US 12,459,182 B2
Resin film manufacturing device and resin film manufacturing method
Ryuichiro Maenishi, Tokyo (JP); Nobuhiro Haramoto, Tokyo (JP); and Fumitake Fujii, Ube (JP)
Assigned to THE JAPAN STEEL WORKS, LTD., Tokyo (JP)
Filed by THE JAPAN STEEL WORKS, LTD., Tokyo (JP)
Filed on Jul. 6, 2022, as Appl. No. 17/858,178.
Application 17/858,178 is a division of application No. 16/792,259, filed on Feb. 16, 2020, granted, now 11,426,914.
Claims priority of application No. 2019-048425 (JP), filed on Mar. 15, 2019; and application No. 2019-227255 (JP), filed on Dec. 17, 2019.
Prior Publication US 2022/0339838 A1, Oct. 27, 2022
Int. Cl. B29C 48/08 (2019.01); B29C 48/31 (2019.01); B29C 48/355 (2019.01); B29C 48/92 (2019.01)
CPC B29C 48/08 (2019.02) [B29C 48/313 (2019.02); B29C 48/355 (2019.02); B29C 48/92 (2019.02); B29C 2948/92647 (2019.02)] 7 Claims
OG exemplary drawing
 
1. A resin film manufacturing method comprising steps of:
(a) extruding a molten resin from a gap between a pair of lips of a die, the die including a plurality of pairs of heat bolts arranged along a longer side of the pair of lips, and heaters for heating the heat bolts, being configured to be adjusted a lip gap for each of the heat bolts;
(b) conveying a resin film and measuring a thickness distribution along a width of the resin film, the resin film being a solidified form of the molten resin;
(c) calculating a control error from the measured thickness distribution, the control error representing a difference between a thickness distribution target value and the measured thickness distribution; and
(d) for each heat bolt, performing feedback control of the lip gap by:
(d1) determining a current state and a reward based on the control error calculated from the thickness distribution, a state representing a predetermined control error range, wherein
the determining of the current state includes determining in which one of a plurality of predetermined control error ranges does the calculated control error fall into, and
the determining of the reward includes determining whether an action selected in a state previous to the current state is an appropriate action for the current state, wherein
the action is determined to be an appropriate action when an absolute value of the calculated control error is smaller than an absolute value of a control error calculated for a state previous to the current state, and an action is determined to not be appropriate when the absolute value of the calculated control error is larger than the absolute value of the control error calculated for the state previous to the current state,
(d2) updating control conditions based on the determined reward and selecting an action corresponding to the current state from the updated control conditions, the control conditions being a combination of states and actions, and
(d3) controlling a corresponding heater based on the selected action corresponding to the current state from the updated control conditions.