Systems and methods for inspecting absorbent articles on a converting line
AssigneeThe Procter & Gamble Company
InventorsPaul Anthony Kawka, Stephen Michael Varga, Aitzaz Ahmad
Life of this patent
Estimating the term…
Abstract
A method for inspecting absorbent articles is provided. The inspection is performed using an inspection algorithm generated with a convolutional neural network having convolutional neural network parameters. The convolutional neural network parameters are generated by a training algorithm. Based on the inspection, characteristics of the absorbent articles, such as defects, can be identified. Absorbent articles having identified characteristics can be rejected, or other actions can be taken.
Claims20
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.
A method for inspecting absorbent articles, the method comprising the steps of:
- creating a database comprising a first group of digitized signals of a first group of absorbent articles and a second group of digitized signals of a second group of absorbent articles, each absorbent article of the first group comprising a first characteristic, and each absorbent article of the second group not comprising the first characteristic;
- 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 inspection data of the substrate with the sensor;
- communicating the inspection data from the sensor to the controller;
- identifying first characteristics by analyzing the inspection data with the inspection algorithm;
- and
- cutting the substrate into discrete absorbent articles.
A method for inspecting absorbent articles, the method comprising the steps of:
- creating a database comprising a first group of digitized signals of a first group of absorbent articles and a second group of digitized signals of a second group of absorbent articles, each absorbent article of the first group comprising a first characteristic, and each absorbent article of the second group not comprising the first characteristic;
- 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;
- advancing a substrate through a converting process;
- creating inspection data of the substrate with a sensor;
- communicating the inspection data from the sensor to a controller, wherein the controller comprises the inspection algorithm;
- identifying first characteristics by analyzing the inspection data with the inspection algorithm;
- and
- cutting the substrate into discrete absorbent articles.
Dependencies are inferred from the claim text.