Multisensory fusion based virtual tool wear sensing for ubiquitous manufacturing

Abstract

Pervasiveness of ubiquitous computing advances the manufacturing scheme into a ubiquitous manufacturing era which poses significant challenges on sensing technology and system reliability. To improve manufacturing system reliability, this paper presents a new virtual tool wear sensing technique based on multisensory data fusion and artificial intelligence model for tool condition monitoring. It infers the difficult-to-measure tool wear parameters (e.g. tool wear width) by fusing in-process multisensory data (e.g. force, vibration, etc.) with dimension reduction technique and support vector regression model. Different state-of-the-art dimension reduction techniques including kernel principal component analysis, locally linear embedding, isometric feature mapping, and minimum redundancy maximum relevant method have been investigated for feature fusion in a virtual sensing model, and the kernel principal component analysis performs best in terms of sensing accuracy. The effectiveness of the developed virtual tool wear sensing technique is experimentally validated in a set of machining tool run-to-failure tests on a computer numerical control milling machine. The results show that the estimated tool wear width through virtual sensing is comparable to that measured offline by a microscope instrument in terms of accuracy, moreover, in a more cost-effective manner. A multi-sensory fusion based virtual tool wear sensing model is developed.KPCA performs best among the dimension reduction techniques investigated.The virtual tool wear sensing model is validated using a machining tool life test.The performance of the model is comparable to the costly offline instrumentation.