Real-time tool wear identification using sensor integration with neural network

Real-time identification of tool wear in shop floor environment is essential for optimization of machining processes and implementation of automated manufacturing systems. In this paper. the signals obtained from acoustic emission and power sensors during machining processes are analyzed and a set of feature parameters characterizing the tool wear condition are extracted. In order to realize the realtime tool wear condition monitoring for different cutting conditions, a sensor integration strategy which combines the information from multiple sensors (acoustic emission sensor and power sensor) and machining parameters is proposed. A neural network based on improved back-propogation algorithm is developed and a prototype scheme for realtime identification of tool wear is implemented. Experiments under different conditions have proved that a higher rate of tool wear identification can be achieved by using the sensor integration model with neural network. The results also indicated that the neural network is a very effective method of sensor integration for online monitoring of tool abnormalities