This paper describes an industrial application of neural networks which proved to be very successful and which is currently working on one assembly line with the perspective of a future expansion to other production plants. The task is the quality control in the production of refrigerators, detecting possible defects that can lead either to a real malfunction or even to a degradation of their performance. The testing phase was required to be accomplished in a short time with respect to a complete testing in order to avoid delays in the production process. Moreover the requirements for the testing system included an easy extension to different products, a good detection of the malfunctioning equipment and a simple use for the personnel. The system is based on a classifier realized with neural autoassociators. This approach allows us to build easily a model of the standard functional equipment, which satisfies the product requirements, by learning from examples. The neural autoassociator can learn to recognize functional devices only from positive samples, but in order to improve its recognition performance the learning algorithm can be extended easily to take into account also negative examples. Thus, the performance of the classifier can be improved by collecting the samples on which it produced a wrong or an ambiguous result and by adding these new examples to the learning set that is used to refine the classifier.

Maggini, M. (2000). Application of Neural Autoassociators to Short Testing of Refrigerators. AIIA NOTIZIE, 13(3), 35-38.

Application of Neural Autoassociators to Short Testing of Refrigerators

MAGGINI, MARCO
2000

Abstract

This paper describes an industrial application of neural networks which proved to be very successful and which is currently working on one assembly line with the perspective of a future expansion to other production plants. The task is the quality control in the production of refrigerators, detecting possible defects that can lead either to a real malfunction or even to a degradation of their performance. The testing phase was required to be accomplished in a short time with respect to a complete testing in order to avoid delays in the production process. Moreover the requirements for the testing system included an easy extension to different products, a good detection of the malfunctioning equipment and a simple use for the personnel. The system is based on a classifier realized with neural autoassociators. This approach allows us to build easily a model of the standard functional equipment, which satisfies the product requirements, by learning from examples. The neural autoassociator can learn to recognize functional devices only from positive samples, but in order to improve its recognition performance the learning algorithm can be extended easily to take into account also negative examples. Thus, the performance of the classifier can be improved by collecting the samples on which it produced a wrong or an ambiguous result and by adding these new examples to the learning set that is used to refine the classifier.
File in questo prodotto:
File Dimensione Formato  
AIIA.pdf

non disponibili

Tipologia: Pre-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 869.11 kB
Formato Adobe PDF
869.11 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11365/29674
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo