Monitoring of tool status using intelligent acoustic emission sensing and decision based neural network

Successful automation of manufacturing processes is must for production of high quality, customized and economical products demanded by todays customers. This calls for uninterrupted machining with desirable process parameters. This can be ensured by continuous monitoring of machining status, which is strongly influenced by the condition of the cutting tool. In this paper, a new scheme is proposed and evaluated for intelligent tool status monitoring. This paper describes the possibility of sensor integration in a machining process through a neural network. Experiments were conducted to study the influence of flank wear on AE and cutting forces. This collected data is then used as training patterns for the neural network. The decision based neural network is used to integrate this information and consequently for deciding on the condition of the tool. The results show that acoustic emission-cutting force based multi-sensory-monitoring methodology classifies tool status correctly