Authors:
Rodolpho F. Godoy Neto
;
Marcelo Marchi
;
Cesar Martins
;
Paulo R. Aguiar
and
Eduardo Bianchi
Affiliation:
Univ. Estadual Paulista - UNESP, Brazil
Keyword(s):
Neural Network Application, Monitoring, Acoustic Emission, Grinding Process, Burn.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Industrial Applications of AI
;
Soft Computing
Abstract:
The grinding process is widely used in surface finishing of steel parts and corresponds to one of the last
steps in the manufacturing process. Thus, it’s essential to have a reliable monitoring of this process. In
grinding of metals, the phenomenon of burn is one of the worst faults to be avoided. Therefore, a monitoring
system able to identify this phenomenon would be of great importance for the process. Thus, the aim of this
work is the monitoring of burn during the grinding process through an intelligent system that uses acoustic
emission (AE) and vibration signals as inputs. Tests were performed on a surface grinding machine,
workpiece SAE 1020 and aluminum oxide grinding wheel were used. The acquisition of the vibration
signals and AE was done by means of an oscilloscope with a sampling rate of 2MHz. By analyzing the
frequency spectra of these signals it was possible to determine the frequency bands that best characterized
the phenomenon of burn. These bands were used as inputs
to an artificial neural networks capable of
classifying the surface condition of the part. The results of this study allowed characterizing the surface of
the work piece into three groups: No burn, burn and high surface roughness. The selected neural model has
produced good results for classifying the three patterns studied.
(More)