08.31.21
Paul Anthony Kawka, Cleves, OH; Stephen Michael Varga, Loveland, OH; and Aitzaz Ahmad, Mason, OH.
Assigned to The Procter & Gamble Company, Cincinnati, OH.
Filed: 3/24/20
Issued: 7/6/21
A method for inspecting absorbent articles, the method comprising the steps of: creating a database comprising a first group of images of a first group of articles and a second group of images of a second group of absorbent articles, each absorbent article of the first group comprising a first defect, and each absorbent article of the second group comprising no first defect; providing the database to a training algorithm to create convolutional neural network parameters; generating an inspection algorithm with a convolutional neural network based on the database using the convolutional neural network parameters; providing a sensor; providing a controller, the controller comprising the inspection algorithm; advancing a substrate through a converting process; creating images of the substrate with the sensor; communicating the images from the sensor to the controller; identifying first defects by analyzing the images with the inspection algorithm; cutting the substrate into discrete absorbent articles; and rejecting absorbent articles that correspond with identified first defects.
Assigned to The Procter & Gamble Company, Cincinnati, OH.
Filed: 3/24/20
Issued: 7/6/21
A method for inspecting absorbent articles, the method comprising the steps of: creating a database comprising a first group of images of a first group of articles and a second group of images of a second group of absorbent articles, each absorbent article of the first group comprising a first defect, and each absorbent article of the second group comprising no first defect; providing the database to a training algorithm to create convolutional neural network parameters; generating an inspection algorithm with a convolutional neural network based on the database using the convolutional neural network parameters; providing a sensor; providing a controller, the controller comprising the inspection algorithm; advancing a substrate through a converting process; creating images of the substrate with the sensor; communicating the images from the sensor to the controller; identifying first defects by analyzing the images with the inspection algorithm; cutting the substrate into discrete absorbent articles; and rejecting absorbent articles that correspond with identified first defects.