Abstract
Wire electrical discharge machining (WEDM) is investigated in the perspective of zero-defect manufacturing with the scope to detect anomalous process conditions leading to typical defects generated during WEDM, i.e. the occurrence of lines and marks on the resulting workpiece surface. A multiple sensor monitoring system is employed to acquire high sampling rate sensorial data relative to signals of voltage and current in the gap between workpiece and wire electrode. An advanced signal processing methodology is implemented to extract and select the most relevant features useful to identify the undesired process conditions through a cognitive pattern recognition paradigm.