| Summary: | This research study intends to develop an online tool condition monitoring system and to examine scientifically the effect of machining parameters on quality measures during machining SAE 1015 steel. It is accomplished by adopting a novel microflown sound sensor which is capable of acquiring sound signals. The dry turning experiments were performed by employing uncoated, TiAlN, TiAlN/WC-C coated inserts. The optimal cutting conditions and their influence on flank wear were determined and predicted value has been validated through confirmation experiment. During machining, sound signals were acquired using NI DAQ card and statistical analysis of raw data has been performed. Kurtosis and I-Kaz coefficient was determined systematically. The correlation between flank wear and I-Kaz coefficient was established, which fits into power-law curve. The neural network model was trained and developed with least error (3.7603e-5). It reveals that the developed neural network can be effectively utilized with minimal error for online monitoring.
|
|---|