Method for predicting cross-sectional shape of tire and method for manufacturing tire

Abstract

To provide a prediction method that can more accurately predict a cross sectional shape of a tire manufactured by vulcanizing a green tire, using data on a cross sectional shape the green tire and data on a cross sectional shape a molding surface of a mold to be used, and a manufacturing method for a tire utilizing the prediction method.SOLUTION: A prediction model PM, which is created by subjecting tire specification data D1 including a cross section shape of green tires G, cross sectional shape data D2 on a molding surface 7 of a mold 6 and cross section image data D3 on a tire T manufactured by vulcanizing a number of green tires G whose tire specification data D1 are different using the mold 6, as teaching data, to machine learning, is stored in a calculation device 2; and the tire specification data D1 on green tires Ga to be predicted and the cross sectional shape data D2 on the molding surface 7 are substituted in the prediction model PM and are subjected to calculation processing, so as to predict a cross sectional shape of a target tire Ta that is manufactured by vulcanizing the green tires Ga using the mold 6.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a method for predicting the cross-sectional shape of a tire and a method for manufacturing a tire. More specifically, the present invention relates to a prediction method capable of predicting, with higher accuracy, the cross-sectional shape of a tire manufactured by vulcanizing a green tire using the cross-sectional shape data of the green tire and the cross-sectional shape data of the molding surface of a mold to be used, and a method for manufacturing a tire using this prediction method.

Background Art

[0002] A tire is manufactured by vulcanizing an unvulcanized green tire in a vulcanization mold. The green tire is molded into a preset shape and deformed into the final shape during vulcanization to complete the tire. In the molding process of the green tire, if the shape of the green tire is not appropriate due to an excess or deficiency of the rubber volume, etc., a tire with the desired shape may not be obtained. Therefore, it is beneficial for reliably obtaining a tire with the desired shape if it is possible to accurately predict what final shape the vulcanized green tire will deform into.

[0003] Conventionally, a method for predicting the cross-sectional shape of a tire in an arbitrary manufacturing process has been proposed (see Patent Document 1). In the method proposed in Patent Document 1, the cross-sectional shape of the tire is calculated based on the predicted cross-sectional shape of the carcass. And the cross-sectional shape of the carcass is predicted based on the manufacturing condition information in the process to be predicted and the structural specification information of the carcass using a predetermined function that determines this cross-sectional shape.

[0004] However, in this proposed method, since one of the purposes is to make a prediction in a short time, as the function for determining the cross-sectional shape of the carcass, a theoretical formula derived from extremely simple theories such as membrane theory and beam theory is adopted. Therefore, there is a limit to accurately predicting the cross-sectional shape of a tire manufactured by vulcanizing a green tire, and there is room for improvement in predicting the cross-sectional shape of a tire with higher accuracy.

Prior Art Documents

Patent Document

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] An object of the present invention is to provide a prediction method capable of predicting the cross-sectional shape of a tire manufactured by vulcanizing a green tire with higher accuracy using the cross-sectional shape data of the green tire and the cross-sectional shape data of the molding surface of the mold to be used, and a tire manufacturing method using this prediction method.

Means for Solving the Problems

[0007] To achieve the above object, the cross-sectional shape prediction method of the tire of the present invention includes tire specification data including the cross-sectional shape of a green tire, cross-sectional shape data of the molding surface of a mold for vulcanizing the green tire, and cross-sectional image data of tires manufactured by vulcanizing a large number of the green tires with different tire specification data using the mold. Using these as teacher data and performing machine learning using the teacher data to generate a prediction model for predicting the cross-sectional shape of a tire manufactured by vulcanization. Input the tire specification data of the green tire to be predicted into an arithmetic unit in which this prediction model is stored, and based on the input tire specification data and the cross-sectional shape data of the molding surface, by arithmetic processing by the arithmetic unit using the prediction model, the green tire to be predicted is vulcanized and manufactured using the mold has reached its final shape A method for predicting the cross-sectional shape of a tire, characterized by predicting the cross-sectional shape of a target tire (however, except for predicting the shape during the process of vulcanizing the green tire to be predicted) 。

[0008] The method for manufacturing a tire according to the present invention is characterized in that, based on the result predicted by the above-described method for predicting the cross-sectional shape of a tire, the tire specification data of a green tire for manufacturing a tire having a target cross-sectional shape is grasped, a green tire corresponding to the grasped tire specification data is molded, and the molded green tire is vulcanized using a mold having the same specifications as the mold.

[0009] According to the method for predicting the cross-sectional shape of a tire of the present invention, a prediction model generated by machine learning using the tire specification data, the cross-sectional shape data of the molding surface, and the tire cross-sectional image data as the teacher data is used. Therefore, by inputting the tire specification data of the green tire to be predicted and the cross-sectional shape data of the molding surface into the prediction model and performing arithmetic processing by the arithmetic unit, it becomes possible to predict the cross-sectional shape of the target tire manufactured by vulcanizing the green tire to be predicted using the mold with higher accuracy.

[0010] According to the method for manufacturing a tire of the present invention, based on the highly accurate result predicted by the above-described method for predicting the cross-sectional shape of a tire, the tire specification data of a green tire for manufacturing a tire having a target cross-sectional shape can be grasped. Then, since a green tire corresponding to the grasped tire specification data is molded and vulcanized using a mold having the same specifications as the mold, it is advantageous for obtaining a tire having a target cross-sectional shape.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0012] Hereinafter, the method for predicting the cross-sectional shape of the tire and the method for manufacturing the tire of the present invention will be specifically described based on the embodiments shown in the drawings.

[0013] Using the prediction system 1 illustrated in FIG. 1, the method for predicting the cross-sectional shape of the tire of the present invention is performed. This prediction system 1 includes an arithmetic device 2, an input unit 3, and a display unit 4, and further includes a measuring device 5 and a cross-sectional image capturing device 5a. The arithmetic device 2, the input unit 3, and the display unit 4 are communicably connected by wire or wirelessly. The data acquired by the measuring device 5 and the cross-sectional image capturing device 5a is input to the arithmetic device 2 directly or through the input unit 3.

[0014] The arithmetic device 2 inputs and stores various data, and performs arithmetic processing using these data. As the arithmetic device 2, various computers can be used. Therefore, the arithmetic device 2 has a memory in which various data is stored and a CPU that performs arithmetic processing.

[0015] The input unit 3 is an input means for inputting various data into the arithmetic unit 2. As the input unit 3, a keyboard, a mouse, and various terminal devices can be used.

[0016] The display unit 4 is a display means for displaying various data input to the arithmetic unit 2 and arithmetic results (numerical values, tables, drawings, etc.) obtained by performing arithmetic processing using these data. As the display unit 4, various monitors can be used.

[0017] The measuring device 5 is a means for measuring and acquiring necessary data. For example, tire specification data D1 including the cross-sectional shape of the green tire G is acquired using the measuring device 5. It is also possible to acquire the cross-sectional shape data D2 of the molding surface 7 of the mold 6 for vulcanizing the green tire G using the measuring device 5. In this invention, at least the cross-sectional shape of the green tire G is measured by the measuring device 5 to acquire data.

[0018] The cross-sectional image photographing device 5a is a means for acquiring image data of the cross-section of the manufactured tire T. Examples of the cross-sectional image photographing device 5a include known image photographing devices such as digital cameras and known X-ray photographing devices (CT scanners). When using an X-ray photographing device (CT scanner), cross-sectional shape data can be measured and acquired without cutting the green tire G in the cross-section. When using a digital camera or the like, the tire T is cut in the cross-section and the cut surface is photographed. The cross-sectional image photographing device 5a can also be used in combination with the measuring device 5 for measuring the cross-sectional shape of the green tire G.

[0019] As the tire specification data D1, cross-sectional shape data of the green tire G as exemplified in FIG. 2 is used. In a general green tire G, an inner liner layer m1 is disposed on the innermost circumference, a carcass layer m2 is disposed on the outer surface thereof, and an unvulcanized rubber R is disposed on the outer surface of the carcass layer m2. A belt layer m4 and the like are embedded in the unvulcanized rubber R of the tread portion. Since the cross-sectional shape of the green tire G generally does not change in the tire circumferential direction, cross-sectional shape data at an arbitrary circumferential position of the green tire G can be used. In the drawings, the right half of the green tire, tire, and mold is illustrated, but the left half has the same specifications as the right half.

[0020] In addition to the above, various characteristic data of each constituent member of the green tire G can be exemplified in the tire specification data D1. Specifically, volume data (cross-sectional area data) of the unvulcanized rubber R forming the green tire G, viscosity data of this unvulcanized rubber R, cross-sectional shape data (and arrangement data) and rigidity data of the carcass layer m2, cross-sectional shape data (and arrangement data) and rigidity data of the bead portion m3, etc. can be exemplified. The tire specification data D1 to be adopted may be only one type of cross-sectional shape data of the green tire G, but one or more other types of tire specification data D1 can also be added. Note that the two-dot chain line CL in the figure indicates the center in the tire width direction.

[0021] Specifically, the cross-sectional shape data D2 of the molding surface 7 of the mold 6 is cross-sectional shape data of the molding surface 7 as exemplified in FIG. 3. The mold 6 exemplified in FIG. 3 is of a sectional type and is composed of a side mold 6a and a sector mold 6b. The side mold 6a vulcanizes and molds mainly the outer side of the side portion of the green tire G and the outer side of the bead portion m3, and the sector mold 6b mainly vulcanizes and molds the tread portion.

[0022] Since the cross-sectional shape of the molding surface 7 generally changes in the tire circumferential direction, cross-sectional shape data of the molding surface 7 at a preset tire circumferential position is used. For example, cross-sectional shape data D2 of a typical molding surface 7 including the most characteristic grooves or cross-sectional shape data D2 of the molding surface 7 with the grooves omitted can be used.

[0023] Alternatively, the portion (site) where the cross-sectional shape changes in the tire circumferential direction of the forming surface 7 can be excluded from the prediction target, and only the portion where the cross-sectional shape does not substantially change in the tire circumferential direction (at least one of the outer side of the side portion and the outer side of the bead portion) can be made the prediction target. That is, the cross-sectional shape may be predicted by limiting it to only the outer side portion of the side portion, only the outer side portion of the bead portion m3, or only the outer side portion of the side portion and the outer side portion of the bead portion m3. In this case, the tire specification data D1 of the portion corresponding to the prediction target and the cross-sectional shape data D2 of the forming surface 7 may be used.

[0024] Examples of the measuring device 5 for measuring and acquiring the cross-sectional shape data of the green tire G include known profile sensors, image capturing devices such as digital cameras, and X-ray imaging devices (CT scanners). When using a profile sensor or an X-ray imaging device (CT scanner), the cross-sectional shape data can be measured and acquired without cutting the green tire G in the cross-section. When using a digital camera or the like, the green tire G is cut in the cross-section and the cut surface is photographed.

[0025] Examples of the measuring device 5 for measuring and acquiring the viscosity data of the unvulcanized rubber R include known viscosity measuring instruments such as Mooney viscometers. This viscosity data may be a measured value at room temperature, but in consideration of the fact that the unvulcanized rubber R is heated in the vulcanization process and its fluidity is improved, the measured value at the temperature at which the fluidity is highest can also be adopted. Examples of the measuring device 5 for measuring and acquiring the volume data (cross-sectional area data) of the unvulcanized rubber R, the cross-sectional shape data (and arrangement data) of the carcass layer m2, and the cross-sectional shape data (and arrangement data) of the bead portion m3 include known image capturing devices such as digital cameras and X-ray imaging devices. Examples of the measuring device 5 for measuring and acquiring the rigidity data of the carcass layer m2 and the bead portion m3 include known bending testers and the like.

[0026] The cross-sectional shape data D2 of the formed surface 7 can be measured and acquired using a measuring device 5 such as a known profile sensor or an image capturing device such as a digital camera for the mold 6. However, since there is generally design drawing data (such as CAD data) used in the manufacture of the mold 6, without measurement, data corresponding to the cross-sectional shape of the formed surface 7 can be extracted from this design drawing data and used as the cross-sectional shape data of the formed surface 7.

[0027] In the present invention, a prediction model PM generated by machine learning is utilized. This prediction model PM is a computer program for predicting the cross-sectional shape of a tire T manufactured by vulcanizing a green tire G. An example of the procedure for generating this prediction model PM will be described.

[0028] First, a large number of green tires G with different tire specification data D1 are vulcanized using a predetermined mold 6 to manufacture a tire T exemplified in FIG. 10. As exemplified in FIG. 4, after the green tire G to be vulcanized is placed in the mold 6, the mold 6 is closed, and pressure and heat are applied between the formed surface 7 of the mold 6 and the vulcanizing bladder 9 that has been inflated. In FIG. 4, the green tire G in its initial shape (before being placed inside the mold 6) is shown, and the cross-sectional shape of the formed surface 7 and the vulcanizing bladder 9 are shown by dashed lines.

[0029] Next, the cross-sectional image data D3 of the manufactured tire T is acquired using a cross-sectional image capturing device 5a. Note that the predetermined mold 6 is not limited to a specific single mold 6, and any mold 6 with the same specifications as the predetermined mold 6 may be used.

[0030] The cross-sectional image data D3 of the tire T to be acquired may be in a state fitted to the mold 6 as exemplified in FIG. 10. The cross-sectional image data D3 of the tire T may be acquired in a state actually fitted to the mold 6, or the tire T may be taken out of the mold 6 and the cross-sectional image data D3 may be acquired in a state (shape) similar to the state when it was fitted to the mold 6.

[0031] Together with the cross-sectional image data D3 of a large number of tires T obtained, tire specification data D1 including the cross-sectional shape of the green tire G before vulcanizing each of the manufactured tires T, and cross-sectional shape data D2 of the molding surface 7 of the mold 6 for vulcanizing this green tire G are prepared. Next, the tire specification data D1, the cross-sectional shape data D2 of the molding surface 7, and the tire cross-sectional image data D3 are used for machine learning as basic data (i.e., teacher data) for predicting the cross-sectional shape of the tire T, thereby generating a prediction model PM.

[0032] Specifically, the above data D1, D2, and D3 are input into the arithmetic unit 2, and machine learning is performed using these data D1, D2, and D3. That is, the relationship between the cross-sectional image of the tire T and the tire specifications of the green tire G and the cross-sectional shape of the molding surface 7 is associated, and the influence of the tire specifications of the green tire G and the cross-sectional shape of the molding surface 7 on the cross-sectional shape of the manufactured tire T is analyzed and evaluated.

[0033] The cross-sectional shape of the tire T is greatly affected by the size of the gap between the outer surface of the green tire G and the molding surface 7 of the mold 6, and the volume of the unvulcanized rubber R between the carcass layer m2 and the molding surface 7. Since the unvulcanized rubber R flows during vulcanization, the viscosity (fluidity) of the unvulcanized rubber R between the carcass layer m2 and the molding surface 7 also affects the cross-sectional shape of the tire T.

[0034] When the gap between the outer surface of the green tire G and the molding surface 7 of the mold 6 is too large, or when the volume of the unvulcanized rubber R between the carcass layer m2 and the molding surface 7 is too small, deformation may occur in the tire T due to insufficient rubber. When the gap between the outer surface of the green tire G and the molding surface 7 of the mold 6 is too small, or when the volume of the unvulcanized rubber R between the carcass layer m2 and the molding surface 7 is too large, deformation may occur in the tire T due to excessive rubber.

[0035] And when the viscosity of the unvulcanized rubber R between the carcass layer m2 and the molding surface 7 is high, the fluidity becomes low, so it is difficult for the shape of the green tire G to change. When this viscosity is low, the fluidity becomes high, so the shape of the green tire G is likely to deform.

[0036] In addition, the cross-sectional shape (and arrangement) and rigidity of the carcass layer m2 affect the fluidity of the unvulcanized rubber R between the carcass layer m2 and the molding surface 7, thus affecting the cross-sectional shape of the tire T. The cross-sectional shape (and arrangement) and rigidity of the bead portion m3 also affect the fluidity of the unvulcanized rubber R between the carcass layer m2 and the molding surface 7, thus affecting the cross-sectional shape of the tire T. The above-described respective factors affect each other in a complex manner, causing the cross-sectional shape of the tire T to change.

[0037] Therefore, by using the data D1, D2, and D3 as teacher data and having artificial intelligence (AI) perform machine learning on the differences, degrees of difference, and characteristics in each case in the data D3 (cross-sectional image data) resulting from the combination of the data D1 and D2, it becomes possible to generate a prediction model PM. As machine learning methods, various known methods such as deep learning using a neural network can be exemplified. In deep learning, a network with a multi-layer structure of an input layer, a plurality of intermediate layers, and an output layer is formed using a known method, and weights are set and connected between nodes between the layers. Then, the tire specification data D1 and the cross-sectional shape data D2 that affect the cross-sectional image data D3 are input from the input layer, and the predicted value of the cross-sectional image data D3 is output to the output layer. The calculated predicted value and the measured value of the cross-sectional image data D3 are compared, and the respective weights are changed so as to reduce the error between the two. Thereby, a prediction model PM with improved prediction accuracy is generated (constructed). The generated prediction model PM is stored in the arithmetic unit 2.

[0038] Next, an example of a procedure for predicting the cross-sectional shape of a target tire Ta manufactured by vulcanizing a green tire Ga to be predicted in a predetermined mold 6 will be described.

[0039] The calculation device 2 inputs the tire specification data D1 of the green tire Ga to be predicted using the input unit 3. The calculation device 2 substitutes the input tire specification data D1 of the green tire Ga and the cross-sectional shape data D2 of the molding surface 7 of the mold 6 into the prediction model PM, and performs a calculation process to execute the prediction model PM. By this calculation process, when the green tire Ga to be predicted is vulcanized using the mold 6 to manufacture the target tire Ta, the cross-sectional shape of the target tire Ta is predicted, and the prediction result is displayed on the display unit 4.

[0040] This prediction is premised on the fact that the bead cores of the pair of bead portions m2 of the green tire Ga are respectively fixed and vulcanized at the normal positions of the molding surface 7. Therefore, the cross-sectional image data D3 of the tire T also uses the data of the tire T in which the bead cores of the pair of bead portions m2 are respectively fixed and vulcanized at the normal positions of the molding surface 7.

[0041] As shown in FIGS. 5 and 6, for example, the prediction result using the prediction model PM shows the outer surface X (profile X) of the cross-sectional shape of the target tire Ta in a solid line. In FIG. 5, the outer surface X of this cross-sectional shape is described together with the cross-sectional shape of the molding surface 7 shown by a broken line. In FIG. 6, the outer surface X of this cross-sectional shape is described together with the outer surface of the cross-sectional shape of the green tire Ga shown by a broken line. Note that the prediction result (outer surface X of the cross-sectional shape) is not limited to the display in FIGS. 5 and 6, and any display that can grasp the outer surface X of the cross-sectional shape of the target tire Ta is acceptable.

[0042] Since the prediction result is displayed in the plane coordinate system of the tire cross-section, it is possible to grasp at a glance how the position of the green tire Ga changes in the target tire Ta. Therefore, it is easy to determine which position of the green tire Ga is excessive or too small with respect to the cross-sectional shape of the target tire. Therefore, it is easy to grasp how much the cross-sectional shape of the green tire Ga should be changed in order to obtain the tire Tg with the target cross-sectional shape.

[0043] In this prediction method, a prediction model PM generated by machine learning using the above-described tire specification data D1, the cross-sectional shape data D2 of the forming surface 7, and the cross-sectional image data D3 of the tire T as teacher data is used. Therefore, the cross-sectional shape of the tire Ta formed by various factors affecting each other complexly can be predicted with higher accuracy by inputting the tire specification data D1 of the green tire Ga to be predicted and the cross-sectional shape data D2 of the forming surface 7 into the prediction model PM for arithmetic processing.

[0044] Also, the cross-sectional shape data of the green tire G adopted as the tire specification data D1 is measured for the actual green tire G using the measuring device 5. Further, since the forming surface 7 is manufactured by precision machining, even when the design drawing data (such as CAD data) used for manufacturing the mold 6 is adopted as the cross-sectional shape data D2 of the forming surface 7, it substantially coincides with the measurement data obtained by measuring the actual forming surface 7 using the measuring device 5. By adopting such tire specification data D1 and the cross-sectional shape data D2 of the forming surface 7, it is advantageous for improving the prediction accuracy.

[0045] The tire specification data D1 preferably includes the volume of the unvulcanized rubber R outside the carcass layer m2 of the green tires G and Ga. This is advantageous for improving the prediction accuracy.

[0046] Also, the tire specification data D1 preferably includes the viscosity data of the unvulcanized rubber R in contact with the forming surface 7 of the green tires G and Ga. That is, including the viscosity data of the unvulcanized rubber R outside the carcass layer m2 is advantageous for improving the prediction accuracy.

[0047] In addition, when including various data as described above in the tire specification data D1, it is advantageous for improving the prediction accuracy. However, as the types of the tire specification data D1 increase, the burden of arithmetic processing increases, and there may be cases where an improvement in prediction accuracy commensurate with this increase in burden cannot be obtained. Therefore, in order to efficiently and accurately make predictions, it is advisable to include at least one type of cross-sectional shape data of the green tire G with the highest influence degree, and add one or more other types of tire specification data D1 as necessary.

[0048] When using only one type of cross-sectional shape data of the green tire G as the tire specification data D1, for example, cross-sectional image data of the green tire G can also be used. In such a case, the prediction model PM is generated using the cross-sectional image data D1 of the green tire G, the cross-sectional image data D3 of the tire T, and the cross-sectional shape data D2 of the molding surface 7.

[0049] As the teaching data, it is also possible to add vulcanization condition data D4 including at least the vulcanization temperature when vulcanizing the green tire G. The vulcanization temperature affects the fluidity of the unvulcanized rubber R, and accordingly, affects the cross-sectional shape of the tire T. Therefore, including the vulcanization temperature in the teaching data is advantageous for improving the prediction accuracy of the cross-sectional shape of the tire Ta. Examples of other vulcanization condition data D4 include the vulcanization pressure applied to the green tire G by the vulcanization bladder 9. The vulcanization pressure also affects the fluidity of the unvulcanized rubber R, and accordingly, affects the cross-sectional shape of the tire T.

[0050] When including the vulcanization condition data D4 in the teaching data, the vulcanization condition data D4 of the green tire Ga to be predicted is input to the arithmetic unit 2, and the input vulcanization condition data D4 is also used for predicting the cross-sectional shape of the target tire Ta. When including the vulcanization condition data D4 in the teaching data, the burden of arithmetic processing increases, and there may be cases where an improvement in prediction accuracy commensurate with this increase in burden cannot be obtained. Therefore, it is advisable to add the vulcanization condition data D4 to the teaching data as necessary.

[0051] If the vulcanization conditions when using this mold 6 do not change much and it is premised that vulcanization is carried out under substantially equivalent vulcanization conditions, there is no need to consider the vulcanization condition data D4. In such a case, the cross-sectional image data D3 under the given vulcanization conditions assumed is used.

[0052] The method for manufacturing a tire of the present invention utilizes the cross-sectional shape prediction method of the present invention. An example of the procedure of the tire manufacturing method will be described.

[0053] In this tire manufacturing method, based on the result predicted using the prediction model PM, the tire specification data D1 of the green tire GaN for manufacturing the tire Tg with the target cross-sectional shape is grasped. That is, referring to FIGS. 5 and 6, the positions and the degrees of correction required for the green tire Ga are grasped. Then, the green tire GaN corrected corresponding to the grasped tire specification data D1 is molded by a known method. For example, as shown in FIG. 7, the outer surface of the cross-sectional shape of the green tire Ga before correction is changed based on the prediction result.

[0054] Next, as illustrated in FIGS. 8 and 9, the green tire GaN corrected by reflecting the prediction result using the prediction model PM is placed in a mold 6 having the same specifications as a predetermined mold 6 installed in a known vulcanizing apparatus 8. Then, the green tire GaN is vulcanized by a known method in the closed mold 6, whereby the tire Ta having the target cross-sectional shape illustrated in FIG. 10 is manufactured.

[0055] In this tire manufacturing method, by utilizing the above-described prediction method, the tire specification data D1 of the green tire GaN for manufacturing the tire Tg with the target cross-sectional shape can be grasped. Since the prediction accuracy of the prediction method to be used is high, it is advantageous to obtain the tire Tg having the target cross-sectional shape by molding the green tire Ga corresponding to the grasped tire specification data D1 and vulcanizing it using a mold 6 having the same specifications as a predetermined mold 6.

Explanation of Reference Numerals

[0056] 1 Prediction system 2 Arithmetic unit 3 Input unit 4 Display unit 5 Measuring device 5a Cross-sectional image capturing device 6 Mold 6a Side mold 6b Sector mold 7 Molding surface 8 Vulcanizing device 9 Vulcanizing bladder PM Prediction model G, Ga, GaN Green tire m1 Inner liner layer m2 Carcass layer m3 Bead part m4 Belt layer R Unvulcanized rubber Rc Vulcanized rubber T, Ta, Tg Tire (vulcanized tire)

Claims

1. Using, as teacher data, tire specification data including the cross-sectional shape of a green tire, cross-sectional shape data of the molding surface of a mold for vulcanizing the green tire, and cross-sectional image data of tires manufactured by vulcanizing a number of the green tires with different tire specification data using the mold, a prediction model for predicting the cross-sectional shape of a tire manufactured by vulcanization is generated by performing machine learning using the teacher data. Tire specification data of a green tire to be predicted is input into an arithmetic unit in which this prediction model is stored, and based on the input tire specification data and the cross-sectional shape data of the molding surface, the cross-sectional shape of a target tire that has been manufactured by vulcanizing the green tire to be predicted using the mold and has reached its final shape is predicted by arithmetic processing performed by the arithmetic unit using the prediction model (however, excluding predicting the shape during the process of vulcanizing the green tire to be predicted).

2. The method for predicting the cross-sectional shape of a tire according to claim 1, wherein the tire specification data includes the volume of unvulcanized rubber outside the carcass layer of the green tire.

3. The method for predicting the cross-sectional shape of a tire according to claim 1 or 2, wherein the tire specification data includes viscosity data of unvulcanized rubber that contacts the molding surface of the green tire.

4. As the teacher data, vulcanization condition data including at least the vulcanization temperature when vulcanizing the green tire is added, the vulcanization condition data of the green tire to be predicted is input into the arithmetic unit, and the input vulcanization condition data is also used for predicting the cross-sectional shape of the target tire. The method for predicting the cross-sectional shape of a tire according to any one of claims 1 to 3.

5. Based on the result predicted by the method for predicting the cross-sectional shape of a tire according to any one of claims 1 to 4, the tire specification data of a green tire for manufacturing a tire with a target cross-sectional shape is grasped, a green tire corresponding to the grasped tire specification data is molded, and the molded green tire is vulcanized using a mold having the same specifications as the mold. A method for manufacturing a tire.

Images