The accuracy and precision of computer numerical control (CNC) machine tool
s directly affect the dimensional accuracy of machined parts. Fast detectio
n of machine tool contouring errors is required to guarantee the accuracy o
f the manufacturing process and, further, to eliminate errors through error
compensation techniques. In this paper, several typical contouring error p
atterns of CNC machine tools (i.e., cyclic, backlash, scale mismatch, etc.)
are presented. Detection of machine tool contouring errors is conducted in
two steps using wavelet transforms (WT) and neural networks (NN). In the f
irst step, wavelet transform is applied to contouring error signals to extr
act error features. In the second step, wavelet coefficients are grouped in
to proper input units for neural networks; that is, data were compressed by
omitting unnecessary details. In this study, cascade-correlation (CC) neur
al networks are selected to recognize the seven basic patterns of CNC conto
uring errors. Multiple contouring errors can also be identified quantitativ
ely in the WT-NN approach.