SUMMARY

Regenerative chatter in machining, characterized by self-excited vibration, is a common process anomaly that limits productivity and part quality in machining operations. This thesis proposes an on-line approach for chatter detection via effective human-machine interaction, facilitating knowledge transfer from experienced machinists to the “digital apprentice” through the “learnable skill primitive” (LSP) method that establishes a chatter detection threshold. The research focus is to develop a methodology for chatter-specific knowledge acquisition and a human-machine interface inspired by computing techniques and frameworks such as learning from demonstration and interactive agent shaping. The learned chatter detection thresholds were obtained through the LSP method by temporally mapping the reaction data to the cutting signal. In addition, a variance mitigation strategy was developed to reduce the negative impact of the high variance in the operator’s reaction time to chatter. Milling experiments were conducted to evaluate the detection accuracy, detection speed, and robustness of the learned chatter detection thresholds. Experimental data support the claim that the learned thresholds can detect chatter with high detection accuracy and good detection speed. Finally, the learned thresholds were demonstrated to be robust to milling of different workpiece materials under different cutting conditions such as feeds, speeds, axial and radial immersions (depths of cut), and cutting directions.