Method and system for producing kneaded rubber

Abstract

Provided is a method and system for producing kneaded rubber with which it is possible to efficiently produce a final kneaded rubber of the desired quality for each kneaded material specification by using an open structure roll kneader. For each kneaded material R specification, the state of the kneaded material R circulating through a circulation path is detected by a sensor unit 9, and the detected data are input to a computation device 10 together with the kneading conditions when the detected data were detected. In the computation device 10, the input detected data are distinguished into normal data showing a good kneading state and non-normal data showing a non-good kneading state based on preset criteria. The kneading conditions capable of realizing the normal data are calculated by the computation device 10 by machine-learning using the kneading conditions input to the computation device 10 together with the normal data and the kneading conditions input to the computation device 10 together with the non-normal data as training data, and kneading is performed by applying the calculated kneading conditions to the next kneaded material R of the same specification to be kneaded.

Description

Method and system for manufacturing kneaded rubber

[0001] The present invention relates to a manufacturing method and manufacturing system for kneaded rubber, and more particularly to a manufacturing method and manufacturing system for kneaded rubber that can efficiently manufacture final kneaded rubber of the desired quality for each specification of the kneaded material using an open-structure roll kneader.

[0002] Various rubber products such as tires and conveyor belts are produced by vulcanizing unvulcanized rubber. This unvulcanized rubber is a final kneaded rubber produced by thoroughly kneading a mixture of a primary kneaded rubber produced by kneading raw rubber and non-vulcanization compounding ingredients with vulcanization compounding ingredients. Various open-structure roll kneaders have been proposed as devices for producing the final kneaded rubber (see, for example, Patent Document 1).

[0003] In an open-structure roll mixer, a mixture of a primary mixed rubber and vulcanization-based compounding agents is formed into a loop shape and circulates through a circulation path. It is thoroughly mixed by repeatedly passing between a pair of kneading rolls installed in the circulation path to produce a final mixed rubber. Patent Document 1 proposes mixing by adjusting the gap between the pair of kneading rolls (roll gap), the amount of the mixed material on the pair of kneading rolls, the temperature of the mixed material, and the like. However, conditions at the production site (environment and equipment) are not always constant and there is some variation. Furthermore, even if the primary mixed rubber and vulcanization-based compounding agents are set to the same specifications, there is some variation. Therefore, simply adjusting the parameters proposed in Patent Document 1 is likely to result in inefficient production of a final mixed rubber of the desired quality. Therefore, there is room for improvement in efficiently producing a final mixed rubber of the desired quality for each mixed material specification using an open-structure roll mixer.

[0004] Japanese Patent Application Publication No. 2006-142802

[0005] An object of the present invention is to provide a method and system for producing kneaded rubber that can efficiently produce final kneaded rubber of desired quality for each specification of the kneaded product using a roll kneader with an open structure.

[0006] In order to achieve the above object, the method for producing kneaded rubber of the present invention is a method for producing a final kneaded rubber by forming a kneaded mixture of a primary kneaded rubber in which a non-vulcanizing compounding agent is kneaded into raw rubber and a vulcanizing compounding agent into a loop shape, circulating this kneaded mixture in a circulation path of an open-structure roll kneader in which a pair of kneading rolls is installed, and kneading the mixture. In this method for producing a final kneaded rubber, a sensor unit detects the state of the kneaded mixture circulating in the circulation path for each specification of the kneaded mixture, and the detected data is input to a calculation device together with the kneading conditions at the time the detected data is detected, and the calculation The device distinguishes the input detection data into normal data indicating a good mixing state and abnormal data indicating a bad mixing state based on preset criteria, and uses the mixing conditions input to the arithmetic device together with the normal data and the mixing conditions input to the arithmetic device together with the abnormal data as learning data through machine learning, thereby calculating the mixing conditions that can achieve the normal data by the arithmetic device, and applying these calculated mixing conditions when mixing the next mixture of the same specifications.

[0007] The kneaded rubber manufacturing system of the present invention has a circulation path along which a mixture of a primary kneaded rubber obtained by kneading a non-vulcanization compounding agent with raw rubber and a vulcanization compounding agent is formed into a loop shape and circulated to be kneaded, and the kneaded rubber manufacturing system is equipped with an open-structure roll kneader on which a pair of kneading rolls is installed, and the kneaded rubber manufacturing system has a sensor unit that detects the state of the kneaded material circulating on the circulation path for each specification of the kneaded material, and a calculation device to which the detection data is input together with the setting conditions of the roll kneader at the time the detection data is detected, and the calculation device Based on the established criteria, the input detection data is distinguished into normal data indicating a good mixing state and abnormal data indicating an ungood mixing state, and the setting conditions input to the arithmetic device together with the normal data and the setting conditions input to the arithmetic device together with the abnormal data are machine-learned as learning data, so that the setting conditions that can realize the normal data are calculated by the arithmetic device, and the calculated setting conditions are applied when kneading the next kneaded material of the same specifications.

[0008] According to the present invention, for each specification of the kneaded product, the kneading conditions input to the arithmetic device together with the normal data and the kneading conditions input to the arithmetic device together with the abnormal data are used as learning data for machine learning, thereby making it possible to accurately calculate the kneading conditions that can achieve the normal data. Therefore, by applying these calculated kneading conditions to the next kneaded product of the same specifications, the kneaded product will be kneaded in a state equivalent to the normal data. This is advantageous for efficiently producing final kneaded rubber of the desired quality for each specification of the kneaded product.

[0009] Fig. 1 is an explanatory diagram illustrating an embodiment of a kneaded rubber manufacturing system in a side view. Fig. 2 is an explanatory diagram illustrating a state in which a kneaded material is being kneaded by the manufacturing system of Fig. 1. Fig. 3 is an explanatory diagram illustrating a front view of the periphery of a pair of kneading rolls of Fig. 2. Fig. 4 is an explanatory diagram illustrating a state in which the flender of Fig. 3 is operating. Fig. 5 is an explanatory diagram illustrating a state in which the manufactured final kneaded rubber is being discharged from the roll kneader of Fig. 2. Fig. 6 is an explanatory diagram illustrating a state in which the loop shape of the kneaded material of Fig. 2 has been broken.

[0010] Hereinafter, a method and system for producing kneaded rubber according to the present invention will be described based on the embodiments shown in the drawings.

[0011] In the embodiment of the kneaded rubber manufacturing system 1 illustrated in Figures 1 to 4, a vulcanization compounding agent M3 is mixed into a primary kneaded rubber R1, which is a mixture of raw rubber M1 and non-vulcanization compounding agent M2, and the mixture R (M1, M2, M3) of the primary kneaded rubber R1 and the vulcanization compounding agent M3 is thoroughly kneaded to produce an unvulcanized final kneaded rubber Rf of desired quality. This desired quality refers to a state in which the vulcanization compounding agent M3 (and the non-vulcanization compounding agent M2) are evenly dispersed and the target viscosity is achieved. However, since the target viscosity is considered to indicate that M2 and M3 are generally evenly dispersed, the term "desired quality" can also be substituted for "target viscosity." The raw rubber M1, non-vulcanization compounding agent M2, and vulcanization compounding agent M3 that make up the final kneaded rubber Rf (kneaded product R) are kneaded using predetermined amounts.

[0012] The raw rubber M1 may be one or more types of natural rubber or various synthetic rubbers depending on the purpose. The non-vulcanization compounding agent M2 may be selected from various known compounding agents such as carbon black and silica depending on the purpose. The vulcanization compounding agent M3 may be selected from various known compounding agents such as sulfur, vulcanization activators, and vulcanization accelerators depending on the purpose.

[0013] The primary mixed rubber R1 obtained by mixing the raw rubber M1 and the non-vulcanization compounding agent M2 may be mixed in this roll mixer 2 or in another mixer (such as a Banbury mixer). To prevent the powdered vulcanization compounding agent M3 from scattering, for example, a masterbatch produced by previously mixing the raw rubber M1 and the vulcanization compounding agent M3 is used.

[0014] The manufacturing system 1 includes a roll mixer 2 having an open structure, non-contact sensor units 9 (9a, 9b), and a computing device 10. A display 11 is connected to the computing device 10 via a wired or wireless connection.

[0015] As shown in Fig. 2, in the roll mixer 2, the kneaded material R (M1, M2, M3) is formed into a loop shape. As the roll mixer 2, various known open structures can be used. This roll mixer 2 includes a pair of opposing kneading rolls 2a, 2b, a kneading conveyor 5a, a delivery conveyor 5b, a supply conveyor 6, a blender 7, and a control device 8. Arrows D, W, and H in the figure indicate the front-rear direction, width direction, and height direction of the roll mixer 2 (kneading rolls 2a, 2b), respectively.

[0016] The pair of kneading rolls 2a, 2b are rotated by hydraulic or electric drive motors 4a, 4b, respectively, and their rotation speeds can be adjusted independently and they can rotate forward and backward. One of the kneading rolls, 2a, is connected to an actuator 3 such as a hydraulic cylinder, and by moving this kneading roll 2a toward and away from the other kneading roll 2b, the gap between the kneading rolls 2a, 2b (roll gap) can be adjusted.

[0017] The re-kneading conveyor 5a extends horizontally from a position above the pair of kneading rolls 2a, 2b, and its extending direction changes diagonally downward midway. The delivery conveyor 5b extends horizontally from a position below the pair of kneading rolls 2a, 2b, and is rotatable up and down midway. The lower end of the re-kneading conveyor 5a, which extends diagonally downward, is located around the rotation center of the delivery conveyor 5b. As illustrated in Figure 2, when the delivery conveyor 5b is rotated upward midway, the re-kneading conveyor 5a and the delivery conveyor 5b form a circulation path along which the loop-shaped kneaded material R circulates.

[0018] The supply conveyor 6 is disposed above the pair of kneading rolls 2a, 2b. The sheet-like masterbatch (vulcanization compounding agent M3) conveyed by the supply conveyor 6 is introduced between the pair of kneading rolls 2a, 2b. Known conveyor devices can be used for the re-kneading conveyor 5a, the delivery conveyor 5b, and the supply conveyor 6. The kneaded material R is placed on the upper surface of the conveyor belts provided on each of these conveyors and conveyed.

[0019] The blender 7 is disposed between the tip of the re-kneading conveyor 5a and the pair of kneading rolls 2a, 2b, and changes the widthwise position of the kneaded material R that is fed from the tip of the re-kneading conveyor 5a onto the pair of kneading rolls 2a, 2b.

[0020] In this embodiment, as shown in Figures 3 and 4, a pair of belt-conveyor-like blenders 7 are installed spaced apart in the width direction. Each blender 7 is slidable in the width direction. The kneaded material R passes through the gap between the blenders 7 from above to below, and by moving each blender 7 to a different position in the width direction and changing the widthwise position of the gap between the blenders 7, the widthwise position of the kneaded material R fed to the pair of kneading rolls 2a, 2b changes. The blender 7 is not limited to the type shown in this embodiment, and various known types can be used.

[0021] The control device 8 controls the operations of the components of the roll kneader 2. That is, the operations of the pair of kneading rolls 2a, 2b (drive motors 4a, 4b), the actuator 3, the re-kneading conveyor 5a, the delivery conveyor 5b, the supply conveyor 6, and the blender 7 are controlled by the control device 8. A known computer is used as the control device 8. Data indicating the drive torque of the drive motors 4a, 4b, the roll gap between the kneading rolls 2a, 2b, the roll rotation speed, the transport speeds of the re-kneading conveyor 5a and the delivery conveyor 5b, the temperature of the kneaded material R, and data (instruction data) from the calculation device 10 described later are input to the control device 8. The control device 8 controls the operations of the components based on the input data.

[0022] The sensor unit 9 detects the state of the kneaded material R circulating through the circulation path for each specification of the kneaded material R (final kneaded rubber Rf). As the sensor unit 9, a camera device such as a digital camera, or a known non-contact sensor such as a laser sensor or an infrared sensor is used. The sensor unit 9 is installed at a location where it can detect the kneaded material R within the detection range of the circulation path, and the number of the installed sensor units is not particularly limited. In this embodiment, the sensor unit 9a is arranged at a position where it can detect the kneaded material R remaining on the pair of kneading rolls 2a, 2b, and the sensor unit 9b is arranged at a position where it can detect the kneaded material R being fed from the tip of the re-kneading conveyor 5a toward the pair of kneading rolls 2a, 2b.

[0023] One of the sensor units 9a mainly detects a bank amount B of the kneaded material R remaining on the pair of kneading rolls 2a, 2b. The bank amount B is defined, for example, as the volume of the kneaded material R present above a tangent line (a straight line shown by a dashed line in FIG. 2) connecting the upper ends of the pair of kneading rolls 2a, 2b. This bank amount B is calculated by an arithmetic unit 10 through an approximate calculation based on detection data (image data) from the sensor unit (camera device) 9a.

[0024] The other sensor unit 9b detects whether or not there is an abnormal state of the kneaded material R circulating in the circulation path (whether or not there is a break, a crack or chip, or a raised lump, etc.). It is advisable to identify in advance the locations in the circulation path where an abnormal state of the kneaded material R is likely to occur, and install the sensor unit 9b at a position where it can detect the kneaded material R in the identified locations.

[0025] The calculation device 10 receives input of the detection data from the sensor unit 9 and the kneading conditions at the time the detection data was detected. A known computer is used as the calculation device 10. The kneading conditions include at least three types: the roll caps of the kneading rolls 2a and 2b, the roll rotation speed, and the conveying speeds of the kneading conveyor 5a and the delivery conveyor 5b (i.e., the circulation speed of the kneaded material R in the circulation path). In addition, for example, the environmental temperature when the kneaded material R is being kneaded can also be included. As the kneading conditions input to the calculation device 10 together with the detection data from the sensor unit 9, kneading conditions that have a greater influence on the quality of the final kneaded rubber Rf produced are selected.

[0026] The display 11 displays various data input to the arithmetic device 10, data (arithmetic results) processed by the arithmetic device 10, etc. For example, data (image data) detected by the sensor unit (camera device) 9 is displayed in real time on the display 11. The display 11 is not essential and may be provided as an option.

[0027] In order to efficiently manufacture the final kneaded rubber Rf of desired quality for each specification of the kneaded material using this manufacturing system 1, it is necessary to calculate optimal kneading conditions and apply the calculated optimal kneading conditions to knead the kneaded material R. Here, an example of a procedure for calculating the optimal kneading conditions will be described.

[0028] First, a large number of kneaded materials R (multiple batches) of the same specifications are kneaded using this manufacturing system 1 to produce a large number of final kneaded rubbers Rf of the desired quality. More specifically, as shown in Figure 1, a vulcanization compounding agent M3 is fed as a master batch onto a pair of kneading rolls 2a, 2b by a supply conveyor 6. In this roll kneader 2, the primary kneaded rubber R1 circulates along a circular circulation path formed by a kneading conveyor 5a and a delivery conveyor 5b.

[0029] Next, as shown in FIG. 2, the kneaded material R, which is the primary kneaded rubber R1 mixed with the vulcanization compounding agent M3, circulates repeatedly through the circulation path. In the circulation path, the kneaded material R is pinched and kneaded between a pair of kneading rolls 2a and 2b, which rotate in opposite directions, and is subjected to a moderate shear force. The kneaded material R accumulates on the pair of kneading rolls 2a and 2b, creating a predetermined bank amount B. If the bank amount B is excessive, the kneaded material R in which the vulcanization compounding agent M3 is sufficiently dispersed cannot be obtained. Therefore, to reduce the bank amount B, the blender 7 is operated in a predetermined pattern, as shown in FIGS. 3 and 4, to change the widthwise position of the kneaded material R fed to the pair of kneading rolls 2a and 2b (leveling the height of the accumulated kneaded material R). The kneaded material R is repeatedly circulated through the circulation path and kneaded, so that the vulcanization compounding agent M3 is uniformly dispersed, and a final kneaded rubber Rf with the desired quality (target viscosity) is produced.

[0030] When the final kneaded rubber Rf is produced, the transfer conveyor 5b is rotated downward midway to eliminate the circulation path, as illustrated in Fig. 5. As a result, the final kneaded rubber Rf is discharged from the roll kneader 2 by the transfer conveyor 5b and transported to the next process. The kneading conditions when kneading one batch of the kneaded material R are basically kept constant from start to finish.

[0031] In this way, when kneading the kneaded material R of the same specifications, the state of the kneaded material R circulating in the circulation path is detected by the sensor unit 9, and the detected data is input to the calculation device 10 together with the kneading conditions at the time the detected data was detected. The calculation device 10 classifies the inputted detected data into normal data indicating a good kneading state and abnormal data indicating a bad kneading state based on a preset criterion.

[0032] More specifically, the computing device 10 is input with preset criteria for distinguishing the data detected by the sensor unit 9 as normal data indicating a good kneading state and abnormal data indicating an unsatisfactory kneading state. For example, with regard to the data detected by the sensor unit 9a (bank amount B), the allowable range of the bank amount B within which the vulcanization compounding agent M3 is sufficiently dispersed is empirically known, and the detected data is distinguished as normal data or abnormal data based on this allowable range. With regard to the data detected by the sensor unit 9b (such as the presence or absence of breaks, cracks, or chips in the kneaded material R circulating through the circulation path), if there are no breaks, cracks, or chips in the kneaded material R, the data is classified as normal data, and if there are any, the data is classified as abnormal data. With regard to the raised lumps of the kneaded material R, the size range within which such lumps adversely affect the kneading state is empirically known, and the detected data is distinguished as normal data or abnormal data based on this size range.

[0033] When the detection data from the sensor unit 9 is input to the calculation device 10, the detection data is classified into normal data and abnormal data based on preset criteria, and the normal data is linked to the kneading conditions that were both input, and the abnormal data is linked to the kneading conditions that were both input and stored in the calculation device 10.

[0034] In this way, a large number of kneading conditions input to the arithmetic device 10 together with normal data and kneading conditions input to the arithmetic device 10 together with abnormal data are stored and used as learning data for machine learning. The arithmetic device 10 performs machine learning using these learning data to calculate kneading conditions that can achieve normal data. That is, when the kneaded material R being kneaded is detected by the sensor unit 9, kneading conditions are calculated such that the detected data can be distinguished from normal data. As a machine learning method, various well-known methods such as deep learning using a neural network can be adopted. When the kneaded material R is kneaded under the calculated kneading conditions, the detected data detected by the sensor unit 9 is classified as normal data, and therefore the calculated kneading conditions can be said to be optimal kneading conditions.

[0035] As described above, after calculating the optimal kneading conditions, the calculated kneading conditions are applied when the next kneaded product R of the same specifications is kneaded. That is, when the next kneaded product R is kneaded as illustrated in FIGS. 2 to 4, the kneading conditions calculated by the arithmetic unit 10 are input to the control device 8, and the control device 8 kneads the kneaded product R using the calculated kneading conditions. By kneading the kneaded product R using the kneading conditions, the kneaded product R is kneaded in a state equivalent to the normal data. Therefore, in the circulation path kneading the kneaded product R, the bank amount B does not become excessive, and no loop-shaped breaks, tears, or chips occur, and the kneading is performed in a normal state. Therefore, this embodiment is advantageous for efficiently producing a final kneaded rubber Rf of the desired quality for each specification of the kneaded product R. When kneading each kneaded material R, in reality, there is some variation in the manufacturing site (environment and equipment), and even if the kneaded material R is set to the same specifications, there will be some variation. However, by kneading the kneaded material R as in this embodiment, it is possible to efficiently produce final kneaded rubber Rf of the desired quality for each specification of the kneaded material R.

[0036] Incidentally, the detection data detected for each roll kneader 2 is used as learning data to calculate optimal kneading conditions, and the calculated kneading conditions are not only applied when the next kneaded material R is kneaded by that roll kneader 2, but also the detection data (learning data) may be shared and used by roll kneaders 2 with equivalent specifications. In other words, the detection data detected by a plurality of roll kneaders 2 with equivalent specifications may be used as learning data to calculate optimal kneading conditions, and the calculated kneading conditions may be applied when the next kneaded material R is kneaded by these roll kneaders 2.

[0037] It is preferable that the amount of learning data described above is large, but if the data is obtained a long time ago, it will not adequately reflect the current state of the roll mixer 2. Therefore, it is advisable to use the mixing conditions for a predetermined number of materials R most recently mixed as learning data, and update the learning data each time the next material R is mixed. For example, this predetermined number is set to about 30 to 50. This is even more advantageous in calculating the optimal mixing conditions for the current roll mixer 2.

[0038] To efficiently obtain the final kneaded rubber Rf of the desired quality, the bank amount B of the kneaded material R and whether or not the loop shape of the kneaded material R is broken in the circulation path have a significant effect. Therefore, it is preferable to use at least these two types of detection data by the sensor unit 9.

[0039] In order to correct the bank amount B of the kneaded material R and abnormalities of the kneaded material R in the circulation path (breakage, tears, chips, raised lumps, etc. of the kneaded material R), it is particularly effective to change the roll cap between the pair of kneading rolls 2a, 2b, the roll rotation speed of the pair of kneading rolls 2a, 2b, and the circulation speed of the kneaded material R in the circulation path. Therefore, it is preferable that the kneading conditions used in this method for producing kneaded rubber include at least these three types.

[0040] The operation of the flender 7 is also useful for correcting the bank amount B of the kneaded material R and abnormalities in the kneaded material R in the circulation path. Therefore, it is more preferable that the kneading conditions used in this kneaded rubber manufacturing method include the operating conditions of the flender 7.

[0041] If there is a large difference in the environmental temperature between the kneaded materials R when they are being kneaded, this will affect the bank amount B of the kneaded materials R and the occurrence of abnormalities in the circulation path of the kneaded materials R. Therefore, it is more preferable that the kneading conditions used in this method of producing kneaded rubber include the environmental temperatures when each kneaded material R is being kneaded, and that the arithmetic device 10 calculates kneading conditions that can achieve normal data according to the environmental temperature when the next kneaded material R of the same specifications is kneaded.

[0042] More specifically, the environmental temperature during kneading of each kneaded material R is classified into a plurality of levels, and kneading conditions that can realize normal data for each classified level are calculated by the arithmetic device 10. Then, when kneading a kneaded material R of the same specifications next time, the environmental temperature level at that time is input to the arithmetic device 10, and the arithmetic device 10 calculates (extracts) kneading conditions that can realize normal data at that environmental temperature level, and applies these calculated kneading conditions to kneading of that kneaded material R.

[0043] REFERENCE SIGNS LIST 1 Manufacturing system 2 Roll kneader 2a, 2b Kneading rolls 3 Actuator 4a, 4b Drive motor 5a Kneading conveyor 5b Delivery conveyor 6 Supply conveyor 7 Blender 8 Control device 9 (9a, 9b) Sensor unit 10 Calculation device 11 Display R1 Primary kneaded rubber R Kneaded product Rf Final kneaded rubber M1 Raw rubber M2 Non-vulcanization compounding agent M3 Vulcanization compounding agent

Claims

1. A method for producing kneaded rubber, in which a mixture of primary kneaded rubber, in which non-vulcanizing compounding agents have been kneaded into raw rubber, and vulcanizing compounding agents is formed into a loop shape, and this mixture is circulated through a circulation path in an open-structure roll kneader equipped with a pair of kneading rolls to produce a final kneaded rubber; the state of the mixture circulating through the circulation path is detected by a sensor unit for each specification of the mixture, and the detected data is input to a calculation device together with the kneading conditions at the time the detected data was detected. The calculation device classifies the input detected data into normal data indicating a good kneaded state and abnormal data indicating an ungood kneaded state based on preset criteria, and calculates the kneading conditions that will achieve the normal data by machine learning using the kneading conditions input to the calculation device together with the normal data and the kneading conditions input to the calculation device together with the abnormal data as learning data. The calculated kneading conditions are then applied when kneading the next mixture of the same specifications.

2. A method for manufacturing kneaded rubber as described in claim 1, in which the kneading conditions for a predetermined number of the kneaded materials most recently kneaded are used as the learning data, and the learning data is updated each time the next kneaded material of the same specifications is kneaded.

3. A method for manufacturing kneaded rubber as described in claim 1 or 2, wherein at least two types of detection data are used: the amount of bank of the kneaded material remaining on the pair of kneading rolls, and whether or not the loop shape of the kneaded material is damaged in the circulation path.

4. A method for producing kneaded rubber according to any one of claims 1 to 3, wherein the kneading conditions are at least three types: a roll cap between the pair of kneading rolls, the roll rotation speed of the pair of kneading rolls, and the circulation speed of the kneaded material.

5. A method for producing kneaded rubber according to any one of claims 1 to 4, wherein the kneading conditions include an operating condition of a flender that changes the width-wise input position of the kneaded material relative to the pair of kneading rolls.

6. A method for manufacturing kneaded rubber described in any one of claims 1 to 5, wherein the kneading conditions include the ambient temperature when the kneaded material is being kneaded, and the arithmetic device calculates the kneading conditions that can achieve the normal data depending on the ambient temperature when the next kneaded material is kneaded.

7. A kneaded rubber manufacturing system having a circulation path along which a mixture of primary kneaded rubber, in which non-vulcanizing compounding agents are kneaded into raw rubber, and vulcanizing compounding agents is formed into a loop shape and circulated for mixing, and equipped with an open-structure roll kneader having a pair of kneading rolls installed on the circulation path, the system comprising: a sensor unit for detecting the state of the kneaded material circulating on the circulation path for each specification of the kneaded material; and a computing device into which the detection data is input together with the setting conditions of the roll kneader at the time the detection data is detected; The calculation device is configured to distinguish the input detection data into normal data indicating a good mixing state and abnormal data indicating a bad mixing state based on preset criteria, and to machine-learn the setting conditions input to the calculation device together with the normal data and the setting conditions input to the calculation device together with the abnormal data as learning data, so that the calculation device calculates the setting conditions that can realize the normal data, and these calculated setting conditions are applied when mixing the next kneaded material of the same specifications.This is a kneaded rubber manufacturing system.

Images