is configured to control the plurality of heating units to heat the injection mold with the heating control parameters.

[0006] One or more embodiments of the present specification provide a mold temperature change control method, the method is executed by a processor of the mold temperature change control system; the system includes an injection molding device, a processor, a controller and a storage device; the injection molding device includes an injection mold and a plurality of heating units; the injection mold is connected to the plurality of heating units; the plurality of heating units are configured to heat the injection mold; the controller is configured to control the plurality of heating units to heat the injection mold with heating control parameters; the method includes: obtaining mold information, raw material information and heating unit information from the storage device; determining mold partition information based on the mold information; determining a target temperature distribution based on the raw material information and the mold partition information; and determining the heating control parameters based on the target temperature distribution and the heating unit information, and sending the heating control parameters to the controller.

[0007] One or more embodiments of this specification provide a mold temperature change control device. The device includes at least one storage medium and at least one processor, the at least one storage medium is used to store computer instructions; the at least one processor is used to execute the computer instructions to implement the mold temperature change control method described in the above embodiment.

[0008] One or more embodiments of the present specification provide a computer-readable storage medium. The storage medium stores computer instructions, and when the computer instructions are executed by a computer, the mold temperature change control method described in the above embodiment is implemented. 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 diagram of a mold temperature change control system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a mold temperature change control method according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart of determining an updated temperature distribution according to some embodiments of this specification;

[0013] Figure 4 is a schematic diagram of a first prediction model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] Figure 1 It is a module diagram of a mold temperature change control system according to some embodiments of this specification.

[0019] like Figure 1 As shown, the mold temperature change control system 100 may include an injection molding device 110 , a processor 120 , a controller 130 and a storage device 140 .

[0020] In some embodiments, the injection molding device 110 includes an injection mold 111 and a plurality of heating units 112 , and the injection mold 111 may be connected to the plurality of heating units 112 .

[0021] Injection molds refer to tools used for injection molding.

[0022] In some embodiments, a plurality of heating units 112 are configured to heat the injection mold 111 .

[0023] In some embodiments, the processor 120 is configured to obtain mold information, raw material information, and heating unit information from the storage device 140; determine mold partition information based on the mold information; determine the target temperature distribution based on the raw material information and the mold partition information; and determine the heating control parameters based on the target temperature distribution and the heating unit information, and send the heating control parameters to the controller 130.

[0024] In some embodiments, the processor 120 is further configured to determine mold partition information based on the mold information, the raw material information, and the production parameters; and determine the target temperature distribution based on the raw material information, the production parameters, and the mold partition information.

[0025] In some embodiments, the processor 120 is further configured to obtain target injection molding process information of a preset time; and determine to update the temperature distribution based on the target injection molding process information, raw material information, production parameters and target temperature distribution.

[0026] In some embodiments, the processor 120 is further configured to determine a core heating zone based on the mold partition information and the target temperature distribution; and determine a heating control parameter based on the core heating zone, the target temperature distribution and the heating unit distribution.

[0027] In some embodiments, the controller is configured to control a plurality of heating units to heat the injection mold with heating control parameters.

[0028] In some embodiments, the storage device is configured to store information. For example, the storage device can store mold information, raw material information, heating unit information, etc.

[0029] For more information on injection molding equipment, processors, controllers, and storage devices, see Figure 2-Figure 4 See the relevant instructions in .

[0030] It should be noted that the above description of the mold temperature change control system and its modules is only for the convenience of description and cannot 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 1 The injection molding device 110, processor 120, controller 130 and storage device 140 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are within the scope of protection of this specification.

[0031] Figure 2200 is an exemplary flow chart of a mold temperature change control method according to some embodiments of this specification. In some embodiments, process 200 may be executed by a processor of the mold temperature change control system 100. Figure 2 As shown, the process 200 includes the following steps 210 to 260.

[0032] Step 210, obtaining mold information, raw material information and heating unit information from a storage device.

[0033] For information about storage devices, see Figure 1 See the relevant instructions in .

[0034] Mold information refers to information related to injection molds. For instructions on injection molds, see Figure 1 See the relevant instructions in .

[0035] In some embodiments, the mold information may include at least one of the size, structure, and properties of the injection mold.

[0036] In some embodiments, the size of the injection mold may include the outer dimensions of the injection mold, the cavity dimensions, and the wall thickness of each part.

[0037] The overall dimensions of an injection mold refer to the overall appearance dimensions of the injection mold, such as the length, width, and height of the injection mold.

[0038] The cavity size of an injection mold refers to the size of the area inside the injection mold used to mold the product, such as the length, width, and depth of the cavity.

[0039] In some embodiments, the processor may retrieve stored mold information from a storage device.

[0040] Raw material information refers to information about the material used for injection molding. In some embodiments, the raw material information may include the raw material type, the temperature and viscosity of the raw material melt, etc. The raw material type may include polyethylene, polypropylene, etc.

[0041] In some embodiments, the processor may retrieve stored raw material information from a storage device.

[0042] The heating unit information refers to information related to the heating unit, wherein the heating unit is arranged in the interlayer of the injection mold wall or at different positions outside the mold wall. The heating unit can be used to locally heat the injection mold. One heating unit can correspond to one electric heating element.

[0043] A large number of heating units are arranged in the interlayer of the injection mold wall or outside the mold wall. By controlling different temperatures of different heating units, the effect of controlling different areas on the injection mold to have different temperatures can be achieved.

[0044] In some embodiments, the heating unit information may include heating unit distribution and heating unit properties.

[0045] The distribution of heating units refers to the distribution of heating units in the injection mold wall sandwich or outside the injection mold wall.

[0046] The distribution of the heating units can be characterized by a sequence consisting of the relative positions (eg, spatial distance, orientation, etc.) of each heating unit on the injection mold and the center point of the injection mold.

[0047] The center point of the injection mold may be a preset position, such as the geometric center, center of gravity, etc. of the injection mold.

[0048] In some embodiments, the heating unit attributes may include at least one of a heating power range, a heating area range, and a heating temperature range of each heating unit on the injection mold. The heating power range refers to the range of heating power that can be used by the heating unit. The heating area range refers to the physical range that can be reached when each heating unit on the injection mold is independently heated to a specified temperature. The heating temperature range refers to the temperature range that the heating unit can heat, such as 50°C-150°C.

[0049] In some embodiments, the heating power range, heating area range, and heating temperature range of each heating unit on the injection mold may be the same.

[0050] In some embodiments, the processor may retrieve stored heating unit information from a storage device.

[0051] In some embodiments, when mold information of an injection mold is available but a heating unit has not yet been arranged on the injection mold, the processor can also use the following steps 211-212 to determine the distribution of the heating units, so as to arrange the heating units in the interlayer of the injection mold wall or outside the injection mold wall according to the distribution of the heating units.

[0052] Step 211 , based on the mold information of the existing injection mold, multiple different raw material information and multiple different production parameters, multiple mold partition information is confirmed.

[0053] In some embodiments, a plurality of different raw material information and a plurality of different production parameters are set for an existing injection mold.

[0054] In some embodiments, the production parameters may include speed, pressure, etc. of injecting the molding solution.

[0055] In some embodiments, multiple different raw material information and multiple different production parameters can be preset by technical personnel in this field based on experience. For example, multiple different raw material information and multiple different production parameters can be multiple different raw material information and multiple different production parameters commonly used for existing injection molds.

[0056] The mold partition information refers to information related to the partitions of the injection mold. In some embodiments, the mold partition information may include mold partitions and partition attributes.

[0057] In some embodiments, the partition attributes may include the area of ​​each partition in the mold partition, whether each partition is a special area, etc.

[0058] In some embodiments, after the mold partitioning is completed, the processor may determine the partition attributes according to the actual conditions of each mold partition.

[0059] Mold partitioning refers to the partitioning result of the injection mold obtained after the injection mold wall is divided into regions. For example, mold partitioning includes dividing the injection mold into 3 partitions.

[0060] In some embodiments, the mold partitions may be represented by the partitions of the injection mold on the 3D model.

[0061] In some embodiments, the processor may determine multiple mold partition information using the following steps 2111 to 2113:

[0062] Step 2111 : dividing the injection mold surface into a plurality of sub-surface regions based on a first preset rule.

[0063] In some embodiments, the first preset rule may be to divide the injection mold wall into a plurality of sub-surface regions based on the shape of the injection mold. For example, if the shape of the injection mold is a regular cuboid, each face of the cuboid may be regarded as a sub-surface region.

[0064] In some embodiments, the first preset rule may also be to evenly divide the surface of the injection mold into 1 cm×1 cm cells, divide a preset number (e.g., 100) of adjacent cells into a group of adjacent cells, and determine a group of adjacent cells as a sub-surface area.

[0065] Step 2112, randomly combining known mold information, multiple different raw material information and multiple different production parameters to obtain multiple combinations.

[0066] Each combination includes mold information of an existing injection mold, raw material information and a production parameter. Between different combinations, the mold information in each combination is the same, and at least one of the raw material information and the production parameter is different.

[0067] Step 2113, based on the multiple combinations, determine the mold partition information corresponding to each combination.

[0068] In some embodiments, for the data corresponding to each of the multiple combinations, the processor may use Figure 3 The method in step 310 predicts the mold partition information corresponding to each combination, see Figure 3 Description of step 310.

[0069] Step 212: Determine the distribution of heating units based on the multiple mold partition information corresponding to the multiple combinations.

[0070] In some embodiments, the processor determines a specific implementation method of heating unit distribution based on multiple mold partition information corresponding to multiple combinations, which can be implemented by the following steps 2114-2115:

[0071] Step 2114, each sub-surface region is sequentially compared with the mold partitions in all the mold partition information to determine how many partitions each sub-surface region is divided into at most, and the maximum partition result corresponding to each sub-surface region is used as the target mold partition of the corresponding sub-surface region. The target mold partition refers to the final mold partition.

[0072] For example, if the same sub-surface area includes two partitions in one mold partition and three partitions in another mold partition, then this sub-surface area is divided into three partitions at most, and the three partitions mean that in the actual injection molding process, the three partitions of this sub-surface area may have different temperature requirements. Therefore, it is necessary to ensure that there is at least one heating unit in each of the three partitions to achieve different temperatures.

[0073] Step 2115 , determining the distribution of heating units in each sub-surface region according to the target mold partition corresponding to each sub-surface region.

[0074] Just as an example, taking a sub-surface region as an example, determining the distribution of heating units in the sub-surface region includes the following steps k1 to k4:

[0075] Step k1, determining the area of ​​each partition in a sub-surface region according to a target mold partition of the sub-surface region.

[0076] Step k2, determining the number of heating units required for each partition according to the area size of each partition and the heating area range of the heating unit.

[0077] In some embodiments, the heating area range of all heating units may be a known fixed value.

[0078] For example, if the area of ​​each zone is 15 square centimeters and the heating area of ​​a heating unit is 10 square centimeters, then this zone requires at least two heating units to meet the heating demand.

[0079] Step k3, based on the determined number of heating units, evenly distribute the heating units in each partition, thereby determining the distribution of the heating units in the partition.

[0080] Step k4, in the same manner as the aforementioned steps k1 to k3, determine the distribution of heating units in other subareas of the sub-surface area, and obtain the distribution of all heating units in the sub-surface area after integration.

[0081] In some embodiments, the processor may also determine the heating unit distribution of other sub-surface areas on the injection mold in the same manner as the aforementioned steps k1 to k4, and obtain the heating unit distribution of the entire injection mold surface after integration.

[0082] In some embodiments, when mold information of an injection mold is available but a heating unit has not been arranged on the injection mold, the processor may also determine the distribution of the heating units based on multiple mold partition information and target temperature distribution. The partition information of multiple molds may be determined using the aforementioned steps 2111 to 2113.

[0083] The target temperature distribution refers to a sequence formed by arranging the target heating temperatures corresponding to each partition in the mold partition information in a preset order. The target heating temperature refers to the final temperature to be reached by the heating unit when heating the partition.

[0084] In some embodiments, the target temperature profile includes a target heating temperature for each of the mold zones.

[0085] For a description of how to determine the target temperature distribution, please refer to the description in step 230 below.

[0086] The preset order can be preset by those skilled in the art based on experience. For example, the preset order can be arranged from top to bottom or from left to right according to the positions of the partitions in the mold partition, and then the target heating temperatures corresponding to the partitions are arranged in sequence according to the order of the arranged partitions.

[0087] For another example, those skilled in the art may number each partition in the mold partition, and arrange the target heating temperatures corresponding to each partition according to the sequence of the numbers.

[0088] In some embodiments, the processor may obtain the target heating temperature of each partition in the mold partition based on the information of multiple mold partitions and the target temperature distribution, and set heating units with different heating temperature ranges in different partitions based on the target heating temperature requirements of each partition, thereby determining the distribution of heating units. For example, if the predicted target heating temperature range of a certain partition is 80°C-100°C, the processor may set a heating unit with a heating temperature range of 80°C-100°C in the partition.

[0089] In some embodiments of the present specification, by predicting multiple mold partition information based on the same type of mold information, different raw material information and different production parameters, and then comprehensively considering the multiple mold partition information to predict the heating unit distribution, the accuracy of the final predicted heating unit distribution can be improved.

[0090] In addition, since the heating unit costs for different heating temperature ranges are different, by determining the appropriate heating unit distribution in advance based on the predicted multiple mold partition information and target temperature distribution, costs can be effectively saved.

[0091] Step 220: Determine mold partition information based on the mold information.

[0092] For instructions on mold partition information, please refer to the instructions in step 211 above.

[0093] In some embodiments, the processor may also determine the mold partition information based on the mold information by a second preset rule.

[0094] In some embodiments, the second preset rule may be to divide each special area on the injection mold structure into a partition, and the remaining areas into a partition. The special area may include a curved surface, a step, a hole groove, a narrow channel, etc. on the injection mold structure.

[0095] In some embodiments, the second preset rule can also be to determine the first target number of partitions based on the size of the injection mold and / or the properties of the injection mold; divide each special area on the injection mold structure into a partition, and the remaining areas into a partition; and further divide each special area into multiple partitions based on the size of the injection mold and / or the properties of the injection mold; and / or further divide the remaining areas until the first target number of partitions is obtained.

[0096] The first target partition number refers to the total number of partitions into which the injection mold is partitioned.

[0097] For example, the second preset rule may be that the larger the size of the injection mold, the more target partitions are preset. For another example, the second preset rule may be that different properties of different injection molds correspond to different preset numbers of partitions. Different preset numbers of partitions corresponding to different properties of different injection molds may be preset by those skilled in the art based on experience.

[0098] As an example only, the implementation method of further dividing each special area into multiple partitions based on the size of the injection mold and / or the properties of the injection mold in the second preset rule can be: if a groove-type special area is further divided, since the groove-type special area will have a groove bottom area and surrounding areas, considering the thermal conductivity of the injection mold properties and the thickness of the groove bottom and the groove wall, there is a certain difference (generally the groove bottom is thicker) in the thermal conductivity of the groove bottom area and the surrounding areas of the groove-type special area. If the thermal conductivity of the groove bottom area and the surrounding areas of the groove-type special area are different, the groove bottom area and the surrounding areas of the groove-type special area can be divided into different partitions.

[0099] The implementation method of further dividing the remaining area into multiple partitions in the second rule may be: further dividing the remaining area by random division, division according to area, etc.

[0100] In some embodiments, the processor may also determine mold partition information based on mold information, raw material information, and production parameters. Figure 3 Description of step 310.

[0101] Step 230 : determining a target temperature distribution based on the raw material information and the mold partition information.

[0102] For a description of the target temperature distribution, please refer to the description in the above step 2115.

[0103] In some embodiments, the processor may determine the target temperature distribution based on the raw material information and the mold partition information through a first preset comparison table. The first preset comparison table contains a correspondence between the reference raw material information and the reference mold partition information and the reference target temperature distribution. The first preset comparison table may be constructed based on prior knowledge or historical data. In some embodiments, the reference target temperature distribution includes a reference target heating temperature for each partition in the mold partition.

[0104] In some embodiments, the processor may also determine the target temperature distribution based on the raw material information, production parameters, and mold partition information. Figure 3 Description of step 320.

[0105] Step 240 , determining heating control parameters based on the target temperature distribution and the heating unit information, and sending the heating control parameters to the controller.

[0106] The heating control parameter refers to a parameter related to the heating unit. In some embodiments, the heating control parameter may include a heating temperature of the heating unit.

[0107] In some embodiments, the processor may set the heating temperature of each heating unit on the heating unit distribution to the target heating temperature of the heating unit of the corresponding partition on the target temperature distribution based on the target temperature distribution and the heating unit distribution in the heating unit information.

[0108] In some embodiments, the processor may send the heating control parameters to the controller via a network.

[0109] In some embodiments, the heating unit information may include a heating unit distribution, and the processor may further determine the heating control parameters using the following steps 241-242:

[0110] Step 241, determining the core heating zone based on the mold partition information and the target temperature distribution.

[0111] The core heating zone refers to an area that can only be heated to the target heating temperature of the zone by the heating unit (eg, electric heating element) of the corresponding zone.

[0112] For example, if the injection mold includes four partitions, namely partition A, partition B, partition C and partition D, partition A is adjacent to the other three partitions (partition B, partition C and partition D), and the target heating temperatures of partition B, partition C and partition D are all lower than the target heating temperature of partition A, that is to say, partition A can only rely on the electric heating elements within the partition to reach the target heating temperature, but cannot rely on the heat conduction of partition B, partition C and partition D to reach the target heating temperature of partition A, then partition A is the core heating zone.

[0113] At the same time, since the temperature of partition A is the highest, partition A can conduct a certain amount of heat to partition B, partition C and partition D, so that partition B, partition C and partition D reach a certain temperature, but may not be as high as the target heating temperature of partition A. When the target heating temperature of a partition is low, the heat conducted from partition A can just meet the target heating temperature requirement of the partition, then the part of the partition that receives the heat conducted from partition A does not need to turn on the corresponding heating unit. It should be noted that the target heating temperatures of adjacent partitions will not differ greatly, so the heat conducted from adjacent partitions will be within a certain limit and can meet the target heating temperature requirement of the partition. At the same time, this solution does not consider that the actual temperature of the partition caused by the heat conducted may slightly exceed the target heating temperature of the partition, and based on experiments, the deviation of this part of the actual temperature from the target heating temperature of the partition will not have a significant impact on the injection molding effect of the injection mold. For the specific implementation process of this part, please refer to the description in step 242 below.

[0114] In some embodiments, the processor may, based on the mold partition information and the target temperature distribution, take all partitions whose target temperatures are greater than or equal to all adjacent partitions as core heating zones.

[0115] Specifically, the processor may implement the following steps 2411 to 2413:

[0116] Step 2411, arbitrarily select a partition as the current partition, and compare the target heating temperature of the current partition with the target heating temperature of the adjacent partitions in turn. If the target heating temperature of the current partition is greater than or equal to the target heating temperatures of all adjacent partitions of the current partition, the current partition is determined to be the core heating zone.

[0117] Step 2412, performing the comparison operation of step 2411 above on all partitions on the injection mold until all core heating areas are screened out.

[0118] Step 242, determining heating control parameters based on the core heating zone, the target temperature distribution and the heating unit distribution.

[0119] In some embodiments, the heating control parameters include the heating temperature of each heating unit. For each core heating zone, the processor can turn on multiple heating units in the core heating zone, and based on the core heating zone, the target temperature distribution and the heating unit distribution, set the heating temperature of the multiple heating units in the core heating zone to the target heating temperature of the corresponding partition.

[0120] The number of multiple heating units turned on in the core heating zone is required to be: the heating area range of the multiple heating units turned on in the core heating zone can cover the entire core heating zone, and the number of heating units used is the least. For example, if the core heating zone has 5 heating units, if turning on 2 heating units is enough to cover the entire core heating zone, then the number of heating units turned on in the core heating zone is 2.

[0121] In some embodiments, the processor may sort the multiple non-core heating zones in descending order according to the target heating temperature, and then determine the heating control parameters of the non-core heating zones in sequence according to the sorting results. Specifically, for each non-core heating zone, the processor may query the second preset table to determine the radiation temperature and radiation range of the zone with a higher target heating temperature in response to the presence of a zone with a higher target heating temperature around the non-core heating zone;

[0122] In response to the radiation temperature being greater than the target heating temperature of the non-core heating zone, it is determined whether the radiation range in the current zone completely includes the heating area range of a certain heating unit in the zone, and if so, the heating unit is not turned on;

[0123] If not included, the heating unit is turned on, and the heating temperature is set to the target heating temperature. At the same time, multiple or all heating units in other areas of the partition are turned on successively, and the temperature is set to the target heating temperature. The number of multiple heating units in other areas of the partition is determined as follows: the heating area range of the multiple heating units in other areas of the partition can cover other areas of the partition, and the number of heating units used is the least. The other areas of the partition refer to other areas in the partition except the heating area range of the previously turned-on heating unit;

[0124] If the radiation temperature is not greater than the target heating temperature of the current zone, multiple heating units are turned on, and the heating temperature is the corresponding target heating temperature.

[0125] The radiation range refers to the area range where heat is indirectly provided to non-heating areas outside the heating area through heat conduction when the heating unit directly heats the heating area.

[0126] The radiation temperature refers to the temperature value that the heating unit can reach within the radiation range.

[0127] In some embodiments, the radiation range and the radiation temperature can be determined by a person skilled in the art based on experiments. Specifically, a person skilled in the art can determine the temperature values ​​at different preset distances outside the heating area corresponding to each heating unit, and make a table of the radiation range and the radiation temperature. The preset distance can be the distance at which the measured temperature value is half of the target heating temperature corresponding to the heating unit.

[0128] In some embodiments, the heating control parameters include the heating temperature and heating power of each heating unit, and the processor can also determine the heating control parameters through a second prediction model based on the core heating area, the target temperature distribution and the heating unit distribution.

[0129] In some embodiments, the second prediction model may be a machine learning model. In some embodiments, the type of the second prediction model may be a neural network (NN) model, etc.

[0130] In some embodiments, the input of the second prediction model may include a core heating zone, a target temperature distribution, and a heating unit distribution, and the output may include a heating control parameter. The core heating zone input to the second prediction model may be a 3D model of an injection mold marked with a core heating zone. The core heating zone is marked as 1 on the 3D model of the injection mold, and other zones are marked as 0. The processor may obtain the 3D model of the injection mold through conventional 3D modeling software.

[0131] In some embodiments, the input to the second prediction model may also include molding cycle requirements.

[0132] The molding cycle requirement refers to the longest molding cycle required for this injection molding. The molding cycle refers to the time required to complete an injection molding (from the beginning of injection molding to demolding of the plastic part).

[0133] Since the heating unit can be heated at different powers, the time taken by the injection mold to complete an injection molding operation is different for different heating powers. For example, the greater the heating power, the faster the heating speed, and the shorter the time taken by the injection mold to complete an injection molding operation. By adding the molding cycle requirements to the input of the second prediction model, the heating power of the heating unit can be accurately predicted.

[0134] In some embodiments, the second prediction model can be obtained through training based on a plurality of second training samples with second labels.

[0135] In some embodiments, each group of second training samples in the second training samples may include a historical sample core heating zone, a historical sample target temperature distribution, and a historical sample heating unit distribution.

[0136] In some embodiments, the second training sample can be obtained through historical data.

[0137] The second label may be a heating control parameter of a historical sample corresponding to the training sample.

[0138] In some embodiments, the processor may use, as a second label, actual heating control parameters in the historical data that can simultaneously meet the target heating temperature requirements of each zone, ensure uniform temperature of each zone, and minimize overall power consumption.

[0139] Temperature uniformity can be understood as the temperature difference between multiple locations obtained by temperature detection in multiple locations within the partition is the smallest. The temperature difference between multiple locations can be minimized when the variance of the temperatures corresponding to the various locations within the partition is the smallest and the average value of the temperatures corresponding to the various locations within the partition is closest to the target heating temperature of the partition.

[0140] Overall refers to the entire stage of heating the zone and maintaining the temperature of the zone at the target heating temperature.

[0141] In some embodiments, the second training sample may further include a historical sample molding cycle requirement, and the second label may also be an actual heating control parameter in the historical data that can simultaneously meet the molding cycle requirement, the target heating temperature requirement of each partition, the uniform temperature of each partition, and the minimum overall power consumption. The historical sample molding cycle requirement can be obtained based on the historical data.

[0142] In some embodiments, accurate prediction of heating control parameters can be achieved through the trained second prediction model.

[0143] In some embodiments of the present specification, a target temperature distribution for optimal molding effect can be determined based on raw material information and mold partition information, and then heating control parameters are determined based on the target temperature distribution and heating unit information, and the heating control parameters are sent to a controller to control multiple heating units to heat the injection mold with the heating control parameters, so that energy consumption can be saved by utilizing heat conduction in different areas, rather than directly using the heating unit to heat each partition on the injection mold separately according to the determined target temperature distribution, thereby saving heating resources.

[0144] Figure 3 is an exemplary flow chart for determining and updating the temperature distribution according to some embodiments of this specification. In some embodiments, process 300 can be executed by a processor of the mold temperature change control system 100. Figure 3 As shown, the process 300 includes the following steps 310 to 340.

[0145] Step 310, determining mold partition information based on mold information, raw material information and production parameters.

[0146] For information about molds, raw materials, production parameters, and mold partitions, see Figure 2 See the relevant instructions in .

[0147] In some embodiments, the processor may determine the second target partition quantity through a second preset comparison table based on the raw material information and the production parameters; and determine the mold partition information through a second preset rule based on the mold information and the second target partition quantity. The second preset comparison table contains a correspondence between the reference raw material information and the reference production parameters and the reference mold partition information. The second preset comparison table may be constructed based on prior knowledge or historical data.

[0148] For a description of the second preset rule, see Figure 2 Relevant instructions in step 220.

[0149] Step 320, determining a target temperature distribution based on the raw material information, production parameters and mold partition information.

[0150] For a description of the target temperature distribution, see Figure 2 Description in step 210.

[0151] In some embodiments, the processor may determine the target temperature distribution through a third preset comparison table based on the raw material information, production parameters, and mold partition information. The third preset comparison table contains a correspondence between reference raw material information, reference production parameters, reference mold partition information, and reference target temperature distribution. The third preset comparison table may be constructed based on prior knowledge or historical data.

[0152] Figure 4 It is a structural schematic diagram of the first determination model shown in some embodiments of this specification.

[0153] In some embodiments, Figure 4 As shown, the processor may also determine mold partition information 421 - 1 and target temperature distribution 430 through a first prediction model 420 based on mold information 410 - 1 , raw material information 410 - 2 , and production parameters 410 - 3 .

[0154] In some embodiments, the first prediction model 420 may be a machine learning model. In some embodiments, the type of the first prediction model 420 may be a neural network (NN) model, a deep neural network (NN) model, or the like.

[0155] In some embodiments, the first prediction model 420 may include a partition prediction layer 421 and a temperature prediction layer 424 .

[0156] In some embodiments, the partition prediction layer 421 may be used to process the mold information 410 - 1 , the raw material information 410 - 2 , and the production parameters 410 - 3 to determine the mold partition information 421 - 1 .

[0157] In some embodiments, the partition prediction layer can be obtained through training based on a plurality of sixth training samples with a sixth label.

[0158] In some embodiments, each group of sixth training samples in the sixth training samples may include historical sample mold information, historical sample raw material information, and historical sample production parameters.

[0159] In some embodiments, the sixth training sample can be obtained through historical data.

[0160] The sixth label may be historical sample mold partition information corresponding to the sixth training sample.

[0161] In some embodiments, the processor may use the mold partition information with the best actual molding effect in the historical data as the sixth label.

[0162] In some embodiments, the temperature prediction layer 424 may be used to process the raw material information 410 - 2 , the production parameters 410 - 3 , and the mold partition information 421 - 1 output by the partition prediction layer 421 to determine the target temperature distribution 430 .

[0163] In some embodiments, the temperature prediction layer can be obtained through training based on a plurality of seventh training samples with seventh labels.

[0164] In some embodiments, each group of seventh training samples in the seventh training samples may include historical sample mold partition information, historical sample raw material information, and historical sample production parameters.

[0165] In some embodiments, the seventh training sample can be obtained through historical data.

[0166] The fifth label may be the historical sample target temperature distribution corresponding to the seventh training sample.

[0167] In some embodiments, the processor may use the target temperature distribution with the best actual molding effect in the historical data as the seventh label.

[0168] In some embodiments, the first prediction model can be obtained by jointly training a partition prediction layer and a temperature prediction layer based on a plurality of first training samples with a first label.

[0169] In some embodiments, each group of first training samples in the first training samples may include historical sample mold information, historical sample raw material information, and historical sample production parameters.

[0170] In some embodiments, the first training sample can be obtained through historical data.

[0171] The first label may be a historical sample target temperature distribution corresponding to the first training sample.

[0172] In some embodiments, the processor may use the target temperature distribution with the best actual molding effect in the historical data as the first label.

[0173] In some embodiments, the processor can input the historical sample mold information, historical sample raw material information and historical sample production parameters in the first training sample with the first label into the initial partition prediction layer, and output the historical sample mold partition information; then input the historical sample raw material information, historical sample production parameters and historical sample mold partition information into the initial temperature prediction layer, construct a loss function through the prediction results of the first label and the initial temperature prediction layer, iteratively update the parameters of the initial partition prediction layer and the initial temperature prediction layer based on the loss function until the loss function converges, the number of iterations reaches a threshold, etc., the training is completed, and a trained first prediction model is obtained.

[0174] In some embodiments, the method for determining the target temperature distribution may further include the following steps 330 - 340 .

[0175] Step 330 , obtaining target injection molding process information 410 - 4 at a preset time.

[0176] The preset time may be a fixed time (e.g., 10 minutes) after the injection mold starts injection molding. The preset time may be preset by those skilled in the art based on experience.

[0177] In some embodiments, the target injection molding process information 410 - 4 may include temperature values ​​and pressure values ​​at multiple points on the injection mold.

[0178] In some embodiments, the processor can obtain the temperature values ​​of multiple points on the injection mold within a preset time through temperature sensors pre-installed at different locations inside the injection mold or a temperature monitoring system inside the injection mold; and obtain the pressure values ​​of multiple points on the injection mold within a preset time through pressure sensors pre-installed at different locations inside the injection mold or a pressure monitoring system inside the injection mold.

[0179] Step 340 , determining an updated temperature distribution based on the target injection molding process information, the raw material information, the production parameters and the target temperature distribution.

[0180] The updated temperature distribution refers to the adjusted target temperature distribution.

[0181] In some embodiments, the processor can determine the reference injection molding process information through a fourth preset comparison table based on the target injection molding process information, raw material information, production parameters and target temperature distribution; and determine the updated temperature distribution based on the difference between the target injection molding process information and the reference injection molding process information. The fourth preset comparison table contains a correspondence between the reference raw material information, the reference production parameters and the reference target temperature distribution and the reference target injection molding process information. The fourth preset comparison table can be constructed based on prior knowledge or historical data. The reference target injection molding process information includes temperature values ​​and pressure values ​​of multiple reference points on the injection mold.

[0182] In some embodiments, the processor can compare the reference target injection molding process information with the actual target injection molding process information. If the actual temperature of a certain point is found to be lower than the reference temperature, the temperature of the partition where the point is located is increased according to the difference. The larger the difference, the greater the increase in temperature. The specific numerical correspondence can be constructed based on human experience. For example, the increase in temperature value (or decrease in temperature value) can be comprehensively processed in combination with the data performance of multiple points in the corresponding partition. For example, the larger the weighted average of the actual temperatures of multiple points in the corresponding partition, the larger the preset increase in temperature value (or decrease in temperature value).

[0183] In some embodiments, the processor may determine the updated temperature distribution after comparing the data of all points in the above manner.

[0184] In some embodiments, Figure 4 As shown, the first prediction model 420 may further include a feature extraction layer 422 .

[0185] In some embodiments, the feature extraction layer 422 may be used to process the target injection molding process information 410 - 4 to determine the injection molding process feature 422 - 1 .

[0186] In some embodiments, the injection molding process feature 422-1 may include whether the material filling of the injection mold during the injection molding process is uniform, the bubble situation of the injection mold during the injection molding process, etc. The bubble situation may include fewer bubbles, more bubbles, appropriate bubbles, etc.

[0187] In some embodiments, the injection molding process feature 422-1 can be represented by a numerical sequence. For example, the injection molding process feature can be represented by a data sequence (1, 0.3), where 1 indicates that the material filling of the injection mold during the injection molding process is very uniform, and 0.3 indicates that the injection mold generates fewer bubbles during the injection molding process.

[0188] In some embodiments, the temperature prediction layer 424 can also be used to determine an updated temperature distribution 430 based on the injection molding process characteristics 422 - 1 , the raw material information 410 - 1 , the production parameters 410 - 3 , the target temperature distribution 410 - 6 , and the mold partition information 421 - 1 output by the partition prediction layer 421 .

[0189] In some embodiments, the first prediction model can also be obtained through joint training of a partition prediction layer, a feature extraction layer, and a temperature prediction layer based on a plurality of third training samples with a third label.

[0190] In some embodiments, each group of third training samples in the third training samples may include historical sample target injection molding process information, historical sample mold information, historical sample raw material information, historical sample production parameters, and historical sample target temperature distribution.

[0191] In some embodiments, the third training sample can be obtained through historical data.

[0192] The third label may be the historical sample update temperature distribution corresponding to the third training sample.

[0193] In some embodiments, the processor may adjust the historical sample target temperature distribution of the same third sample to obtain multiple groups of adjusted historical sample target temperature distributions, and use a group of historical sample target temperatures with the best adjusted molding effect as the third label.

[0194] Since the adjustment of target temperature distribution of multiple groups of historical samples cannot be completed on one injection mold at the same time, multiple identical injection molds can be injected with the same raw materials, production parameters, mold partitions, and target temperature distribution. After obtaining the target injection molding process information, different temperature adjustments can be made to each injection mold.

[0195] In some embodiments, the processor can input the historical sample mold information, historical sample raw material information and historical sample production parameters in the third training sample with a third label into the initial partition prediction layer to obtain the historical sample mold partition information; then input the historical sample target injection molding process information into the initial feature extraction layer to obtain the historical sample injection molding process features; then input the historical sample injection molding process features, historical sample mold partition information, historical sample raw material information, historical sample production parameters and historical sample target temperature distribution into the initial temperature prediction layer; construct a loss function through the third label and the prediction result of the initial temperature prediction layer, iteratively update the parameters of the initial partition prediction layer, the initial feature extraction layer and the initial temperature prediction layer based on the loss function until the loss function converges, the number of iterations reaches a threshold, etc., the training is completed, and a trained first prediction model is obtained.

[0196] In some embodiments of the present specification, in the process of predicting the updated temperature distribution through the first prediction model, the target injection process information and mold partition information are also considered to influence the target heating temperature in each partition, thereby further improving the accuracy of the final predicted updated temperature distribution.

[0197] In some embodiments, the processor may also determine whether the injection molding is abnormal based on the real-time injection molding information and through an abnormality determination model; and in response to the injection molding abnormality, use the real-time injection molding information at the current moment as the target injection molding process information.

[0198] The real-time injection molding information refers to the injection molding process information at each preset time after the start of injection molding, such as the injection molding process information every minute.

[0199] In some embodiments, the processor can obtain injection molding process information once at each preset moment (e.g., every minute), and after each acquisition of real-time injection molding process information, it can determine whether the injection molding is abnormal based on the real-time injection molding information through an abnormality determination model; and in response to injection molding abnormalities, use the real-time injection molding information at the current moment as the target injection molding process information.

[0200] Injection molding abnormality refers to the abnormality of the melt during the injection molding process. For example, in a normal injection molding process, the melt enters the mold, and the heating unit heats it. The melt gradually fills all spaces and pores, and the bubbles gradually evaporate and disappear. However, under the condition of inappropriate temperature, such as too low temperature, the bubbles cannot be completely eliminated, but only partially, then the temperature and pressure in the injection mold will no longer change or remain at a level with bubble characteristics, and this is considered an injection molding abnormality.

[0201] In some embodiments, the abnormality determination model may be a machine learning model. In some embodiments, the type of the abnormality determination model may be a neural network (NN) model, a deep neural network (DNN) model, etc.

[0202] In some embodiments, the abnormality determination model can be obtained through training based on a plurality of fifth training samples with fifth labels.

[0203] In some embodiments, each set of fifth training samples in the fifth training samples may include historical sample injection molding information.

[0204] In some embodiments, the fifth training sample can be obtained through historical data. In some embodiments, the processor can obtain historical injection molding information corresponding to modules with good molding effects and modules with poor molding effects due to unreasonable heating temperature from historical data as the fifth training sample.

[0205] The fifth label may be whether the injection molding corresponding to the fifth training sample is abnormal. The fifth label may be represented by 0 or 1, 1 represents abnormal injection molding, and 0 represents normal injection molding. The fifth label may be obtained by manual annotation. Specifically, it is manually determined at what moment the historical injection molding information in the fifth training sample becomes abnormal, and the corresponding labels of the historical sample injection molding information before this moment are all marked as normal, and the corresponding labels of the historical sample injection molding information after this moment are all marked as abnormal.

[0206] In some embodiments of the present specification, real-time injection information of injection abnormalities is taken as target injection process information, brought into the temperature prediction layer, the temperature distribution is re-determined and updated, and the temperature of the mold partition is adjusted, which can further ensure that the injection mold has the best molding effect.

[0207] In some embodiments, the processor may also use the following steps 341 to 343 to determine the updated temperature distribution:

[0208] Step 341 , obtaining plastic part information of a plastic part that is manufactured and demolded based on a target temperature distribution.

[0209] The plastic part information may include at least one of a picture of the plastic part, quality inspection information, demolding difficulty, and molding cycle, etc.

[0210] The quality inspection information may be the inspection results obtained by the manufacturer according to the existing inspection methods.

[0211] For details on the molding cycle, see Figure 2 Description in step 240.

[0212] Demolding difficulty refers to the difficulty of removing the plastic part from the injection mold.

[0213] In some embodiments, the processor may obtain stored plastic part information through a storage device. The storage device stores the plastic part information. For example, the storage device stores pictures of the plastic part obtained by a camera device.

[0214] Step 342: Based on the plastic part information, the injection molding effect characteristics of the mold partition are determined through the effect extraction layer.

[0215] In some embodiments, Figure 4 As shown, the first prediction model 420 may further include an effect extraction layer 423. The effect extraction layer 423 may be used to process the plastic part information 410-5 and determine the injection effect feature 423-1 of the mold partition.

[0216] The injection molding effect feature 423-1 can characterize the quality of the plastic part finally obtained by injection molding.

[0217] In some embodiments, the injection molding effect feature 423-1 may be a numerical vector, and the numerical value of each element of the vector may reflect the injection molding performance in different dimensions. For example, a numerical vector of the injection molding effect feature may reflect the injection molding performance in five dimensions: the bubble situation on the surface of the plastic part, the smoothness of the surface of the plastic part, the glossiness of the surface of the plastic part, the demolding difficulty of the plastic part, and the overall quality of the plastic part. The glossiness of the surface of the plastic part may reflect the glossiness of the surface of the plastic part.

[0218] Step 343, based on the raw material information, production parameters, mold partition information and target temperature distribution, and at least one of the injection effect characteristics and the injection process characteristics, determine the updated temperature distribution through the temperature prediction layer.

[0219] In some embodiments, the temperature prediction layer 424 may also be used to process the raw material information 410 - 2 , the production information 410 - 3 , the mold partition information 421 - 1 , the injection molding effect characteristics 423 - 1 , the injection molding process characteristics 422 - 1 and the target temperature distribution 410 - 6 to determine an updated temperature distribution 430 .

[0220] In some embodiments, the temperature prediction layer 424 may also be used to process the raw material information 410 - 2 , the production information 410 - 3 , the mold partition information 421 - 1 , the injection molding effect characteristics 423 - 1 , and the target temperature distribution 410 - 6 to determine an updated temperature distribution 430 .

[0221] In some embodiments, the temperature prediction layer may also be used to process the raw material information 410 - 2 , the production information 410 - 3 , the mold partition information 421 - 1 , the injection molding process characteristics 422 - 1 , and the target temperature distribution 410 - 6 to determine the updated temperature distribution 430 .

[0222] In some embodiments, the first prediction model can also be obtained through joint training of a partition prediction layer, a feature extraction layer, an effect extraction layer and a temperature prediction layer based on multiple fourth training samples with fourth labels.

[0223] In some embodiments, each group of fourth training samples in the fourth training samples may include historical sample target injection molding process information, historical sample mold information, historical sample raw material information, historical sample production parameters, historical sample target temperature distribution, and historical sample plastic part information.

[0224] In some embodiments, the fourth training sample can be obtained through historical data.

[0225] The fourth label may be an updated temperature distribution of the historical samples corresponding to the fourth training sample.

[0226] In some embodiments, the processor can adjust the historical sample target temperature distribution of the same fourth sample to obtain multiple groups of adjusted historical sample target temperature distributions, and use a group of historical sample target temperatures with the best adjusted molding effect as the fourth label. The specific determination method of the fourth label is similar to the determination method of the third label, and specifically refer to the description of the determination method of the third label.

[0227] In some embodiments, the processor can input the historical sample mold information, historical sample raw material information and historical sample production parameters in the fourth training sample with the fourth label into the initial partition prediction layer to obtain the historical sample mold partition information; then input the historical sample target injection molding process information into the initial feature extraction layer to obtain the historical sample injection molding process feature; then input the historical sample plastic part information into the initial effect extraction layer to obtain the historical sample injection molding effect feature; then input the historical sample mold partition information, historical sample raw material information, historical sample production parameters and historical sample target temperature distribution, as well as at least one of the historical sample injection molding process feature and the historical sample injection molding effect feature, into the initial temperature prediction layer; construct a loss function through the prediction result of the fourth label and the initial temperature prediction layer, and iteratively update the parameters of the initial effect extraction layer, the initial partition prediction layer, the initial feature extraction layer and the initial temperature prediction layer based on the loss function until the loss function converges, the number of iterations reaches a threshold, etc., the training is completed, and a trained first prediction model is obtained.

[0228] In some embodiments of the present specification, in the process of determining the target temperature distribution, the influence of multiple factors such as raw material information, production parameters and predicted mold partition information are taken into consideration at the same time, thereby improving the accuracy of determining the target temperature distribution.

[0229] In addition, the processor also obtains the target injection molding process information in real time, and then determines the updated temperature distribution based on the target injection molding process information, raw material information, production parameters and target temperature distribution, and adjusts the determined target temperature distribution, further improving the accuracy of the target temperature distribution and enabling the injection mold to have the best molding effect.

[0230] At the same time, in the prediction process of updating the temperature distribution through the first prediction model, various factors such as raw material information, production parameters, injection molding effect characteristics of mold partitions and target temperature distribution are considered at the same time, and their influence on the updated temperature distribution is further improved, which further improves the accuracy of the prediction results.

[0231] It should be noted that the above description of process 300 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0232] 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.

[0233] 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.

[0234] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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. A mold temperature change control system, characterized in that: The system includes an injection molding device, a processor, a controller, and a storage device; The injection molding equipment comprises an injection mold and a plurality of heating units; the injection mold is connected to the plurality of heating units; The plurality of heating units are configured to heat the injection mold; The processor is configured to: Acquire mold information, raw material information and heating unit information from the storage device, wherein the heating unit information includes heating unit distribution; Determining mold partition information based on the mold information includes: determining mold partition information based on the mold information, the raw material information and production parameters; Determining a target temperature distribution based on the raw material information, the production parameters and the mold partition information; Based on the mold partition information and the target temperature distribution, all partitions whose target heating temperatures are greater than or equal to the target heating temperatures corresponding to all adjacent partitions are taken as core heating zones, wherein the core heating zone refers to a zone that can only be heated to the target heating temperature of the partition by the heating unit of the corresponding partition; and determining heating control parameters based on the core heating zone, the target temperature distribution, and the heating unit distribution, and sending the heating control parameters to the controller; The controller is configured to control the plurality of heating units to heat the injection mold with the heating control parameters; Wherein, determining the mold partition information based on the mold information includes: determining the mold partition information based on the mold information by a second preset rule, wherein the second preset rule is to divide each special area on the injection mold structure into a partition, and the remaining areas into a partition; the special area includes an area where a curved surface, a step, a hole groove, and a narrow channel on the injection mold structure are located; For each non-core heating zone on the injection mold, in response to the presence of a zone with a higher target heating temperature around the non-core heating zone, determine the radiation temperature and radiation range of the zone with the higher target heating temperature; the radiation range refers to the area range of indirectly providing heat to the non-heating area outside the heating zone through heat conduction when the heating unit directly heats the heating zone; the radiation temperature refers to the temperature value that the heating unit can reach in the radiation range; In response to the radiation temperature being greater than the target heating temperature of the non-core heating zone, it is determined whether the radiation range of the partition with the higher target heating temperature completely includes the heating area range of a heating unit in the non-core heating partition. If so, the heating unit is not turned on; if not, the heating unit is turned on.

2. The system according to claim 1, characterized in that The processor is further configured to: Obtaining target injection molding process information at a preset time; and An updated temperature distribution is determined based on the target injection molding process information, the raw material information, the production parameters, and the target temperature distribution.

3. A mold temperature change control method, characterized in that: The method is executed by a processor of the mold temperature change control system of claim 1; the system comprises an injection molding device, a processor, a controller and a storage device; The injection molding equipment comprises an injection mold and a plurality of heating units; the injection mold is connected to the plurality of heating units; The plurality of heating units are configured to heat the injection mold; The controller is configured to control the plurality of heating units to heat the injection mold with heating control parameters; The method comprises: Acquire mold information, raw material information and heating unit information from the storage device, wherein the heating unit information includes heating unit distribution; Determining mold partition information based on the mold information includes: determining mold partition information based on the mold information, the raw material information and production parameters; Determining a target temperature distribution based on the raw material information, the production parameters, and the mold partition information; and Based on the mold partition information and the target temperature distribution, all partitions whose target heating temperatures are greater than or equal to the target heating temperatures corresponding to all adjacent partitions are taken as core heating zones, wherein the core heating zone refers to a zone that can only be heated to the target heating temperature of the partition by the heating unit of the corresponding partition; and determining the heating control parameters based on the core heating zone, the target temperature distribution and the heating unit distribution, and sending the heating control parameters to the controller; Wherein, determining the mold partition information based on the mold information includes: determining the mold partition information based on the mold information by a second preset rule, wherein the second preset rule is to divide each special area on the injection mold structure into a partition, and the remaining areas into a partition; the special area includes an area where a curved surface, a step, a hole groove, and a narrow channel on the injection mold structure are located; For each non-core heating zone on the injection mold, in response to the presence of a zone with a higher target heating temperature around the non-core heating zone, determine the radiation temperature and radiation range of the zone with the higher target heating temperature; the radiation range refers to the area range of indirectly providing heat to the non-heating area outside the heating zone through heat conduction when the heating unit directly heats the heating zone; the radiation temperature refers to the temperature value that the heating unit can reach in the radiation range; In response to the radiation temperature being greater than the target heating temperature of the non-core heating zone, it is determined whether the radiation range of the partition with the higher target heating temperature completely includes the heating area range of a heating unit in the non-core heating partition. If so, the heating unit is not turned on; if not, the heating unit is turned on.

4. The method according to claim 3, characterized in that The method further comprises: Obtaining target injection molding process information at a preset time; and An updated temperature distribution is determined based on the target injection molding process information, the raw material information, the production parameters, and the target temperature distribution.

5. A mold temperature change control device, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the mold temperature change control method as described in any one of claims 3 to 4.

Images