CYCLIC WAVEFORM SIGNAL ANALYSIS FOR ONLINE MONITORING OF VALVE SEAT ASSEMBLY PROCESSES

摘要

High dimensional cyclic waveform sensing signals are commonly used for manufacturing system monitoring. However, the lack of effective analysis methods in current monitoring systems causes major concerns in production in terms of monitoring performance. In this study, a generic methodology for analyzing cyclic waveform signals is proposed, and a false rejection problem in the engine valve seat assembly process was used as a case study to illustrate the proposed methodology. Performance comparison using production data has been conducted and the results have demonstrated the improvement on the false rejection reduction for potential productivity improvement.