To ensure overall quality of a precision large-scale component, a tool condition monitoring (TCM) technique for multi-step form milling is presented. The form milling of fir tree slots for a steam turbine rotor is an appropriate example that requires a fine surface finish and high dimensional accuracy. Therefore, we propose a novel TCM system based on a multi-sensor fusion strategy which utilises the combination of spindle motor current and acoustic emission (AE) as well as adaptive thresholding for multiple manufacturing steps (roughing, semi-finishing and finishing). To investigate the tool deterioration process, tool longevity tests using a test piece are carried out for each step. With the aid of qualitative inspection, it is found that AE signals provide comprehensive tool state information regarding tool flank wear, crack propagation and severe adhesive wear. In addition, by intentionally adding a bundle of chips to the surface, bursts of AE of large amplitudes occur in finishing, which provides the possibility of discovering anomalous events related to surface quality. By careful consideration of such characteristics, provisional alert levels are determined using a two-dimensional diagram with respect to both sensors. The strategy is verified throughout the actual manufacturing processes of the rotors. The proposed TCM system shows not only an excellent ability to prevent catastrophic tool failure and surface irregularities in form milling but also acceptable expendability for various groove specifications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.