In: Proc. IEEE Int. Conf. on Robotics and Automation, 10-15 May 1999, Detroit, MI, Vol. 2, pages 1502-1507. 1999.
Abstract: The paper presents an intelligent architecture based fuzzy Petri net with a feed-forward neural network for modeling product quality in a CNC machining center. It discusses how the proposed architecture can be used for modeling, monitoring and control a product quality specification such as surface roughness. The surface roughness represents the output quality specification manufactured by CNC machining center as a result of a milling process. The fuzzy Petri net approach utilizes the exact input milling parameters, such as the spindle speed, feed-rate, tool diameter and coolant (off/on) which can be obtained via the machine or sensor system. The neural network approach employed the selected input parameters defined by the machine operator via the CNC code. The aim of the proposed architecture is to model the required quality of surface roughness.
Keywords: fuzzy Petri nets, neural networks, product quality modeling, surface roughness.