Mixing and melting device and auxiliary control method using mixing and melting device

Abstract

To provide a mixing and melting device and an auxiliary control method for the mixing and melting device, capable of maintaining a quality of a produced fusion material even if an operating state is affected by a sudden change in an environment or a malfunction of a machine.SOLUTION: A mixing and melting device that mixes and melts materials according to a predetermined work process includes: a motor that generates driving force; a rotation axis; multiple blade members; a material charge part; a mixing vessel for mixing and melting; a storage part for work process; a working part that operates according to the work process; a detection part for operating conditions; and a control part that predicts a predicted melting point arrival time T1 when the working part operates according to the work process stored in the storage part by the detected results, and controls the working part so that an absolute value of a difference between set melting point arrival time T0 and predicted melting point arrival time T1 stored in the storage part becomes smaller when the absolute value of the difference between the set melting point arrival time T0 and the predicted melting point arrival time T1 is equal to or greater than a threshold value.SELECTED DRAWING: Figure 12

Description

[Technical field]

[0001] The present invention relates to a mixing and melting apparatus and an auxiliary control method for the mixing and melting apparatus. [Background technology]

[0002] In recent years, the concentration of carbon dioxide in the atmosphere has increased, and climate change such as global warming has become a problem. In order to suppress environmental abnormalities such as global warming and reduce the use of fossil resources that are in danger of being depleted, the use of biomass, a renewable resource that effectively utilizes biotechnology, has been promoted. Regarding the production of biomass materials, a technology has been disclosed for forming a wood-based composite resin material from a wood-based filler material, a lubricant, a thermoplastic resin raw material, and an oxygen modifier (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 4598194 Summary of the Invention [Problem to be solved by the invention]

[0004] The mixing and grinding apparatus described in Patent Document 1 does not mention maintaining the quality of the produced fusion material even if the operating condition is affected by external disturbances such as a sudden change in the environment or mechanical malfunction.

[0005] In view of the above-mentioned problems, the present invention aims to provide a mixing and melting device and an auxiliary control method for the mixing and melting device that can maintain the quality of the fusion material produced even if the operating state is affected by external disturbances such as a sudden change in the environment or a malfunction of the machine. [Means for solving the problem]

[0006] The mixing and melting device of this embodiment is A motor that generates driving force; A rotating shaft rotated by the motor; a plurality of blade members formed on an outer periphery of the rotating shaft on the other side in the axial direction; a material input section into which material is input; a mixing vessel connected below the material input section, through which the rotating shaft passes, for mixing and melting the materials input into the material input section; Equipped with A mixing and melting device for mixing and melting the materials by the plurality of blade members according to a predetermined operation process, A storage unit that stores a work process; A working unit that operates according to the work process stored in the memory unit; A detection unit that detects an operating state of the working unit; a control unit that, when the working unit is operated according to the work process stored in the memory unit based on the result detected by the detection unit, predicts a predicted melting point arrival time, which is the time it takes for the material to reach its melting point, and controls the working unit so that, when an absolute value of a difference between a predetermined set melting point arrival time stored in the memory unit and the predicted melting point arrival time is equal to or greater than a predetermined time threshold, the absolute value of the difference between the set melting point arrival time and the predicted melting point arrival time becomes smaller; It further comprises: Effect of the Invention

[0007] According to the mixing and melting apparatus and the auxiliary control method for the mixing and melting apparatus of the present invention, even if the operating state is affected by external disturbances such as a sudden change in the environment or a malfunction of the machine, the quality of the produced fusion material can be maintained. [Brief description of the drawings]

[0008] [Figure 1] An example of a mixed melting system to which the machine learning device of this embodiment is applied is shown. [Diagram 2] 2 is a partially enlarged view of a blade member and a supply screw in the mixing and melting device of the present embodiment. FIG. [Diagram 3] 1 is a skeleton block diagram of the entire system of a mixing and melting device according to an embodiment of the present invention; [Figure 4] 1 shows an example of a system configuration of a mixing and melting apparatus 1 to which a machine learning device according to this embodiment is applied. [Diagram 5] 1 shows an example of a block diagram of a machine learning device according to an embodiment of the present invention. [Figure 6] 1 illustrates an example of an input unit of the machine learning device according to the present embodiment. [Figure 7] 1 illustrates an example of a mixed melting information acquisition unit of the machine learning device according to the present embodiment. [Figure 8] 1 shows an example of a neural network model used in the machine learning device according to the present embodiment. [Figure 9] 1 shows an example of a flowchart of a machine learning method performed by the machine learning device according to the present embodiment. [Figure 10] 1 shows an example of a block diagram of a mixed melting information inference device according to an embodiment of the present invention. [Figure 11] 1 shows an example of a flowchart of a mixed melt information inference method by the mixed melt information inference device according to the present embodiment. [Figure 12] 1 shows an example of a flowchart of an auxiliary control method for the mixing and melting apparatus 1 according to the present embodiment. [Figure 13] 4 shows a first example of an auxiliary control method according to the present embodiment. [Figure 14] 2 shows a second example of an auxiliary control method according to the present embodiment. [Figure 15] 11 shows a third example of an auxiliary control method according to the present embodiment. [Figure 16] 4 shows a fourth example of the auxiliary control method according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The mixing and melting apparatus 1 of this embodiment will be specifically described with reference to the drawings.

[0010] Fig. 1 shows an example of a mixing and melting system 100 according to an embodiment of the present invention. Fig. 2 shows a partially enlarged view of a blade member 10 and a supply screw 12 in the mixing and melting device 1 of the present embodiment. Fig. 3 is a skeleton block diagram showing the entire system of the mixing and melting device 1 of the present embodiment.

[0011] The mixed melting system 100 according to the present embodiment includes, as its main components, a mixed melting device 1, a machine learning device 60, and a mixed melting information inference device 70. The control unit 40 of the mixed melting device 1, the machine learning device 60, and the mixed melting information inference device 70 are connected to, for example, a wired or wireless network 90, and are configured to be able to transmit and receive various data. Note that the number of the control units 40, the machine learning devices 60, and the mixed melting information inference devices 70 of the mixed melting device 1 and the connection configuration of the network 90 are not limited to the example of FIG. 1, and may be changed as appropriate.

[0012] The control unit 40, the machine learning device 60, and the mixed melting information inference device 70 of the mixed melting device 1 may be configured with one or more arithmetic processing devices (CPU, MPU, GPU, DSP, etc.). The control unit 40, the machine learning device 60, and the mixed melting information inference device 70 may be implemented using, for example, a circuit board with a central processing unit (CPU) at its center, or a dedicated circuit board. The control unit 40, the machine learning device 60, and the mixed melting information inference device 70 are supplied with power from a commercial power source via a power line (not shown). The control unit 40 may be installed separately from the mixed melting device 1.

[0013] The memory unit 41 of the mixing and melting device 1 stores various data and programs, and may be composed of, for example, a volatile memory (DRAM, SRAM, etc.) that functions as a main memory and a non-volatile memory (ROM, flash memory, etc.). The memory unit 41 may be included in the control unit 40. Alternatively, it may be installed separately from the mixing and melting device 1.

[0014] The mixing and melting device 1 of this embodiment includes a machine base 2, a cylindrical mixing container 3 arranged horizontally on the machine base 2, a motor 8 as a drive source installed on the machine base 2, a rotating shaft 5 rotated by the motor 8, a plurality of blade members 10 arranged on the rotating shaft 5 in the mixing container 3, a material input section 14 for inputting materials, and a supply screw 12 for supplying the materials inputted to the material input section 14 to the mixing container 3. The material input section 14 has an upper hopper 14a and a material inflow section 14b located below the hopper 14a and sandwiching an opening / closing section 15 therebetween.

[0015] The motor 8 is driven by a power source (not shown). The motor 8 transmits a driving force to the rotating shaft 5, and rotates the blade member 10 and the supply screw 12 via the rotating shaft 5. The motor 8 can control the number of rotations so that the peripheral speed of the tip of the blade member 10 is within a range of 5 m / s to 50 m / s. The output shaft of the motor 8 and the rotating shaft 5 are connected by a slippery V-belt 7 so that when a sudden change in load torque occurs in the rotating shaft 5, the load torque is not transmitted to the motor 8. The output shaft of the motor 8 and the rotating shaft 5 may be connected via a brake, a clutch, or the like. The rotating shaft 5 may be formed coaxially with the output shaft of the motor 8.

[0016] The rotating shaft 5 is supported horizontally by bearings 4, 4, and is disposed coaxially through the center of the mixing vessel 3. One end of the rotating shaft 5 is in rotational communication with a motor 8 serving as a drive source via a pulley 6 and a V-belt 7. The rotating shaft 5 is hollow with a small diameter hole formed in the axial center for circulating fluid, and is provided with rotary joints 9 on both ends, so that fluid is supplied axially into the inside of the rotating shaft 5 through the rotary joints 9.

[0017] As shown in Fig. 2, a total of six blade members 10a-10f, each having a rectangular cross section and an overall rectangular shape, are provided on the outer periphery of the rotating shaft 5, which is disposed penetrating through the mixing vessel 3, at intervals of 180 degrees in the circumferential direction of the rotating shaft 5 and spaced apart in the axial direction. As shown in Fig. 2, the thickness of the blade members 10a-10f is formed such that about 40% of the outer periphery side is thicker than the inner periphery side, so that the material is crushed, mixed, and melted effectively. When using materials that have already been crushed, the crushing process is not necessary.

[0018] Of these, the blade members 10a and 10f at both ends in the axial direction are fixed to the outer periphery of the rotating shaft 5 at an inclination of about 15 degrees from the tip to the base of the blade member 10 so that their front edges come into sliding contact with the inner surfaces of the vertical walls 11, 11 at both ends of the mixing vessel 3 with almost no gap when rotating clockwise as viewed from the right side of Figure 1.

[0019] The four blade members 10b, 10c, 10d, and 10e in the middle section are fixed to the outer circumferential surface of the rotating shaft 5 in a staggered pattern, inclined from the tip to the base of each blade, and are arranged so that their leading edges face both ends of the mixing vessel 3 during rotation. That is, the four blade members 10b, 10d, 10c, and 10e are opposed to each other in the axial direction as shown in Fig. 2, and are arranged on the rotating shaft 5 at a mounting angle (angle with respect to the circumferential direction) of 15 degrees so that the opposing distance between them narrows in the rotation direction.

[0020] In addition, in the direction of the rotating shaft 5, the motor 8 side of the mixing vessel 3 is the material supply section 3a, and the opposite side of the motor 8 is the material mixing section 3b. A spiral supply screw 12 formed on the outer periphery of the rotating shaft 5 is housed in the material supply section 3a. The material supply section 3a surrounds the supply screw 12. A material input section 14 is provided above the material supply section 3a. After the material is input into the material input section 14, an opening / closing section 15 is provided that can be closed airtightly during crushing, mixing, and melting. In addition, a pair of balance wheels 16 are provided on both sides of the blade member 10 of the rotating shaft 5 and the supply screw 12 to ensure smooth rotation.

[0021] The material mixing section 3b surrounds the blade member 10 fixed to the rotating shaft 5. The material mixing section 3b has a material supply section 3a on the upstream side. The material fed into the material supply section 3a is moved to the material mixing section 3b by a supply screw 12 in the material supply section 3a. The material is mixed in the material mixing section 3b by the blade member 10. It is to be noted that the material may be fed from above the material mixing section 3b without using the material supply section 3a and the supply screw 12.

[0022] 3, a continuous water passage 24 is formed in the peripheral wall of the mixing vessel 3 and in the center of the rotating shaft 5, and a fluid circulation section 22 is formed that can adjust the temperature in the peripheral wall of the mixing vessel 3 and the rotating shaft 5 by circulating the fluid. The fluid circulation section 22 adjusts the temperature of the fluid by a circulating fluid control section 23, adjusts the temperatures of the mixing vessel 3, the rotating shaft 5, etc., and returns to the circulating fluid control section 23. The circulating fluid control section 23 controls the temperature, flow rate, etc. of the fluid according to instructions from the control section 40.

[0023] Here, the fluid used is oil, air, tap water, cold water, warm water or hot water. Therefore, the mixing and melting device 1 of this embodiment can appropriately adjust the pressure, temperature, humidity, etc. in the mixing container 3. In addition, for example, when air or tap water is used, it can be operated at low cost, when cold water is used, it can cool the inside of the mixing container 3, and when warm water or hot water is used, it can warm the inside of the mixing container 3.

[0024] In addition, a discharge port lid 17 for removing the molten material is provided on the bottom wall of the mixing vessel 3. The discharge port lid 17 is rotatably supported by a shaft 18, and the shaft 18 is connected to rotary cylinders 19, 19 so as to be able to be opened and closed.

[0025] In addition, the collars 20, 20 on both sides shown in Figure 2 are for sending air to the mixing vessel 3, and the continuous grooves on each end are composed of right-handed and left-handed spiral grooves so that air is sent to the mixing vessel 3 by the rotation of the rotating shaft 5.

[0026] The control unit 40 is also connected to the motor 8 via a connection cable, and receives a continuous electric signal representing the load torque of the main shaft from the motor 8. The control unit 40 may control the timing of opening and closing the discharge port lid 17 of the mixing vessel 3 based on a change in the load torque acting on the main shaft of the motor 8 in response to the grinding, mixing, and melting of the material in the mixing vessel 3, thereby removing the ground, mixed, and melted material.

[0027] A method for producing a fused material using the mixing and melting device 1 of this embodiment will be described. A user puts materials into the mixing container 3 of the mixing and melting device 1 through an opening (not shown), drives the motor 8, and rotates the rotating shaft 5, the blade member 10, and the supply screw 12 to finely crush the materials. The size of the crushed particles is preferably about 2 to 7 mm. The crushing step is not performed when materials that have been crushed in advance by another device are simply put in.

[0028] Subsequently, the motor 8 is driven to rotate the rotary shaft 5, the blade member 10, and the supply screw 12, thereby mixing the pulverized materials. The rotation speed of the rotary shaft 5 is preferably set to 500 rpm or more.

[0029] In addition, in the production of the fusion material of this embodiment, it is not necessary to use additives for compatibility. Not using additives improves environmental friendliness. Furthermore, in this embodiment, it is preferable to supply a fluid to the material by the fluid supply unit 30. By supplying a fluid, the internal pressure can be increased in a later process. The fluid may be supplied to the inside of the mixing container 3 in advance, or may be supplied to the inside of the mixing container 3 during operation.

[0030] Here, the fluid used is air, tap water, cold water, warm water, or hot water. Therefore, the mixing and melting device 1 of this embodiment can appropriately adjust the pressure, temperature, humidity, and the like in the mixing container 3. In addition, for example, when air or tap water is used, it can be operated at low cost, when cold water is used, it can cool the inside of the mixing container 3, and when warm water or hot water is used, it can warm the inside of the mixing container 3.

[0031] Next, the motor 8 is driven to rotate the rotating shaft 5, the blade member 10, and the supply screw 12. When the blade member 10 is rotated at high speed, the temperature inside the mixing vessel 3 becomes high, at 100°C or higher, due to the movement of the materials themselves and friction caused by the materials colliding with each other and shearing them. After that, steam is generated from the fluid, pressure is applied inside the mixing vessel 3, and each material melts.

[0032] Next, the motor 8 is driven to rotate the rotating shaft 5, the blade member 10, and the supply screw 12 to advance the reaction of the materials. As the reaction progresses, the materials are integrated. At the same time, the fluid is vaporized and discharged to the outside from an outlet (not shown) of the mixing vessel 3. Therefore, the inside of the mixing vessel 3 becomes dry, and a fusion product from which moisture and the like have been removed is obtained.

[0033] The resulting fusion product is a new material in which multiple materials with different melting points are uniformly fused at the molecular level, and since it can be molded by injection, extrusion, blowing, pressing, etc., it can be used for a variety of purposes.

[0034] In addition, the method for producing a fusion material of this embodiment is performed in less than 1800 seconds. Usually, the more heat input a material receives, the more severe its deterioration becomes. In the method for producing a fusion material of this embodiment, heat is not applied from the outside, and the time for which heat is applied to the material is short. Therefore, the fusion material produced by the method for producing a fusion material of this embodiment is less likely to deteriorate and can maintain its strength. In addition, since the fusion material produced by the method for producing a fusion material of this embodiment is less likely to deteriorate, the completed fusion product can be reused.

[0035] The mixing and melting apparatus 1 of this embodiment also has a fluid supplying section 30. The fluid supplying section 30 is connected to the material input section 14 of the mixing and melting apparatus 1. The fluid supplying section 30 has a supply pipe 31, a first flow control section 32 installed in the middle of the supply pipe 31 communicating with the material inlet section 14b, a first fluid supplying member 33 installed at the tip of the supply pipe 31 communicating with the material inlet section 14b, a second flow control section 34 installed in the middle of the supply pipe 31 communicating with the mixing container 3, and a second fluid supplying member 35 installed at the tip of the supply pipe 31 communicating with the mixing container 3.

[0036] Supply pipe 31 is a pipe through which a fluid flows, such as air, tap water, cold water, warm water, hot water, or a circulating fluid adjusted by circulating fluid control unit 23 shown in Fig. 3. The amount of fluid flowing through supply pipe 31 is adjusted by at least one of first flow rate control unit 32 and second flow rate control unit 34. First flow rate control unit 32 and second flow rate control unit 34 are installed midway through supply pipe 31, and the flow rate of the fluid passing through supply pipe 31 may be controlled by adjusting, for example, the rotation angle of a valve.

[0037] The first fluid supplying member 33 in this embodiment is installed in a hole formed in the material inlet portion 14b, and the second fluid supplying member 35 is installed in a hole formed in the mixing vessel 3. In the mixing and melting device 1 of this embodiment, at least one hole may be formed in the material inlet portion 14b and the mixing vessel 3, and at least one first fluid supplying member 33 and second fluid supplying member 35 may be installed. The hole may be formed in the hopper 14a.

[0038] The first fluid supply member 33 and the second fluid supply member 35 may be a nozzle or shower that directly or mist-sprays the fluid. Fluids such as air, tap water, cold water, warm water, hot water, or circulating fluid that have flowed through the supply pipe 31 are sprayed from the first fluid supply member 33 and the second fluid supply member 35. The sprayed fluid is supplied to the material inlet 14b or the mixing vessel 3 and mixed with the materials. The fluid may be supplied to the material inlet 14b in advance, or may be supplied to the material inlet 14b during operation. At least one of the multiple first fluid supply members 33 and second fluid supply members 35 may be operated, but it is preferable that all of the multiple first fluid supply members 33 and second fluid supply members 35 are operated to avoid uneven supply.

[0039] The mixing and melting apparatus 1 of this embodiment further includes a fluid circulation section 22 that adjusts the temperature of the mixing vessel 3 by circulating a circulating fluid, and the fluid circulation section 22 has a water passage 24 formed continuously in the peripheral wall of the mixing vessel 3, communicates the water passage 24 with the supply pipe 31, and uses the circulating fluid as the fluid. Therefore, the mixing and melting apparatus 1 of this embodiment can appropriately adjust the temperature inside the mixing vessel 3.

[0040] In this way, by supplying fluids from the first fluid supply member 33 and the second fluid supply member 35, the amount of fluid in the mixing vessel 3 can be adjusted at any time before, during, and after the fusion of the materials. For example, a fluid such as water can be added to the materials before melting, and the internal pressure can be increased in a later process. Also, the temperature in the mixing vessel 3 after melting can be adjusted. Furthermore, the appropriate amount of fluid to be added for each material to be fused can be automatically controlled and managed, and quantitative mass production can be achieved. Also, a fluid such as water can be added after the materials are charged, and the materials are charged in a dry state, so that charging defects are less likely to occur.

[0041] In addition, by spraying mist from the first fluid supply member 33 and the second fluid supply member 35 before melting, the fluid can be uniformly sprayed onto the material before melting. Therefore, the fluid is uniformly applied to the entire fusion material, and heat can be uniformly transferred during fusion or temperature adjustment. In addition, after fusion, a product with uniform physical properties and high strength can be obtained. During cooling, the fused material can be rapidly cooled, and thermal deterioration of the material can be mitigated.

[0042] FIG. 4 shows an example of a system configuration of a mixing and melting apparatus 1 to which the machine learning device 60 according to this embodiment is applied.

[0043] This mixing and melting device 1 may be a device that actually uses data learned by this machine learning device 60 in the future, or may be a test device that simulates the same structure as the device that will actually be used.

[0044] The mixing and melting apparatus 1 has an operation panel 42 operated by an operator, a control unit 40 that drives and controls the first flow rate control unit 32, the second flow rate control unit 34, and the circulating fluid control unit 23 in response to commands from the operation panel 42, and a memory unit 41 that stores in advance the drive of the first flow rate control unit 32, the second flow rate control unit 34, and the circulating fluid control unit 23, and the flow rates and temperatures of the fluids flowing through them. The memory unit 41 may be included in the control unit 40 or may be separate.

[0045] Furthermore, the mixing and melting apparatus 1 has an inverter 43 that receives a signal from the control unit 40 and controls the motor 8 that rotates the rotating shaft 5, a torque detection unit 44 that detects the torque of the motor 8, an internal pressure detection unit 45 that detects the pressure inside the mixing container 3, an oxygen concentration detection unit 46 that detects the oxygen concentration inside the mixing container 3, an internal humidity detection unit 47 that detects the humidity inside the mixing container 3, an internal temperature detection unit 48 that detects the temperature inside the mixing container 3, and an external wall temperature detection unit 49 that detects the temperature of the external wall of the mixing container 3. Note that it is sufficient to have at least one of each of the detection units 43 to 49.

[0046] The control unit 40 has a command unit 40a that sends command values ​​to each control unit, and a calculation unit 40b that calculates the command values ​​from the detection values ​​of each detection unit 43 to 49. The memory unit 41 stores a table or a calculation formula for converting the detection values ​​of each detection unit 43 to 49 into command values. The operation panel 42, the control unit 40, or the memory unit 41 may be installed separately from the mixing and melting apparatus 1.

[0047] Fig. 5 shows an example of a block diagram of the machine learning device 60 according to the present embodiment. Fig. 6 shows an example of the input unit 50 of the machine learning device 60 according to the present embodiment. Fig. 7 shows an example of the mixed melting information acquisition unit 54 of the machine learning device 60 according to the present embodiment.

[0048] The input unit 50 has at least one of a filler material information acquisition unit 51, a resin material information acquisition unit 52, and an additive material information acquisition unit 53, and a mixed melting information acquisition unit 54 which indicates the operating state of the mixing and melting device 1. The input unit 50 may be configured to automatically input information using a sensor or the like, or may be configured to input information by a user.

[0049] The filler material information acquisition unit 51 acquires information about the filler material as input data. The information about the filler material includes, for example, material name information 51a of the filler material to be used and characteristic information of the filler material. The characteristic information of the filler material may include at least one of type information 51b inputting whether the filler material is plant-based or animal-based, property information 51c of the filler material such as specific gravity, melting point, hydrophilicity, etc., blending ratio information 51d of the filler material, and water content information 51e of the filler material.

[0050] The resin material information acquisition unit 52 acquires information about the resin material as input data. The information about the resin material includes, for example, material name information 52a of the resin material used and characteristic information of the resin material. The characteristic information of the resin material may include at least one of type information 52b inputting whether the resin material is crystalline or non-crystalline, property information 52c such as specific gravity, melting point, viscosity, hydrophilicity, and fluidity (Melt Mass-Flow Rate (MFR)) of the resin material, blending ratio information 52d of the resin material, and water content information 52e of the resin material.

[0051] The additive material information acquisition unit 53 acquires information on the additive material as input data. The information on the additive material includes, for example, material name information 53a of the additive material to be used and characteristic information of the additive material. The characteristic information of the additive material may include at least one of type information 53b inputting whether the additive material is a plasticizer, stabilizer, antioxidant, ultraviolet absorber, lubricant, release agent, antistatic agent, colorant, foaming agent, flame retardant, etc., property information 53c of the additive material such as specific gravity, melting point, hydrophilicity, etc., mixture ratio information 53d of the additive material, and water content information 53e of the additive material.

[0052] The mixed melting information acquisition unit 54 acquires information on the operating state of the mixed melting device 1 as output data. The mixed melting information may include at least one of motor rotation information 54a indicating the rotation time or number of rotations of the motor 8, added fluid information 54b indicating the timing or amount of fluid added from the fluid supply unit 30, and circulating fluid information 54c indicating the temperature of the circulating fluid by the fluid circulating unit 22. The mixed melting information acquisition unit 54 may acquire at least one of the motor rotation information 54a, added fluid information 54b, and circulating fluid information 54c in chronological order by the control unit 40 having a timer function, detection by the detection units 43 to 49, or manual input, etc.

[0053] When inputting data to the input unit 50 manually, an operator terminal 80 may be used. The operator terminal 80 is connected to the input unit 50 and the machine learning device 60 via a network 90. ​​The operator terminal 80 may also be connected to the mixing and melting device 1. The operator terminal 80 may be a general-purpose product, and includes a processor, a memory, an input device, a display device, a storage device, a communication interface, an external device interface, an input / output device interface, and a media input / output unit. The above components may be omitted as appropriate depending on the purpose for which the operator terminal 80 is used.

[0054] The machine learning device 60 includes a learning data acquisition unit 600, a learning data storage unit 601, a machine learning unit 602, and a trained model storage unit 603. The machine learning device 60 is configured, for example, by a computer or the like. In this case, the learning data acquisition unit 600 is configured by a communication interface or an input / output device or the like, the machine learning unit 602 is configured by a processor or the like, and the learning data storage unit 601 and the trained model storage unit 603 are configured by storage or the like.

[0055] The learning data acquisition unit 600 is an interface unit that is connected to various external devices via a network 90 or the like and acquires learning data including at least input data. The external devices are, for example, an input unit 50 connected to the mixing and melting device 1, an input unit 50 provided in a simulated test device, an operator terminal 80 used by an operator, or the like.

[0056] The learning data storage unit 601 is a database that stores one or more sets of learning data acquired by the learning data acquisition unit 600. The specific configuration of the database that constitutes the learning data storage unit 601 may be designed as appropriate.

[0057] The machine learning unit 602 performs machine learning using the learning data stored in the learning data storage unit 601. That is, the machine learning unit 602 inputs a plurality of sets of learning data to the learning model 610, and causes the learning model 610 to learn the correlation between the input data included in the learning data and the setting data of the mixing and melting apparatus 1, thereby generating a trained learning model 610. In this embodiment, a case where a neural network is adopted as a specific method of supervised learning by the machine learning unit 402 will be described.

[0058] The trained model storage unit 603 is a database that stores the trained learning model 610 generated by the machine learning unit 602. The trained learning model 610 stored in the trained model storage unit 603 is provided to an actual system via an arbitrary communication network, recording medium, etc. Note that, although the training data storage unit 601 and the trained model storage unit 603 are shown as separate storage units in FIG. 5, they may be configured as a single storage unit.

[0059] The learning data includes at least one of filler material information, resin material information, and additive material information as input data. When "supervised learning" is adopted as machine learning, the learning data further includes mixed melting information as output data associated with the input data. In supervised learning, the output data is referred to as, for example, teacher data or correct answer label.

[0060] Therefore, the learning data according to this embodiment is configured by associating input data including at least one of filler material information, resin material information, and additive material information with output data including mixed melting information.

[0061] Here, the relationship between the input data included in the learning data (at least one of the filler material information, resin material information, and additive material information) and the mixed melting information will be described.

[0062] The mixed melting information is determined almost entirely by at least one of the filler material information, resin material information, and additive material information. That is, by inputting the information on the materials used as input data for learning, it becomes possible to infer the mixed melting information as the operating conditions of the mixed melting device 1.

[0063] When acquiring the above-mentioned learning data, the learning data acquiring unit 600 uses at least one of the filler material information, the resin material information, and the additive material information stored in the storage unit 41 as input data.

[0064] When an operator obtains mixing and melting information as an operating condition of the mixing and melting device 1 and inputs the information to the operator terminal 80, the learning data acquisition unit 600 acquires the setting values ​​inputted at the operator terminal 80 as output data (teaching data) from the operator terminal 80. The learning data acquisition unit 600 then configures one learning data by associating the input data with the output data, and stores the learning data in the learning data storage unit 601.

[0065] FIG. 8 shows an example of a neural network model used in the machine learning device 60 according to this embodiment.

[0066] The learning model 610 is configured as a neural network model shown in Fig. 8. The neural network model is configured from one neuron (x1 to xl) in an input layer, m neurons (y11 to y1m) in a first hidden layer, n neurons (y21 to y2n) in a second hidden layer, and o neurons (z1 to zo) in an output layer.

[0067] Each neuron in the input layer is associated with a respective input data included in the learning data. Each neuron in the output layer is associated with a respective output data included in the learning data. Note that a predetermined pre-processing may be performed on the input data before it is input to the input layer, and a predetermined post-processing may be performed on the output data after it is output from the output layer.

[0068] The first and second hidden layers are also called hidden layers, and the neural network may have a plurality of hidden layers in addition to the first and second hidden layers, or may have only the first hidden layer as a hidden layer. Synapses connecting neurons in each layer are laid between the input layer and the first hidden layer, between the first hidden layer and the second hidden layer, and between the second hidden layer and the output layer, and each synapse is assigned a weight wi (i is a natural number).

[0069] A neural network model uses training data to learn the correlation between the input data and output data by inputting input data contained in the training data into an input layer and comparing the output data output from the output layer as an inference result with the output data (teacher data) contained in the training data.

[0070] Specifically, input data included in the learning data is input to each neuron in the input layer. The value of each neuron in the output layer is calculated by performing a process for all neurons other than the input layer, in which the value of the neuron on the input side connected to the neuron in question is calculated as the sum of a sequence of multiplication values ​​of the value of the neuron on the input side connected to the neuron and the weight wi associated with the synapse connecting the neuron on the output side and the neuron on the input side.

[0071] Then, the values ​​(z1 to zo) output to each neuron in the output layer as the inference results are compared with the values ​​(t1 to to) of the teacher data corresponding to each of the output data included in the learning data to determine the error, and a process (backpropagation) is performed to adjust the weights wi associated with each synapse so that the error is reduced.

[0072] When a specified learning termination condition is met, such as the above series of steps being repeated a specified number of times or the above error being smaller than an allowable value, the machine learning is terminated and a trained neural network model (all weights wi associated with each synapse) is generated.

[0073] FIG. 9 shows an example of a flowchart of a machine learning method performed by the machine learning device 60 according to this embodiment.

[0074] First, in step S11, the learning data acquisition unit 600 prepares a desired number of pieces of learning data as a preliminary preparation for starting machine learning, and stores the prepared learning data in the learning data storage unit 601. The number of pieces of learning data to be prepared here may be set in consideration of the inference accuracy required for the learning model 610 to be finally obtained.

[0075] There are several methods for preparing learning data. For example, when inferring mixing and melting information in a specific mixing and melting device 1 or test device, at least one of filler material information, resin material information, and additive material information is obtained, and an operator uses the operator terminal 80 to input the results in association with these inputs, thereby preparing input data and output data that constitute the learning data. By repeating this process, it is possible to prepare multiple sets of learning data.

[0076] Next, in step S12, the machine learning unit 602 prepares a pre-learning model 610 to start machine learning. The pre-learning model 610 prepared here is configured with the neural network model exemplified in FIG. 8, and the weights of each synapse are set to initial values. Each neuron in the input layer is associated with at least one of filler material information, resin material information, and additive material information, which are input data included in the learning data. Each neuron in the output layer is associated with mixed melting information.

[0077] Next, in step S13, the machine learning unit 602 acquires one piece of learning data from the multiple sets of learning data stored in the learning data storage unit 601, for example, at random.

[0078] Next, in step S14, the machine learning unit 602 inputs the input data included in one learning data to the input layer of the prepared learning model 610 before learning (or during learning). As a result, output data is output as an inference result from the output layer of the learning model 610, but the output data is generated by the learning model 610 before learning (or during learning). Therefore, in the state before learning (or during learning), the output data output as an inference result indicates information different from the output data (teacher data) included in the learning data.

[0079] Next, in step S15, the machine learning unit 602 performs machine learning by comparing output data (teacher data) included in one learning data acquired in step S12 with output data output from the output layer as an inference result in step S13 and adjusting the weight of each synapse. In this way, the machine learning unit 602 causes the learning model 610 to learn the correlation between the input data and the output data.

[0080] Next, in step S16, the machine learning unit 602 determines whether or not it is necessary to continue machine learning based on, for example, the error between the output data and the teacher data and the remaining amount of unlearned learning data stored in the learning data storage unit 601.

[0081] In step S16, if the machine learning unit 602 determines to continue the machine learning (No in step S16), the process returns to step S13, and the process of steps S13 to S15 is performed multiple times on the learning model 610 under learning, using unlearned learning data. On the other hand, in step S16, if the machine learning unit 602 determines to end the machine learning (Yes in step S16), the process proceeds to step S17.

[0082] Then, in step S17, the machine learning unit 602 stores the trained learning model 610 generated by adjusting the weights associated with each synapse in the trained model storage unit 603, and ends the series of machine learning methods shown in Fig. 9. In the machine learning method, step S11 corresponds to a learning data storage step, steps S12 to S16 correspond to a machine learning step, and step S17 corresponds to a trained model storage step.

[0083] As described above, according to the machine learning device 60 and machine learning method of this embodiment, it is possible to provide a learning model 610 that can infer mixed melting information from at least one of the filler material information, resin material information, and additive material information stored in the memory unit 41 as input data included in the learning data.

[0084] FIG. 10 shows an example of a block diagram of a mixed melting system 100 according to this embodiment.

[0085] The mixed melting information inference device 70 includes an input data acquisition unit 700, an inference unit 701, a trained model storage unit 702, and an output processing unit 703. The mixed melting information inference device 70 is composed of, for example, a computer. In this case, the input data acquisition unit 700 is composed of a communication interface or an input / output device, the inference unit 701 and the output processing unit 703 are composed of a processor, and the trained model storage unit 702 is composed of a storage. The mixed melting system 100 may be incorporated into the mixed melting device 1, or may be incorporated into a higher-level management device of the mixed melting device 1 (for example, an equipment controller, an equipment management system that manages multiple equipment, etc.).

[0086] The input data acquisition unit 700 is an interface unit that is connected to the memory unit 41 and the input unit 50 provided in the mixing and melting device 1, and acquires input information (at least one of filler material information, resin material information, or additive material information) stored in the memory unit 41.

[0087] The inference unit 701 inputs the input data acquired by the input data acquisition unit 700 to the learning model 610, and performs an inference process to infer mixed melting information. For the inference process, the machine learning device 60 and the trained learning model 610 in which supervised learning has been performed by the machine learning method are used.

[0088] The inference unit 701 not only performs inference processing using the learning model 610, but also includes a pre-processing function of adjusting the input data acquired by the input data acquisition unit 700 into a desired format and inputting the adjusted data to the learning model 610 as pre-processing of the inference processing, and a post-processing function of finally inferring mixed melting information by applying a predetermined logical formula or calculation formula to the value of the output data output from the learning model 610 as post-processing of the inference processing. Note that the inference results of the inference unit 701 are preferably stored in the trained model storage unit 702 or another storage device (not shown), and past inference results can be used as learning data used for online learning or re-learning, for example, to further improve the inference accuracy of the learning model 610.

[0089] The trained model storage unit 702 is a database that stores trained learning models 610 used in the inference process of the inference unit 701. The number of learning models 610 stored in the trained model storage unit 702 is not limited to one. For example, multiple learning models 610 with different numbers of input data or different machine learning methods may be stored and selectively usable.

[0090] The output processing unit 703 performs processing to output the inference result of the inference unit 701, that is, the mixed melting information. As a specific output means, various means can be adopted. For example, the output processing unit 703 may notify the mixed melting information to an operator by display or sound, or may transmit the mixed melting information as history to, for example, the mixed melting device 1 or a higher-level management device (not shown) of the mixed melting device 1, store the information in a memory unit of the management device of the mixed melting device 1, or use the information for driving control of the motor 8.

[0091] FIG. 11 shows an example of a flowchart of a mixed melting information inference method using the mixed melting device 1 according to this embodiment.

[0092] First, in step S21, the input data acquisition unit 700 acquires the input data (at least one of filler material information, resin material information, and additive material information) input from the operation panel 42 and stored in the storage unit 41.

[0093] Next, in step S22, the inference unit 701 performs preprocessing on the input data, inputs the data to the input layer of the learning model 610, and obtains the output data output from the output layer of the learning model 610.

[0094] Next, in step S23, the inference unit 701 infers mixed melting information.

[0095] As described above, according to the mixed melt information deductive device 70 and the mixed melt information deductive method of this embodiment, mixed melt information can be deduced without relying on the experience of the worker.

[0096] FIG. 12 shows a flowchart of the auxiliary control method by the mixing and melting device 1 according to this embodiment. FIG. 13 shows a first example of the auxiliary control method according to this embodiment. FIG. 14 shows a second example of the auxiliary control method according to this embodiment. In this embodiment, the operation of the mixing and melting device 1 is divided into the steps of material input + stirring, crushing + dehydration, dispersion + melting, cooling, and discharge, and auxiliary control is performed in the dispersion + melting step. Note that auxiliary control may be performed in any step, or may be performed in multiple steps.

[0097] In addition, the auxiliary control is not limited to the mixed melting system 100 of this embodiment, and can be used in various forms of mixed melting devices 1 that automatically execute work processes in a predetermined manner. For example, it may be used in a mixed melting device 1 that automatically executes work processes stored in advance in a program or the like by inputting input data without using the machine learning device 60 and the mixed melting information inference device 70 in Figs. 1 and 4, and performs output processing. The storage unit 41 that stores the work processes may be installed in the mixed melting device 1, or may be a storage device of another device, a cloud, or the like.

[0098] The mixing and melting device 1 of this embodiment can automatically execute the work process stored in advance in the storage unit 41 by inputting input data, and can perform output processing. However, for example, if there is an influence of a sudden change in the environment or a disturbance such as a malfunction of the machine, the time until the material reaches the melting point at which it melts may change as shown in Fig. 13, and the quality of the manufactured fused material may decrease. Therefore, the mixing and melting device 1 of this embodiment performs an operation state change rate correction process, which is an auxiliary control to adjust the time until the material reaches the melting point.

[0099] In the auxiliary control method by the mixing and melting device 1 according to this embodiment, first, in step S31, the detection units 43 to 49 shown in Fig. 4 detect the operating state. The detection units 43 to 49 for detecting the operating state in the mixing and melting device 1 of this embodiment may be, for example, at least one of the inverter 43 that receives a signal from the control unit 40 and controls the motor 8 that rotates the rotating shaft 5, the torque detection unit 44 that detects the torque in the mixing container 3, the internal pressure detection unit 45 that detects the pressure in the mixing container 3, the oxygen concentration detection unit 46 that detects the oxygen concentration in the mixing container 3, the internal humidity detection unit 47 that detects the humidity in the mixing container 3, the internal temperature detection unit 48 that detects the temperature in the mixing container 3, or the outer peripheral wall temperature detection unit 49 that detects the temperature of the outer peripheral wall of the mixing container 3.

[0100] Next, in step S32, the control unit 40 determines whether the rate of change of the operating state is equal to or greater than a predetermined change rate threshold value α. If the rate of change of the operating state is smaller than the change rate threshold value α, the process proceeds to step 36. If the rate of change of the operating state is equal to or greater than the change rate threshold value α, in step 33, the control unit 40 calculates a predicted melting point arrival time T1.

[0101] For example, in the present embodiment, when the temperature change rate of the internal temperature or the outer wall temperature of the mixing vessel 3 is set as the operating state change rate, the operating state change rate correction process is set as the temperature change rate correction process, and it is determined whether the temperature change rate is equal to or greater than a predetermined change rate threshold value α. If the temperature change rate is equal to or greater than the change rate threshold value α, there is a risk that disturbances will affect the mixing vessel 3, and the time required to reach the melting point at which the material melts may change. Therefore, the auxiliary control method of the present embodiment calculates a predicted melting point arrival time T1.

[0102] Next, in step 34, the control unit 40 compares whether the absolute value of the difference between the preset melting point arrival time T0 and the predicted melting point arrival time T1 is smaller than a predetermined time threshold value β. If the absolute value of the difference between the preset melting point arrival time T0 and the predicted melting point arrival time T1 is equal to or greater than the predetermined time threshold value β, in step 35, the control unit 40 executes an operating state change rate correction process for correcting the operating state change rate. If the absolute value of the difference between the preset melting point arrival time T0 and the predicted melting point arrival time T1 is smaller than the predetermined time threshold value β, the process proceeds to step 36.

[0103] In the first example of the auxiliary control method shown in Fig. 13, when the difference between the set melting point arrival time T0 and the predicted melting point arrival time T1 is a positive value, a temperature change rate reduction process is executed as an operating state change rate correction process. The temperature change rate reduction process reduces the temperature change rate by reducing the rotation speed of the motor 8, adding cooling water by the fluid supply unit 30, circulating cooling water by the fluid circulation unit 22, etc. By reducing the temperature change rate, the predicted melting point arrival time T1 becomes longer. Here, at least one of the motor 8, the fluid supply unit 30, and the fluid circulation unit 22 constitutes a working unit.

[0104] Moreover, in the second example of the auxiliary control method shown in Fig. 14, when the difference between the set melting point arrival time T0 and the predicted melting point arrival time T1 is a negative value, a temperature change rate increase process is executed as an operating state change rate correction process. The temperature change rate increase process increases the temperature change rate by increasing the rotation speed of the motor 8, adding hot water or warm water by the fluid supply unit 30, circulating hot water or warm water by the fluid circulation unit 22, etc. By increasing the temperature change rate, the predicted melting point arrival time T1 becomes shorter. Here, at least one of the motor 8, the fluid supply unit 30, and the fluid circulation unit 22 constitutes a working unit.

[0105] Next, in step 36, the control unit 40 determines whether or not the set melting point arrival time T0 has elapsed. If the set melting point arrival time T0 has not elapsed, the process returns to step 31. If the set melting point arrival time T0 has elapsed, the auxiliary control ends. The passage of time can be determined by providing the control unit 40 with a timer function.

[0106] In this way, according to the mixing and melting device 1 of this embodiment, even if the operating state of the mixing container 3 is affected by external disturbances such as a sudden change in the environment or a malfunction of the machine, and the time it takes for the material to reach its melting point is likely to change, the quality of the produced fusion material can be maintained without deterioration by controlling the operating state of the working unit.

[0107] In addition, according to the first example auxiliary control method, the quality of the produced fusion material can be maintained without degradation by executing an operating state change rate correction process in accordance with the temperature change rate of the internal temperature or the outer wall temperature detected by the internal temperature detection unit 48 or the outer wall temperature detection unit 49 of the mixing and melting device 1.

[0108] 15 shows a third example of the auxiliary control method according to the present embodiment. The third example of the auxiliary control method executes an operation state change rate correction process according to the internal pressure in the mixing container 3 detected by the internal pressure detection unit 45 of the mixing and melting device 1.

[0109] In the third example of the auxiliary control method, in step S31, the internal pressure detection unit 45 detects the pressure inside the mixing container 3. Next, in step S32, the control unit 40 determines whether the rate of change of the pressure inside the mixing container 3 is equal to or greater than a predetermined change rate threshold value α. If the rate of change of the operating state is equal to or greater than the change rate threshold value α, in step S33, the control unit 40 calculates a predicted melting point arrival time T1.

[0110] Next, in step 34, the control unit 40 compares whether the absolute value of the difference obtained by subtracting the predicted melting point arrival time T1 from the preset set melting point arrival time T0 is smaller than a predetermined time threshold value β. If the absolute value of the difference obtained by subtracting the predicted melting point arrival time T1 from the preset melting point arrival time T0 is equal to or greater than the predetermined time threshold value β, in step 35, the control unit 40 executes an operating state change rate correction process for correcting the operating state change rate.

[0111] In the third example of the auxiliary control method shown in Fig. 15, when the difference between the set melting point arrival time T0 and the predicted melting point arrival time T1 is a positive value, a temperature change rate reduction process is executed as an operating state change rate correction process. The temperature change rate reduction process reduces the temperature change rate by reducing the rotation speed of the motor 8, adding cooling water by the fluid supply unit 30, circulating cooling water by the fluid circulation unit 22, and the like. By reducing the temperature change rate, the predicted melting point arrival time T1 becomes longer. The temperature change rate increase process may be executed in the same manner as in the example shown in Fig. 14.

[0112] In this way, according to the third example auxiliary control method, the quality of the produced fusion material can be maintained without degradation by executing an operating state change rate correction process in response to the internal pressure in the mixing container 3 detected by the internal pressure detection unit 45 of the mixing and melting device 1.

[0113] 16 shows a fourth example of the auxiliary control method according to the present embodiment. The fourth example of the auxiliary control method executes an operation state change rate correction process according to the oxygen concentration in the mixing container 3 detected by the oxygen concentration detection unit 46 of the mixing and melting apparatus 1.

[0114] In the fourth example of the auxiliary control method, in step S31, the oxygen concentration detection unit 46 detects the oxygen concentration in the mixing container 3. Next, in step S32, the control unit 40 determines whether the rate of change of the oxygen concentration in the mixing container 3 is equal to or greater than a predetermined change rate threshold value α. If the rate of change of the operating state is equal to or greater than the change rate threshold value α, in step S33, the control unit 40 calculates a predicted melting point arrival time T1.

[0115] Next, in step 34, the control unit 40 compares whether the absolute value of the difference obtained by subtracting the predicted melting point arrival time T1 from the preset set melting point arrival time T0 is smaller than a predetermined time threshold value β. If the absolute value of the difference obtained by subtracting the predicted melting point arrival time T1 from the preset melting point arrival time T0 is equal to or greater than the predetermined time threshold value β, in step 35, the control unit 40 executes an operating state change rate correction process for correcting the operating state change rate.

[0116] In the fourth example of the auxiliary control method shown in Fig. 16, when the difference between the set melting point arrival time T0 and the predicted melting point arrival time T1 is a positive value, a temperature change rate reduction process is executed as an operating state change rate correction process. The temperature change rate reduction process reduces the temperature change rate by reducing the rotation speed of the motor 8, adding cooling water by the fluid supply unit 30, circulating cooling water by the fluid circulation unit 22, and the like. By reducing the temperature change rate, the predicted melting point arrival time T1 becomes longer. The temperature change rate increase process may be executed in the same manner as in the example shown in Fig. 14.

[0117] In this way, according to the fourth example auxiliary control method, the quality of the produced fusion material can be maintained without degradation by executing an operating state change rate correction process in accordance with the oxygen concentration in the mixing container 3 detected by the oxygen concentration detection unit 46 of the mixing and melting device 1.

[0118] The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention, all of which are included in the technical concept of the present invention.

[0119] In the above embodiment, a case has been described in which a neural network is employed as a specific method of machine learning by the machine learning unit 602, but the machine learning unit 602 may employ any other machine learning method. Examples of other machine learning methods include tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, neural net types (including deep learning) such as recurrent neural networks and convolutional neural networks, clustering types such as hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, and k-means, multivariate analyses such as principal component analysis, factor analysis, and logistic regression, and support vector machines.

[0120] The present invention can also be provided in the form of a program (machine learning program) for causing a general-purpose computer to execute each step of the machine learning method according to the above embodiment. The present invention can also be provided in the form of a program (mixed melt information inference program) for causing a general-purpose computer to execute each step of the mixed melt information inference method according to the above embodiment.

[0121] The present invention can be provided not only in the form of the mixed melt information inference device 70 (mixed melt information inference method or mixed melt information inference program) according to the above embodiment, but also in the form of an inference device (inference method or inference program) used to infer mixed melt information. In this case, the inference device (inference method or inference program) can include a memory and a processor, and the processor executes a series of processes. The series of processes includes an input data acquisition process (input data acquisition step) for acquiring input data including input data (at least one of filler material information, resin material information, and additive material information) stored in the storage unit 41, and an inference process (inference step) for inferring mixed melt information inference information when the input data is acquired by the input data acquisition process.

[0122] Providing it in the form of an inference device (inference method or inference program) makes it easier to apply it to various devices compared to implementing the mixed melt information inference device 70. It can be naturally understood by those skilled in the art that when the inference device (inference method or inference program) infers mixed melt information, it may apply an inference method implemented by the inference unit 701 of the mixed melt information inference device 70 using the machine learning device 60 and the trained learning model 610 generated by the machine learning method according to the above embodiment. [Explanation of symbols]

[0123] 1...mixing and melting device, 3...mixing container, 3a...material supply section, 3b...material mixing container, 4...bearing, 5...rotating shaft, 6...pulley, 7...V-belt, 8...motor, 9...rotary joint, 10...blade member, 11...vertical wall, 12...supply screw, 14...material input section, 15...opening and closing section, 16...balance wheel, 17...discharge port cover, 18...shaft, 19...rotary cylinder, 20...collar, 22... fluid circulation unit, 23... circulating fluid control unit, 24... water passage, 30... fluid supply unit, 31... supply pipe, 32... first flow rate control unit, 33... first fluid supply member, 34... second flow rate control unit, 35... second fluid supply member, 40...control unit, 41...memory unit, 42...operation panel, 43...inverter, 44...torque detection unit, 45...internal pressure detection unit, 46...oxygen concentration detection unit, 47...humidity detection unit, 48...internal temperature detection unit, 49...outer peripheral wall temperature detection unit, 50: input unit, 51: filler material information acquisition unit, 52: resin material information acquisition unit, 53: additive material information acquisition unit, 54: mixed melt information acquisition unit, 60...machine learning device, 600...learning data acquisition unit, 601...learning data storage unit, 602...machine learning unit, 603...model storage unit, 610...learning model, 70: mixed melting information inference device, 700: input data acquisition unit, 701: inference unit, 702: model storage unit, 703: output processing unit

Claims

1. A motor that generates driving force; A rotating shaft rotated by the motor; a plurality of blade members formed on an outer periphery of the rotating shaft on the other side in the axial direction; a material input section into which material is input; a mixing vessel connected below the material input section, through which the rotating shaft passes, for mixing and melting the materials inputted into the material input section; Equipped with A mixing and melting device for mixing and melting the materials by the plurality of blade members according to a predetermined operation process, A storage unit that stores the work process; A working unit that operates according to the work process stored in the memory unit; A detection unit that detects an operating state of the working unit; a control unit that, when the working unit is operated according to the work process stored in the memory unit based on the result detected by the detection unit, predicts a predicted melting point arrival time, which is the time it takes for the material to reach its melting point, and controls the working unit so that, when an absolute value of a difference between a predetermined set melting point arrival time stored in the memory unit and the predicted melting point arrival time is equal to or greater than a predetermined time threshold, the absolute value of the difference between the set melting point arrival time and the predicted melting point arrival time becomes smaller; Further comprising: Mixing and melting equipment.

2. A fluid supply unit that supplies a fluid to the material input unit or the mixing vessel; a fluid circulating unit that adjusts the temperature of the material in the mixing vessel, the temperature in the peripheral wall of the mixing vessel, and the temperature of the rotating shaft by circulating a fluid; Further equipped with The working unit includes: The motor, The fluid supply unit, or The fluid circulation unit, At least one of The mixing and melting apparatus according to claim 1.

3. The detection unit is an inverter that detects the number of rotations of the rotating shaft; an internal pressure detection unit for detecting the pressure inside the mixing vessel; an internal temperature detector for detecting the temperature inside the mixing vessel; an oxygen concentration detection unit for detecting an oxygen concentration in the mixing vessel; an internal humidity detector for detecting humidity inside the mixing container; Or, an outer peripheral wall temperature detection unit for detecting the temperature of the outer peripheral wall of the mixing vessel; At least one of The mixing and melting apparatus according to claim 2.

4. When a difference obtained by subtracting the predicted melting point arrival time from the set melting point arrival time is a positive value, the control unit executes a temperature change rate reduction process for reducing a temperature change rate by at least one of reducing a rotation speed of the motor, adding cooling water by the fluid supply unit, or circulating cooling water by the fluid circulation unit. The mixing and melting apparatus according to claim 2 or 3.

5. When the difference between the set melting point arrival time and the predicted melting point arrival time is a negative value, the control unit executes a temperature change rate increase process to increase a temperature change rate by at least one of increasing the rotation speed of the motor, adding warm water or hot water by the fluid supply unit, or circulating warm water or hot water by the fluid circulation unit. The mixing and melting apparatus according to claim 2 or 3.

6. A motor that generates driving force; A rotating shaft rotated by the motor; a plurality of blade members formed on an outer periphery of the rotating shaft on the other side in the axial direction; a material input section into which material is input; a mixing vessel connected below the material input section, through which the rotating shaft passes, for mixing and melting the materials inputted into the material input section; A storage unit that stores a work process; A working unit that operates according to the work process stored in the memory unit; A detection unit that detects an operating state of the working unit; A method for controlling an auxiliary operation of a mixing and melting device that mixes and melts the materials by the plurality of blade members according to a predetermined operation process, comprising: a step of detecting the operating state by the detection unit; determining whether a rate of change in the operating state is equal to or greater than a predetermined rate of change threshold; A step of calculating a predicted melting point arrival time, which is a time for the material to reach its melting point when the working unit is operated in accordance with the work step; comparing whether an absolute value of a difference between a predetermined set melting point arrival time stored in the storage unit and the predicted melting point arrival time is smaller than a predetermined time threshold; When an absolute value of a difference between the set melting point arrival time and the predicted melting point arrival time is equal to or greater than a predetermined time threshold, executing an operating state change rate correction process for correcting the change rate of the operating state; determining whether the set melting point reaching time has elapsed; have Auxiliary control method for a mixing and melting device.

7. The mixing and melting device is A fluid supply unit that supplies a fluid to the material input unit or the mixing vessel; a fluid circulating unit that adjusts the temperature of the material in the mixing vessel, the temperature in the peripheral wall of the mixing vessel, and the temperature of the rotating shaft by circulating a fluid; Further equipped with The operating state change rate correction process is a temperature change rate correction process, The temperature change rate correction process corrects at least one of the rotation speed of the motor, the addition of fluid by the fluid supply unit, and the circulation of fluid by the fluid circulation unit. A method for auxiliary control using the mixing and melting apparatus according to claim 6.

8. When a difference between the set melting point arrival time and the predicted melting point arrival time is a positive value, the operating state change rate correction process executes a temperature change rate reduction process for reducing a temperature change rate by at least one of reducing a rotation speed of the motor, adding cooling water by the fluid supply unit, or circulating cooling water by the fluid circulation unit. A method for auxiliary control using the mixing and melting apparatus according to claim 7.

9. When the difference between the set melting point arrival time and the predicted melting point arrival time is a negative value, the operating state change rate correction process executes a temperature change rate increase process for increasing the temperature change rate by at least one of increasing the rotation speed of the motor, adding warm water or hot water by the fluid supply unit, or circulating warm water or hot water by the fluid circulation unit. A method for auxiliary control using the mixing and melting apparatus according to claim 7.

Images