ONLINE CUTTING STATE RECOGNITION IN TURNING USING A NEURAL-NETWORK

Tool wear, chatter vibration, chip breaking and built-up edge are the main phenomena to be monitored in modern manufacturing processes. Much work has been carried out in the analysis and detection of these phen omena. However, most work has been mainly concerned with single, isola ted detection I of such phenomena. The relationships between each faul t have so far received very little attention. This paper presents a ne ural-network-based on-line fault diagnosis scheme which monitors the l evel of tool wear, chatter vibration and chip breaking in a turning op eration. The experimental results show that the neural network has a h igh prediction success rate.