Injection molding system and molding condition generation method based on artificial intelligence

Abstract

The artificial intelligence-based injection molding system of one aspect of the present invention can change the molding conditions when a defective product is produced due to interference during the injection molding process of the product, so as to produce a good product. It is characterized by comprising: an injection molding machine (100) that injects molding material into a mold to injection-mold a product; an injection molding state data acquisition unit (710) that acquires current injection molding state data during the injection molding of the product, wherein the current injection molding state data includes at least one of the viscosity distribution of the molding material injected into the mold and the injection pressure value; a judgment unit (720) that judges whether the molding quality is maintained by inputting the current injection molding state data into a molding quality maintenance model (735) learned using a preset target injection molding state data; and a molding condition setting unit (730) that changes the preset molding conditions when the judgment unit (720) judges that the molding quality is not maintained, so that the current injection molding state data follows the target injection molding state data.

Description

Technical Field

[0001] The present invention relates to an injection molding system, and more particularly to the control of an injection molding system. Background Art

[0002] Injection molding is the most widely used manufacturing method for plastic products. For example, various parts such as covers and shells of products such as televisions, mobile phones, and PDAs can be manufactured through injection molding.

[0003] Generally, the production of products through injection molding is achieved through the following processes. First, the molding material to which pigments, stabilizers, plasticizers, fillers, etc. are added is put into a hopper and made into a molten state. Then, the molten molding material is injected into the mold and solidified by cooling. Then, after the solidified molding material is taken out of the mold, the unnecessary parts are removed. Various types and products with different sizes are manufactured through these processes.

[0004] As an apparatus for performing the injection molding as described above, an injection molding machine is used. The injection molding machine includes an injection device for supplying a molding material in a molten state, and a clamping device for solidifying the molding material in a molten state by cooling.

[0005] In order to manufacture products with an injection molding machine, it is necessary to properly set various molding conditions such as temperature, speed, pressure, and time to produce high-quality products. However, even if injection molding is performed under the proper molding conditions, it may not be possible to produce high-quality products due to interference such as changes in ambient temperature / humidity during injection molding or changes in the physical properties of the molding material.

[0006] Therefore, in order to produce products with uniform quality, it is necessary to change the molding conditions according to changes in the surrounding environment or the physical properties of the molding material. However, when the operator changes the molding conditions, even if the same interference occurs, the molding conditions will be set differently depending on the operator, so there is a problem that it is difficult to expect uniform molding quality. Summary of the invention

[0007] The problem to be solved by the invention.

[0008] The present invention is proposed to solve the above-mentioned problems, and its purpose is to provide an artificial intelligence-based injection molding system, which can change the molding conditions to produce good products when interference occurs in the production of defective products during the injection molding process.

[0009] In addition, an object of the present invention is to provide an artificial intelligence-based injection molding system that is capable of setting molding conditions that can maintain excellent molding quality by using a molding quality maintenance model based on deep learning.

[0010] Technical solutions to the problem

[0011] According to one aspect of the present invention for achieving the above-mentioned purpose, an artificial intelligence-based injection molding system is characterized in that it includes: an injection molding machine (100) for injecting molding material into a mold to injection-mold a product; an injection molding state data acquisition unit (710) for acquiring current injection molding state data during injection molding of the product, wherein the current injection molding state data includes at least one of a viscosity distribution of the molding material injected into the mold and an injection pressure value; a judgment unit (720) for judging whether the molding quality is maintained by inputting the current injection molding state data into a molding quality maintenance model (735) learned using preset target injection molding state data; and a molding condition setting unit (730) for changing the preset molding conditions when the judgment unit (720) judges that the molding quality is not maintained, so that the current injection molding state data follows the target injection molding state data.

[0012] According to another aspect of the present invention for achieving the above-mentioned purpose, a molding condition generating method for an injection molding system based on artificial intelligence is characterized in that it includes: a step of acquiring current injection state data when injecting molding material into a mold to injection mold a product, the current injection state data including at least one of the viscosity distribution and injection pressure value of the molding material injected into the mold; a step of judging whether the molding quality is maintained by inputting the current injection state data into a molding quality maintenance model (735) learned using target injection state data, the target injection state data including at least one of the target viscosity distribution and target injection pressure value measured during the injection molding of a good product; and a step of changing a pre-set molding condition so that the current injection state data follows the target injection state data when it is judged that the molding quality is not maintained.

[0013] Effects of the Invention

[0014] According to the present invention, when a defective product is produced due to interference during the injection molding process of a product, a molding condition generating device implemented by a neural network based on deep learning can automatically change the molding conditions, thereby having the effect of improving the quality of the product.

[0015] Furthermore, according to the present invention, since the molding conditions are automatically changed by the molding condition generating device, there is an effect that the molding conditions can be changed to conditions that can produce good products in a short time even without skilled experts. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a diagram illustrating an artificial intelligence-based injection molding system according to an embodiment of the present invention.

[0017] Figure 2 1 is a diagram showing a configuration of an injection molding machine according to an embodiment of the present invention.

[0018] Figure 3 It is a figure which shows the state of mold opening of a fixed mold and a movable mold.

[0019] Figure 4 This is a diagram showing a state where a fixed mold and a movable mold are clamped together by a moving part.

[0020] Figure 5 1 is a diagram showing the structure of a molding condition generating device according to an embodiment of the present invention.

[0021] Figure 6 is a flowchart illustrating a method for generating molding conditions according to an embodiment of the present invention.

[0022] Figure 7 is a flow chart showing a molding condition changing method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0024] Figure 1 is a diagram illustrating an artificial intelligence-based injection molding system according to an embodiment of the present invention.

[0025] The artificial intelligence-based injection molding system 10 of the present invention (hereinafter referred to as "injection molding system") uses molding materials to produce products under optimal molding conditions. To this end, Figure 1 As shown, the injection molding system 10 includes an injection molding machine 100 and a molding condition generating device 200 .

[0026] The injection molding machine 100 of the present invention performs injection molding in order to manufacture a product.

[0027] Figure 2 1 is a diagram showing the structure of an injection molding machine 100 according to an embodiment of the present invention. Figure 1 and Figure 2 , the injection molding machine 100 is described in more detail.

[0028] like Figure 1 and Figure 2 As shown, the injection molding machine 100 according to the present invention includes an injection device 102 and a clamping device 103 .

[0029] The injection device 102 supplies the molding material in a molten state to the clamping device 103. The injection device 102 includes a barrel 121, an injection screw 122 arranged inside the barrel 121, and an injection drive 123 driving the injection screw 122. The barrel 121 can be configured to be parallel to the first axis direction (X axis direction). The first axis direction (X axis direction) can be a direction parallel to the direction in which the injection device 102 and the clamping device 103 are separated from each other. When the molding material is supplied to the inside of the barrel 121, the injection drive 123 can move the molding material supplied to the inside of the barrel 121 in the first direction (FD arrow direction) by rotating the injection screw 122. In this process, the molding material can be melted by friction and heating. The first direction (FD arrow direction) is a direction from the injection device 102 toward the clamping device 103, and can be a direction parallel to the first axis direction (X axis direction). When the molten molding material is located in the first direction (FD arrow direction) relative to the injection screw 122, the injection drive unit 123 can move the injection screw 122 in the first direction (FD arrow direction). Thus, the molten molding material can be supplied from the barrel 121 to the clamping device 103.

[0030] The clamping device 103 solidifies the molten molding material by cooling. The clamping device 103 may include a fixed template 131 combined with a fixed mold 150, a movable template 132 combined with a movable mold 160, and a moving part 133 that moves the movable template 132 along a first axis direction (X axis direction).

[0031] Figure 3 and Figure 4 This is a diagram showing a state in which the moving part closes the fixed mold and the movable mold.

[0032] If the moving part 133 moves the moving template 132 in the second direction (the SD arrow direction) so that the moving mold 160 and the fixed mold 150 are closed, the injection device 102 supplies the molding material in a molten state to the inside of the moving mold 160 and the fixed mold 150. The second direction (the SD arrow direction) is parallel to the first axis direction (the X axis direction) and opposite to the first direction (the FD arrow direction). Then, the clamping device 103 solidifies the molding material in a molten state filled in the inside of the moving mold 160 and the fixed mold 150 by cooling, and then the moving part 133 opens the moving mold 160 and the fixed mold 150 by moving the moving template 132 in the first direction (the FD arrow direction).

[0033] The clamping device 103 may include a tie bar 134. The tie bar 134 guides the movement of the movable template 132. The movable template 132 may be movably combined with the tie bar 134. The movable template 132 may move in a first axis direction (X axis direction) along the tie bar 134. The tie bar 134 may be configured to be parallel to the first axis direction (X axis direction). The tie bar 134 may be combined to be inserted into the fixed template 131 and the movable template 132, respectively.

[0034] On the other hand, the injection molding machine 100 of the present invention supplies molding material to the clamped movable mold 160 and fixed mold 150 according to the molding conditions generated by the molding condition generating device 200, and produces a product. The movable mold 160 and the fixed mold 150 are hereinafter referred to as molds.

[0035] The molding condition generating device 200 generates molding conditions and transmits them to the injection molding machine 100. In addition, when the injection molding machine 100 produces a product according to the generated molding conditions, the molding condition generating device 200 determines whether the molding quality is maintained, and changes the molding conditions if it is determined that the molding quality cannot be maintained due to interference.

[0036] Below, refer to Figure 5 , the molding condition generating device 200 according to the present invention is described in more detail.

[0037] Figure 5 FIG. 2 is a diagram showing the structure of a molding condition generating device according to an embodiment of the present invention. Figure 5 As shown, the molding condition generating device 200 includes an injection state data acquiring unit 710, a determining unit 720, a molding condition setting unit 730, and a molding quality maintaining model 735. Figure 5 7 shows a case where the judgment unit 720, the molding condition setting unit 730, and the molding quality maintenance model 735 are separately configured, but this is only an example, and the judgment unit 720 and the molding condition setting unit 730 may also be implemented by a single engine 725 configured in the form of software. Figure 5 As shown, the molding condition generating device 200 according to the present invention may further include a model generating unit 740 and a database 750 .

[0038] When the injection molding machine 100 is injection molding a product, the injection molding state data acquisition unit 710 acquires injection molding state data from the injection molding machine 100. In one embodiment, the injection molding state data may include at least one of the viscosity distribution of the molding material injected into the mold and the injection pressure value. At this time, the viscosity distribution of the molding material can be calculated based on the thickness of the injection molding product and the pressure change amount inside the mold that changes over time.

[0039] For example, the injection state data acquisition unit 710 may calculate the viscosity distribution of the molding material using the following equation 1.

[0040]

Mathematical formula 1

[0041]

[0042] In formula 1, η represents viscosity (Visocity), σ w represents the wall shear stress (Wall ShearStress), γ w Indicates the wall shear rate (Wall Shear Rate). In addition, H indicates the thickness of the injection molded product, L indicates the flow distance defined by the distance between the pressure sensor and the temperature sensor (or the distance between two pressure sensors), △P indicates the pressure change, and △t indicates the time change. Here, the pressure change refers to the pressure change during the period of flow equivalent to the flow distance (L), and the time change refers to the time consumed during the period of flow equivalent to the flow distance (L).

[0043] To this end, the injection molding state data acquisition unit 710 can measure the pressure change amount inside the mold that changes with the time change amount or measure the injection pressure when performing the injection molding operation based on the injection molding machine 100. The injection molding state data acquisition unit 710 calculates the viscosity distribution of the molding material using the measured time change amount, pressure change amount, thickness of the injection molded product, and flow distance.

[0044] The injection state data acquisition unit 710 acquires the injection molding data from the injection molding machine 100 at each preset time point or each time an injection state data acquisition request is received from the determination unit 720, and provides the injection molding data to the determination unit 720. Hereinafter, the injection molding state data acquired at each preset time point or each time an injection state data acquisition request is received is referred to as current injection molding state data.

[0045] On the other hand, when the product previously produced by the injection molding machine 100 is a good product that meets the preset conditions, the injection molding state data acquisition unit 710 can determine the injection molding state data acquired during the injection molding of the product as the target injection molding state data, and store the determined target injection molding state data in the database 750. The target injection molding state data may include at least one of a target viscosity distribution and a target injection pressure value, and when the produced product is a good product that meets the preset conditions, the target viscosity distribution can be calculated based on the time variation, pressure variation, thickness of the injection molded product, and flow distance measured during the injection molding of the product.

[0046] The judgment unit 720 uses the current injection state data acquired by the data acquisition unit 710 to judge whether the quality of the product is consistent with the quality of the product injected according to the preset molding conditions. At this time, the preset molding conditions may be the initial molding conditions set by the molding condition setting unit 730 when the injection molding machine 100 is initially started, and such initial molding conditions may be the molding conditions acquired when producing good products.

[0047] In one embodiment, the determination unit 720 may determine whether the molding quality is maintained by inputting the current injection molding state data acquired by the injection molding state data acquisition unit 710 into the molding quality maintenance model 735. At this time, the molding quality maintenance model 735 may be a neural network based on deep learning that is learned using the target injection molding state data. When the molding quality maintenance model 735 determines that the input current injection molding state data is out of a critical range set based on the target injection molding state data, the determination unit 720 may determine that the molding quality is not maintained.

[0048] When the injection molding machine 100 is initially started, the molding condition setting unit 730 sets the initial molding conditions to be used and outputs them to the injection molding machine 100. In one embodiment, the initial molding conditions include at least one of the temperature and pressure inside the mold, the injection pressure, the barrel temperature, the injection speed, the holding time, and the holding pressure. At this time, as described above, the initial molding conditions can be set to the molding conditions obtained when producing good products.

[0049] In particular, the molding condition setting unit 730 according to the present invention can change the molding conditions applied to the injection molding machine 100 according to the judgment result of whether the molding conditions are maintained based on the judgment result of the judgment unit 720. In the case where the judgment unit 720 judges that the molding quality is maintained, the molding condition setting unit 730 can determine to maintain the currently set molding conditions. However, if the judgment unit 720 judges that the molding quality is not maintained, the molding condition setting unit 730 can change the molding conditions so that the current injection state data acquired by the injection state data acquisition unit 710 follows the target injection state data.

[0050] In one embodiment, the molding condition setting unit 730 can change at least one of the injection speed, barrel temperature, and mold temperature in the molding conditions. The molding condition setting unit 730 can first change the molding conditions that are relatively easy and quick to apply among the injection speed, barrel temperature, and mold temperature. As an example, since the injection speed is a molding condition that can be changed immediately, the molding condition setting unit 730 can determine to change the injection speed first. Although the barrel temperature is controllable, since the application time is longer than the injection speed, the molding condition setting unit 730 can determine to change the barrel temperature after changing the injection speed. In addition, although the mold temperature is also controllable, since it is not a direct component of the injection molding machine 100, the application time is relatively the longest, so the molding condition setting unit 730 can determine to change the mold temperature after changing the barrel temperature.

[0051] In detail, when the judgment unit 720 determines that the molding quality is not maintained, the molding condition setting unit 730 uses the molding quality maintenance model 735 to calculate the deviation between the current injection state data and the target injection state data, and changes the injection speed by a value proportional to the deviation so that the current injection state data follows the target injection state data.

[0052] For example, when the judgment unit 720 determines that the molding quality is not maintained, the molding condition setting unit 730 uses the molding quality maintenance model 735 to calculate the deviation between the current viscosity distribution and the target viscosity distribution, and changes the injection speed by a value proportional to the deviation so that the current viscosity distribution follows the target viscosity distribution.

[0053] At this time, a larger viscosity distribution value indicates high viscosity, which means that the molding material does not flow smoothly. Therefore, when the current viscosity distribution is greater than the target viscosity distribution, the viscosity distribution value can be reduced by increasing the injection speed or increasing the barrel temperature or mold temperature to make the molding material flow smoothly.

[0054] As another example, when the judgment unit 720 determines that the molding conditions are not maintained, the molding condition setting unit 730 uses the molding quality maintenance model 735 to calculate the deviation between the current injection pressure value and the target injection pressure value, and changes the injection speed by a value proportional to the deviation so that the current injection pressure value follows the target injection pressure value.

[0055] Here, when the injection speed is changed by a value proportional to the deviation amount, the molding condition setting unit 730 changes the injection speed within a preset injection speed limit value.

[0056] If the injection speed deviates from the injection speed limit when the injection speed is changed to a value proportional to the deviation, the molding condition setting unit 730 uses the molding quality maintenance model 735 to change the injection speed to the injection speed limit, and changes the barrel temperature to a value proportional to the deviation so that the current injection state data follows the target injection state data.

[0057] For example, when the judgment unit 720 determines that the molding quality is not maintained, the molding condition setting unit 730 uses the molding quality maintenance model 735 to calculate the deviation between the current viscosity distribution and the target viscosity distribution, changes the injection speed to the injection speed limit, and changes the barrel temperature by a value proportional to the deviation so that the current viscosity distribution follows the target viscosity distribution.

[0058] As another example, when the judgment unit 720 determines that the molding quality is not maintained, the molding condition setting unit 730 uses the molding quality maintenance model 735 to calculate the deviation between the current injection pressure value and the target injection pressure value, changes the injection speed to the injection speed limit, and changes the barrel temperature by a value proportional to the deviation so that the current injection pressure value follows the target injection pressure value.

[0059] Here, when the cylinder temperature is changed by a value proportional to the deviation amount, the molding condition setting unit 730 changes the cylinder temperature within a preset cylinder temperature limit value.

[0060] At this time, the molding condition setting unit 730 may change the cylinder temperature by a value proportional to a remaining deviation amount other than the deviation amount applied when the injection speed is changed to the injection speed limit value.

[0061] If the barrel temperature deviates from the barrel temperature limit when the barrel temperature is changed to a value proportional to the deviation, the molding condition setting unit 730 uses the molding quality maintenance model 735 to change the barrel temperature to the barrel temperature limit, and changes the mold temperature to a value proportional to the deviation so that the current injection state data follows the target injection state data.

[0062] For example, when the judgment unit 720 determines that the molding quality is not maintained, the molding condition setting unit 730 uses the molding quality maintenance model 735 to calculate the deviation between the current viscosity distribution and the target viscosity distribution, changes the injection speed to the injection speed limit, changes the barrel temperature to the barrel temperature limit, and changes the mold temperature by a value proportional to the deviation, so that the current viscosity distribution follows the target viscosity distribution.

[0063] As another example, when the judgment unit 720 determines that the molding quality is not maintained, the molding condition setting unit 730 uses the molding quality maintenance model 735 to calculate the deviation between the current injection pressure value and the target injection pressure value, changes the injection speed to the injection speed limit, changes the barrel temperature to the barrel temperature limit, and changes the mold temperature by a value proportional to the deviation, so that the current injection pressure value follows the target injection pressure value.

[0064] Here, when the mold temperature is changed by a value proportional to the deviation amount, the molding condition setting unit 730 changes the mold temperature and the cylinder temperature within a preset mold temperature limit value.

[0065] At this time, the molding condition setting unit 730 may change the mold temperature by a value proportional to the remaining deviation amount other than the deviation amount applied when changing the injection speed to the injection speed limit value and the deviation amount applied when changing the barrel temperature to the barrel temperature limit value.

[0066] If the mold temperature deviates from the mold temperature limit cylinder temperature when the mold temperature is changed by a value proportional to the deviation amount, the molding condition setting unit 730 changes the mold temperature cylinder temperature to the mold temperature cylinder temperature limit.

[0067] On the other hand, if the mold temperature deviates from the mold temperature limit when the mold temperature is changed by a value proportional to the deviation, the molding condition generating device 200 may determine that it is difficult to maintain the molding conditions and send a reminder to the operator.

[0068] In this way, when there is a difference between the current injection molding state data and the target injection molding state data, the molding condition setting unit 730 according to the present invention sequentially changes the injection speed, barrel temperature and mold temperature so that the current injection molding state data follows the target injection molding state data. Therefore, even if interference occurs during the injection molding operation, the quality of the product produced by injection molding can be maintained at the same level as the quality of a good product.

[0069] In addition, according to the present invention, the change of molding conditions is not performed based on the experience of the operator, but is performed using the molding quality maintenance model 735 composed of a neural network based on deep learning, so that the molding quality can be maintained unchanged regardless of the operator's proficiency.

[0070] The molding condition setting unit 730 outputs the changed molding conditions to the injection molding machine 100. Thus, the injection molding machine 100 performs injection molding according to the changed molding conditions to produce a product.

[0071] When the current injection state data is input through the injection state data acquisition unit 710, the molding quality maintenance model 735 determines whether the molding quality is maintained based on the current injection state data and the target injection state data. The molding quality maintenance model 735 can be learned by the model generation unit 740. In one embodiment, the molding quality maintenance model 735 can be a deep learning-based neural network that can determine whether the molding quality is maintained based on a plurality of weights and a plurality of biases. According to this embodiment, the molding quality maintenance model 735 can be implemented with an ANN (Artificial Neural Network) algorithm.

[0072] The model generation unit 740 generates the molding quality maintenance model 735 and learns the generated molding quality maintenance model 735. Specifically, the model generation unit 740 may generate the molding quality maintenance model 735 by using a plurality of target injection state data as a learning data set and learning the neural network.

[0073] Specifically, the model generation unit 740 generates a plurality of learning data sets using at least one of the target viscosity distribution and the target injection pressure value obtained when producing good products, and uses the generated plurality of learning data sets to enable the neural network to learn, thereby generating the molding quality maintenance model 735.

[0074] Furthermore, if new target injection state data is generated at a predetermined period, the model generation unit 740 may learn the molding quality maintenance model 735 using the new target injection state data.

[0075] In this way, in the present invention, even if the operator does not have professional knowledge about injection molding, he can be guided to perform the judgment of whether to maintain the molding quality and the change of the molding conditions for maintaining the molding quality through the molding quality maintenance model 735 generated by the model generation unit 740, thereby reducing the dependence on professionals for injection molding operations, thereby having the effect of being able to establish a smart factory in the injection molding field based on an unmanned injection molding system.

[0076] The database 750 may store current injection state data and target injection state data generated by the injection state data acquisition unit 710. In addition, the database 750 may store molding conditions set or changed by the molding condition setting unit 730. In addition, the database 750 may store various information used in injection molding.

[0077] Below, refer to Figure 6 , the molding condition generating method in the injection molding system of the present invention is described in detail. Figure 6is a flowchart illustrating a method for generating molding conditions in an injection molding system according to an embodiment of the present invention. Figure 6 The molding condition generation method in the injection molding system shown can be obtained by Figure 1 The injection molding system shown is performed.

[0078] The injection molding machine 100 produces products according to the molding conditions set by the molding condition generating device 200. In one embodiment, the injection molding machine may set the molding conditions applied when producing good products as initial molding conditions.

[0079] When the product is being injection molded by the injection molding machine 100, the molding condition generating device 200 obtains current injection state data, which includes at least one of the current viscosity distribution and the current injection pressure value of the molding material injected into the mold of the injection molding machine 100 (S810).

[0080] In one embodiment, the current viscosity distribution can be calculated by the time variation, pressure variation, thickness of the injection-molded product, and flow distance during product injection molding.

[0081] Then, the molding condition generating device 200 determines whether the molding quality is maintained based on the current injection molding data and the target injection molding data (S820). At this time, the target injection molding data refers to the injection molding state data obtained when producing good products. In one embodiment, the molding condition generating device 200 can determine whether the molding quality is maintained by inputting the current injection molding state data into the molding quality maintenance model learned using the target injection molding state data.

[0082] Specifically, when it is determined according to the molding quality maintenance model that the current injection state data deviates from the critical range set based on the target injection state data, the molding condition generation device 200 determines that the molding quality is not maintained; when it is determined that it does not deviate from the critical range, the molding condition generation device 200 determines that the molding quality is maintained.

[0083] If the molding quality is maintained as determined in step S820, the molding condition generating device 200 changes the preset molding condition so that the current injection state data follows the target injection state data (S830). In one embodiment, the molding condition generating device 200 may change at least one of the injection speed, the barrel temperature, and the mold temperature in the preset molding condition.

[0084] At this time, as the molding conditions changed by the molding condition generating device 200 are output to the injection molding machine 100, the injection molding machine 100 performs injection molding according to the changed molding conditions (S800).

[0085] On the other hand, if it is determined in step S820 that the molding quality is to be maintained, the molding condition generating device 200 determines to maintain the currently applied molding conditions (S840).

[0086] At this time, as the molding condition generating device 200 outputs the maintained molding condition, the injection molding machine 100 performs injection molding according to the applied molding condition (S800).

[0087] Below, refer to Figure 7 , a more detailed description is given of the process of changing the molding conditions by the molding condition generating device. Figure 7 This is a flowchart showing a process of changing molding conditions by the molding condition generating device according to one embodiment of the present invention. Figure 7 The process shown is performed by the molding condition generating device 200, and the molding condition generating device 200 can be performed using the molding quality maintenance model. Figure 7 The process shown.

[0088] First, in Figure 6 If it is determined in step S820 that the molding quality is not maintained, the molding condition generating device 200 calculates the deviation between the current injection state data and the target injection state data (S900).

[0089] The molding condition creation device 200 changes the injection speed by a value proportional to the deviation amount ( S910 ).

[0090] The molding condition generating device 200 determines whether the changed injection speed is out of the injection speed limit value (S920).

[0091] If it is determined in step S920 that the changed injection speed does not deviate from the injection speed limit, the molding condition generating device 200 outputs the changed molding conditions including the changed injection speed to the injection molding machine 100 (S1000).

[0092] On the other hand, if the result of the determination in step S920 is that the injection speed after the change is out of the injection speed limit, the molding condition generating device 200 changes the injection speed to the injection speed limit (S930), and changes the barrel temperature to a value proportional to the deviation (S940). At this time, the barrel temperature can be changed to a value proportional to the remaining deviation except for the deviation used when the injection speed is changed to the injection speed limit.

[0093] The molding condition generating device 200 determines whether the changed barrel temperature is out of the barrel temperature limit value (S950).

[0094] If the judgment result of step S950 determines that the changed barrel temperature does not deviate from the barrel temperature limit, the molding condition generating device 200 will output the changed molding conditions including the changed injection speed (injection speed limit) and the changed barrel temperature to the injection molding machine 100 (S1000).

[0095] On the other hand, if the result of the determination in step S950 is that the changed barrel temperature is out of the barrel temperature limit, the molding condition generating device 200 changes the barrel temperature to the barrel temperature limit (S960), and changes the mold temperature by a value proportional to the deviation (S970). At this time, the mold temperature may be changed by a value proportional to the remaining deviation except for the deviation used when the injection speed is changed to the injection speed limit and the deviation used when the barrel temperature is changed to the barrel temperature limit.

[0096] The molding condition generating device 200 determines whether the changed mold temperature is out of the mold temperature limit value ( S980 ).

[0097] When the judgment result of step S980 determines that the changed mold temperature does not deviate from the mold temperature limit, the molding condition generating device 200 outputs the changed molding conditions including the changed injection speed (injection speed limit), the changed barrel temperature (barrel temperature limit) and the changed mold temperature to the injection molding machine 100 (S1000).

[0098] On the other hand, if the judgment result of step S980 is that the changed mold temperature deviates from the mold temperature limit, the molding condition generating device 200 changes the mold temperature to the mold temperature limit (S990), and outputs the changed molding conditions including the changed injection speed (injection speed limit), the changed barrel temperature (barrel temperature limit) and the changed mold temperature (mold temperature limit) to the injection molding machine 100 (S1000).

[0099] On the other hand, when it is determined that the changed mold temperature deviates from the mold temperature limit value, the molding condition generating device 200 may determine that it is difficult to maintain the molding quality and send a reminder to the operator.

[0100] For those skilled in the art, it can be understood that the above-mentioned invention can be implemented in other specific ways without changing the technical concept or essential features.

[0101] All methods and steps mentioned in this specification may be implemented in part using one or more computer programs or components. The component may be provided as a series of computer commands by any conventional computer-readable medium including volatile and non-volatile memory such as RAM, ROM, flash memory, magnetic disk or optical disk, optical storage, or other memory, or machine-readable medium. The commands may be provided as software or firmware, or may be implemented in whole or in part in hardware such as ASICs, FPGAs, DSPs, or other similar components. The commands may be executed by one or more processors or other hardware components, and when the processor or other hardware components execute the series of computer commands, all or part of the methods and steps disclosed in this specification may be executed.

[0102] Therefore, it should be understood that all aspects of the embodiments described above are exemplary rather than restrictive. Furthermore, it should be interpreted that the scope of the present invention is determined by the claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts belong to the present invention.

Claims

1. An artificial intelligence-based injection molding system, characterized in that: include: An injection molding machine (100) injects molding material into a mold to form a product; An injection molding state data acquisition unit (710) is configured to acquire current injection molding state data during injection molding of the product, wherein the current injection molding state data includes at least one of a viscosity distribution of the molding material injected into the mold and an injection pressure value; A judgment unit (720) judges whether the molding quality is maintained by inputting the current injection state data into a molding quality maintenance model (735) learned using preset target injection state data; as well as A molding condition setting unit (730) changes the preset molding conditions so that the current injection molding state data follows the target injection molding state data when the determination unit (720) determines that the molding quality is not maintained; The molding condition setting unit (730) changes at least one of the injection speed, the barrel temperature and the mold temperature in the molding conditions; When the judging unit (720) judges that the molding quality is not maintained, the molding condition setting unit (730) calculates the deviation between the current injection molding state data and the target injection molding state data, and changes the injection speed by a value proportional to the deviation within a preset injection speed limit, so that the current injection molding state data follows the target injection molding state data; If the injection speed deviates from the injection speed limit when the injection speed is changed by a value proportional to the deviation, the molding condition setting unit (730) changes the injection speed to the injection speed limit and changes the barrel temperature by a value proportional to the deviation within a preset barrel temperature limit; If the barrel temperature deviates from the barrel temperature limit when the barrel temperature is changed by a value proportional to the deviation, the molding condition setting unit (730) changes the barrel temperature to the barrel temperature limit and changes the mold temperature by a value proportional to the deviation within a preset mold temperature limit; If the mold temperature deviates from the mold temperature limit when the mold temperature is changed by a value proportional to the deviation, the molding condition setting unit (730) changes the mold temperature to the mold temperature limit.

2. The artificial intelligence-based injection molding system according to claim 1, characterized in that: The injection molding state data acquisition unit (710) acquires the viscosity distribution by using the thickness of the injection molded product and the pressure variation inside the mold that changes over time.

3. The artificial intelligence-based injection molding system according to claim 1, characterized in that: The target injection state data includes at least one of a target viscosity distribution acquired during injection molding of a good product and a target injection pressure value measured during injection molding of the good product.

4. The artificial intelligence-based injection molding system according to claim 1, characterized in that: When it is determined that the current injection state data is out of a critical range set based on the target injection state data, the determination unit (720) determines that the molding quality is not maintained.

5. The artificial intelligence-based injection molding system according to claim 1, characterized in that: The invention also includes a model generation unit (740), which generates the molding quality maintenance model (735) by enabling a neural network to learn using the target injection state data, wherein the target injection state data includes at least one of a plurality of target viscosity distributions and a plurality of target injection pressure values ​​measured during injection molding of a good product.

6. A method for generating molding conditions for an injection molding system based on artificial intelligence, characterized in that: include: When the molding material is injected into the mold to injection mold the product, a step of acquiring current injection state data, wherein the current injection state data includes at least one of a viscosity distribution and an injection pressure value of the molding material injected into the mold; A step of judging whether the molding quality is maintained by inputting the current injection molding state data into a molding quality maintenance model (735) learned using target injection molding state data, wherein the target injection molding state data includes at least one of a target viscosity distribution and a target injection pressure value measured during injection molding of a good product; and If it is determined that the molding quality is not maintained, changing the preset molding conditions so that the current injection molding state data follows the target injection molding state data; In the step of changing the molding conditions, at least one of the injection speed, the barrel temperature and the mold temperature among the molding conditions is changed; The step of changing the molding conditions includes: When it is determined that the molding quality is not maintained, a deviation between the current injection state data and the target injection state data is calculated, and within a preset injection speed limit, the injection speed is changed by a value proportional to the deviation; If the injection speed deviates from the injection speed limit when the injection speed is changed by a value proportional to the deviation, the injection speed is changed to the injection speed limit, and the barrel temperature is changed by a value proportional to the deviation within a preset barrel temperature limit; If the barrel temperature deviates from the barrel temperature limit when the barrel temperature is changed by a value proportional to the deviation, the barrel temperature is changed to the barrel temperature limit, and the mold temperature is changed by a value proportional to the deviation within a preset mold temperature limit; as well as A step of changing the mold temperature to the mold temperature limit value if the mold temperature deviates from the mold temperature limit value when the mold temperature is changed by a value proportional to the deviation amount.

Images