Automatic feature extraction of waveform signals for in-process diagnosticperformance improvement

In this paper, a new methodology is presented for developing a diagnostic s ystem using waveform signals with limited or with no prior fault informatio n. The key issues studied in this paper are automatic fault detection, opti mal feature extraction, optimal feature subset selection, and diagnostic pe rformance assessment. By using this methodology, a diagnostic system can be developed and its performance is continuously improved as the knowledge of process faults is automatically accumulated during production. As a real e xample, the tonnage signal analysis for stamping process monitoring is prov ided to demonstrate the implementation of this methodology.