Defects Detection in Continuous Manufacturing by means of Convolutional Neural Networks

Authors:
José A. Calderón-Martinez;Pascual Campoy-Cervera
Affiliations:
Department of Automatic Control, Electrical Engineering and Industrial Computing, Universidad Politecnica de Madrid, Madrid, Spain 28006 and Instituto Tecnologico de Aguascalientes, Aguascalientes ...;Department of Automatic Control, Electrical Engineering and Industrial Computing, Universidad Politecnica de Madrid, Madrid, Spain 28006
Venue:
IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Year:
2009

Citing 4
Cited 1

Convolutional networks for images, speech, and time series

The handbook of brain theory and neural networks
Real-time vision-based system for textile fabric inspection

Real-Time Imaging
Automatic Generation of Digital Filters by NN Based Learning: An Application on Paper Pulp Inspection

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Face recognition: a convolutional neural-network approach

IEEE Transactions on Neural Networks

Application perspectives for the convolutional downward spiral architecture

ICS'08 Proceedings of the 12th WSEAS international conference on Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Detecting defects in paper pulp manufacturing process's using a non-touched, effective, on-line and fast method is critical in the paper industry. This work presents a neural network based system for detecting pitchand shivedefects using digital filters generated by a Convolutional Neural Architecture. The main subjects discussed are: generating digital filters automatically, filters optimal size for this application, and detecting and identifying defects. The experimental results exhibit how simple and powerful is the architecture designed for generating filters to detect different defect types.