| CPC G06N 5/04 (2013.01) [G05B 19/188 (2013.01); G05B 19/406 (2013.01); G06N 20/00 (2019.01); G05B 2219/45239 (2013.01)] | 6 Claims |
|
1. A learned model generation method of generating a learned model for maintenance of a winding apparatus including
a first supply reel that supplies a first electrode sheet,
a second supply reel that supplies a second electrode sheet,
a first bonding roller that is provided on a first electrode sheet side,
a second bonding roller that is provided on a second electrode sheet side, and is paired with the first bonding roller to bond the first electrode sheet and the second electrode sheet to each other,
a first winding core,
a second winding core,
a winding core rotation driver that, during a winding operation, moves the first winding core to a predetermined winding position, winds the first electrode sheet and the second electrode sheet on the first winding core in an overlapping manner, moves the second winding core to the predetermined winding position, and winds the first electrode sheet and the second electrode sheet on the second winding core in an overlapping manner, and
a sensor that, during the winding operation, reads a first end surface of the first electrode sheet and a second end surface of the second electrode sheet along a radial direction of a first winding body in which the first electrode sheet and the second electrode sheet are wound in an overlapping manner by a plurality of turns on the first winding core, and reads a third end surface of the first electrode sheet and a fourth end surface of the second electrode sheet along a radial direction of a second winding body in which the first electrode sheet and the second electrode sheet are wound in an overlapping manner by a plurality of turns on the second winding core, the learned model generation method comprising:
acquiring, using a controller and from the sensor, first group data including image data indicating a position of the first end surface read along the radial direction of the first winding body, second group data including image data indicating a position of the second end surface read along the radial direction of the first winding body, third group data including image data indicating a position of the third end surface read along the radial direction of the second winding body, and fourth group data including image data indicating a position of the fourth end surface read along the radial direction of the second winding body;
comparing each of the first group data, the second group data, the third group data, and the fourth group data to predetermined reference data in order to determine if there is a defect present in the first winding body or the second winding body, the defect being determined based on a positional relationship among: 1) continuous positions of the third end surface indicated by the third group data, 2) continuous positions of the fourth end surface indicated by the fourth group data, and 3) reference lines included as the predetermined reference data;
generating a first learned model using the third group data and the fourth group data, when it is determined that the second winding body has the defect, the first learned model outputting information indicating that the defect in the second winding body is caused by the second winding core;
acquiring, using the controller and from the sensor, fifth group data indicating a position of a fifth end surface of the first electrode sheet along a radial direction of a third winding body in which the first electrode sheet and the second electrode sheet are wound in an overlapping manner by a plurality of turns on the first winding core and sixth group data indicating a position of a sixth end surface of the second electrode sheet along the radial direction of the third winding body,
comparing each of the fifth group data and sixth group data to the predetermined reference data in order to determine if there is a defect present in the third winding body, the defect being determined based on a positional relationship among: 1) continuous positions of the fifth end surface indicated by the fifth group data, 2) continuous positions of the sixth end surface indicated by the sixth group data, and 3) reference lines as the predetermined reference data; and
generating a second learning model, using the first group data, the second group data, the third group data, the fourth group data, the fifth group data, and the sixth group data, when it is determined that the third winding body has the defect, the second learning model outputting information indicating that the defect in the third winding body is caused by the first winding core;
determining a first maintenance plan to correct the second winding core, when the first learning model outputs information indicating that the defect in the second winding body is caused by the second winding core, and determining a second maintenance plan to correct the first winding core, when the second learning model outputs information indicating that the defect in the third winding body is caused by the first winding core; and
outputting the first maintenance plan or the second maintenance plan to a display for performing correct action and correcting the defect in the second winding body or the third winding body.
|