Resin film manufacturing device and resin film manufacturing method
AssigneeThe Japan Steel Works, Ltd.
InventorsRyuichiro Maenishi, Nobuhiro Haramoto, Fumitake Fujii
Life of this patent
Estimating the term…
Abstract
In a resin film manufacturing device according to an embodiment, a current state and a reward for a previously selected action are determined for each heat bolt based on a control error calculated from a thickness distribution of a resin film acquired from a thickness sensor. Then, control conditions, which are a combination of states and actions, are updated based on the reward, and a most appropriate action corresponding to the current state is selected from the updated control conditions. Then, the heater is controlled based on the most appropriate action.
Claims7
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.
Dependencies are inferred from the claim text.