Rubber mixing machine control device, method and program utilizing machine learning

Patent metadata

Field	Value
Publication number	US-11141884-B2
Application number	US-201716622364-A
Country	US
Kind code	B2
Filing date	Jul 6, 2017
Priority date	Jul 6, 2017
Publication date	Oct 12, 2021
Grant date	Oct 12, 2021

Abstract

The measured value of a rubber temperature parameter that is related to the temperature of a rubber material to be kneaded by a mixing machine 2 and measured values of correlation parameters that have a correlation with a change in the value of the rubber temperature parameter are acquired. The measured values are assigned to an operational control parameter-calculation model equation, which is modified from a rubber temperature parameter-calculation model equation including operational control parameters and the correlation parameters, and a constant and coefficients of the operational control parameters and the correlation parameters are calculated using a machine learning algorithm. A predetermined operational control parameter, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, is calculated using an operational control parameter-calculation equation that is specified by the coefficients and the constant calculated using the machine learning algorithm.

First claim

The invention claimed is:

1. A mixing machine control device comprising:
a measured value-acquisition unit that acquires a measured value of a rubber temperature parameter related to a temperature of a rubber material to be mixed by a mixing machine and measured values of correlation parameters, which have a correlation with a change in the value of the rubber temperature parameter caused by the kneading of the mixing machine and include at least operational control parameters of the mixing machine specified by correlation analysis;
a machine learning unit that assigns the measured values to an operational control parameter-calculation model equation, which is modified from a rubber temperature parameter-calculation model equation including the operational control parameters and the correlation parameters and calculates a predetermined operational control parameter among the plurality of operational control parameters, and calculates a constant and coefficients of the operational control parameters and the correlation parameters by using a machine learning algorithm; and
an operational control parameter-calculation unit that calculates the predetermined operational control parameter, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, by using an operational control parameter-calculation equation specified by the coefficients and the constant calculated using the machine learning algorithm.

2. The mixing machine control device according to claim 1 ,
wherein the predetermined operational control parameter is the number of rotations per unit time of a rotor of the mixing machine that kneads the rubber material, and
the operational control parameter-calculation unit calculates the number of rotations per unit time of the rotor, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, by using the operational control parameter-calculation equation that calculates the number of rotations per unit time of the rotor.

3. The mixing machine control device according to claim 1 ,
wherein the predetermined operational control parameter is a cooling water temperature where the mixing machine cools the rubber material, and
the operational control parameter-calculation unit calculates the cooling water temperature, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, by using the operational control parameter-calculation equation that calculates the cooling water temperature.

4. The mixing machine control device according to claim 1 ,
wherein the predetermined operational control parameter is pressure of a ram of the mixing machine that presses the rubber material into a mixing chamber, and
the operational control parameter-calculation unit calculates the pressure of the ram, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, by using the operational control parameter-calculation equation that calculates the pressure of the ram.

5. The mixing machine control device according to claim 1 ,
wherein the predetermined operational control parameter is the amount of cooling water that cools an object to be cooled in the mixing machine, and
the operational control parameter-calculation unit calculates the amount of the cooling water, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, by using the operational control parameter-calculation equation that calculates the amount of the cooling water.

6. The mixing machine control device according to claim 1 ,
wherein the predetermined operational control parameter is a moving distance of the ram of the mixing machine, which presses the rubber material into the mixing chamber, from a reference position, and
the operational control parameter-calculation unit calculates the moving distance of the ram from the reference position, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, by using the operational control parameter-calculation equation that calculates the moving distance of the ram from the reference position.

7. The mixing machine control device according to claim 1 ,
wherein the rubber temperature parameter represents a ratio of a temperature change of the rubber material to a predetermined time.

8. The mixing machine control device according to claim 1 ,
wherein the measured value-acquisition unit acquires the measured value of the rubber temperature parameter and the measured values of the correlation parameters in each operation form for kneading the rubber material by the mixing machine,
the machine learning unit calculates a constant and coefficients of the operational control parameters and the correlation parameters that are required in a case corresponding to each operation form, and
the operational control parameter-calculation unit calculates the predetermined operational control parameter that is required in a case in which the rubber temperature parameter is controlled to a predetermined value in each operation form.

9. A mixing machine control method comprising:
acquiring a measured value of a rubber temperature parameter related to a temperature of a rubber material to be kneaded by a mixing machine and measured values of correlation parameters that have a correlation with a change in the value of the rubber temperature parameter caused by the kneading of the mixing machine and include at least operational control parameters of the mixing machine specified by correlation analysis;
assigning the measured values to an operational control parameter-calculation model equation, which is modified from a rubber temperature parameter-calculation model equation including the operational control parameters and the correlation parameters and calculates a predetermined operational control parameter among the plurality of operational control parameters, and calculating a constant and coefficients of the operational control parameters and the correlation parameters by using a machine learning algorithm; and
calculating the predetermined operational control parameter, which is required in a case in which the rubber temperature parameter is controlled to a predetermined value, by using an operational control parameter-calculation equation specified by the coefficients and the constant calculated using the machine learning algorithm.

10. A non-transitory computer-readable storage medium having stored therein a program causing a computer to implement:
acquiring a measured value of a rubber temperature parameter related to a temperature of a rubber material to be kneaded by a mixing machine and measured values of correlation parameters that have a correlation with a change in the value of the rubber temperature parameter caused by the kneading of the mixing machine and include at least operational control parameters of the mixing machine specified by correlation analysis;
assigning the measured values to an operational control parameter-calculation model equation, which is modified from a rubber temperature parameter-calculation model equation including the operational control parameters and the correlation parameters and calculates a predetermined operational control parameter among the plurality of operational control parameters, and calculating a constant and coefficients of the operational control parameters and the correlation parameters by using a machine learning algorithm; and
calculating the predetermined operational control parameter, which is required in a case in which the rubber temperature parameter is controlled to a predet

Assignees

• Mitsubishi Heavy Ind Mach Systems Ltd

Inventors

• Matsushita Yoichi
• Soga Ryota
• Noguchi Shinichi
• Shintani Koji

Classifications

• B29B7/823 Primary

  Temperature control · CPC title

• B29B7/286 Primary

  measuring properties of the mixture, e.g. temperature, density (B29B7/283 takes precedence) · CPC title

• B29B7/7495

  for mixing rubber · CPC title

• B29B7/283

  measuring data of the driving system, e.g. torque, speed, power · CPC title

• B29B7/28

  for measuring, controlling or regulating, e.g. viscosity control {(B29B7/242 takes precedence)} · CPC title