Multiple sensor monitoring of machining was investigated for online cutting tool life assessment through cognitive decision making based on signal processing for feature extraction and pattern recognition. Sensor signals obtained from sensor monitoring of turning operations were processed and analysed. The outcome was a set of extracted signal features correlated with the consumed tool life percentage. The aim of the work is to build an online cognitive system, based on artificial neural networks, able to predict the consumed tool life during turning operations. A preliminary experimental campaign was carried out for the construction of the sensorial knowledge database; the neural network type, architecture and training algorithm. After setting up the sensorial knowledge database and the neural network paradigm, the cognitive decision making system is ready to be implemented for online cutting tool life prediction during actual turning operations by exploiting the capacity of neural networks to constantly learn and improve through interaction with the sensorial data acquisition and processing system.
展开▼
