Dressing is an essential process for the machining industries. The grinding community keeps the slogan “grinding is dressing,” given the importance of this reconditioning process. This paper presents a methodology for forecasting the dresser width one step forward by using indirect monitoring. The dresser width is an important parameter to guarantee the quality of the dressing process and, in many cases, it is monitored directly by the operators. Acoustic emission signals were collected during the dressing process and an estimation neural network was used to correlate the dresser width with the processed signals to estimate the current value of the width. The output of the estimation network was input to a time-delay neural network to predict the next value of the dresser width. By utilizing this procedure, an automatic system would be able to readjust the dressing parameters while avoiding the stops, reducing costs, and maintaining repeatability during the process.

Inferential measurement of the dresser width for the grinding process automation / Ferreira, Fabio Isaac; de Aguiar, Paulo Roberto; Lopes, Wenderson Nascimento; Martins, Cesar Henrique Rossinoli; Ruzzi, Rodrigo de Souza; Bianchi, Eduardo Carlos; D’Addona, Doriana Marilena. - In: INTERNATIONAL JOURNAL, ADVANCED MANUFACTURING TECHNOLOGY. - ISSN 0268-3768. - 100:9-12(2019), pp. 3055-3066. [10.1007/s00170-018-2869-x]

Inferential measurement of the dresser width for the grinding process automation

D’Addona, Doriana Marilena
2019

Abstract

Dressing is an essential process for the machining industries. The grinding community keeps the slogan “grinding is dressing,” given the importance of this reconditioning process. This paper presents a methodology for forecasting the dresser width one step forward by using indirect monitoring. The dresser width is an important parameter to guarantee the quality of the dressing process and, in many cases, it is monitored directly by the operators. Acoustic emission signals were collected during the dressing process and an estimation neural network was used to correlate the dresser width with the processed signals to estimate the current value of the width. The output of the estimation network was input to a time-delay neural network to predict the next value of the dresser width. By utilizing this procedure, an automatic system would be able to readjust the dressing parameters while avoiding the stops, reducing costs, and maintaining repeatability during the process.
2019
Inferential measurement of the dresser width for the grinding process automation / Ferreira, Fabio Isaac; de Aguiar, Paulo Roberto; Lopes, Wenderson Nascimento; Martins, Cesar Henrique Rossinoli; Ruzzi, Rodrigo de Souza; Bianchi, Eduardo Carlos; D’Addona, Doriana Marilena. - In: INTERNATIONAL JOURNAL, ADVANCED MANUFACTURING TECHNOLOGY. - ISSN 0268-3768. - 100:9-12(2019), pp. 3055-3066. [10.1007/s00170-018-2869-x]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: https://hdl.handle.net/11588/746901
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 6
social impact