A multiple sensor monitoring procedure is developed with the aim to perform tool wear forecast in drilling of CFRP/CFRP stacks. Experimental drilling tests with a traditional twist drill bit and an innovative step drill bit are carried out using a multi-sensor system to acquire thrust force and torque signals during the process. The tool wear curve for each drill bit under different drilling conditions is obtained by measuring the tool flank wear. An artificial neural network for pattern recognition is developed to find correlations between selected sensor signal features and tool wear state, with the aim to forecast the tool wear values during drilling based on the information extracted from the acquired sensor signals.
Multiple sensor monitoring for tool wear forecast in drilling of CFRP/CFRP stacks with traditional and innovative drill bits
Alessandra Caggiano;
2018-01-01
Abstract
A multiple sensor monitoring procedure is developed with the aim to perform tool wear forecast in drilling of CFRP/CFRP stacks. Experimental drilling tests with a traditional twist drill bit and an innovative step drill bit are carried out using a multi-sensor system to acquire thrust force and torque signals during the process. The tool wear curve for each drill bit under different drilling conditions is obtained by measuring the tool flank wear. An artificial neural network for pattern recognition is developed to find correlations between selected sensor signal features and tool wear state, with the aim to forecast the tool wear values during drilling based on the information extracted from the acquired sensor signals.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
