US 12,175,373 B2
Injection molding machine system
Takayuki Hirano, Hiroshima (JP); Akihiko Saeki, Hiroshima (JP); Akira Morii, Hiroshima (JP); and Hiroshi Onishi, Hiroshima (JP)
Assigned to THE JAPAN STEEL WORKS, LTD., Tokyo (JP)
Appl. No. 16/982,903
Filed by THE JAPAN STEEL WORKS, LTD., Tokyo (JP)
PCT Filed Mar. 22, 2019, PCT No. PCT/JP2019/012230
§ 371(c)(1), (2) Date Sep. 21, 2020,
PCT Pub. No. WO2019/182145, PCT Pub. Date Sep. 26, 2019.
Claims priority of application No. 2018-055633 (JP), filed on Mar. 23, 2018.
Prior Publication US 2021/0001526 A1, Jan. 7, 2021
Int. Cl. G06N 3/092 (2023.01); B29C 45/76 (2006.01)
CPC G06N 3/092 (2023.01) [B29C 45/768 (2013.01); B29C 2945/76949 (2013.01)] 6 Claims
OG exemplary drawing
 
1. An injection molding machine system comprising:
an agent having a machine learner, the machine learner performing reinforcement learning of determining an action according to a value function while receiving rewards for actions done in various states and learning the value function, and
an injection molding machine configured to manufacture a mold product under prescribed molding conditions; and
the injection molding machine system being configured to adjust the molding conditions using the agent,
wherein the machine learner is configured to:
use, as the state, only physical data obtained from the injection molding machine and a defect type representing a kind of a molding defect of the mold product;
use the molding conditions as the action; and
use, as the reward, a defect state indicating a defect degree of a molding defect.