Artificial neural network to predict the weld status in laser welding of copper to aluminum

Laser welding of copper to aluminum is challenging due the formation complex intermetallic phases. More Al (~18.5 at. %) can be dissolved in Cu, contrast Cu (~2.5 Al. Therefore, from side, large melting achieved. However optimum and must melted for a strong joint. Finding right amount difficult time consuming by tradition analysis technique like inspection weld cross-sections. Considering speed process complexity involving with metallography cross-sections, alternative rapid method qualify welds are necessary. The acoustic emission during laser give proportional information Al, melted. With such an approach status obtained real time. In this paper signal using airborne sensor audible range 20 Hz kHz, correlated strength material mixing (Al, melt). Finally, predicted artificial neural network based on acquired signal.