A COMPREHENSIVE IDENTIFICATION OF TOOL FAILURE AND CHATTER USING A PARALLEL MULTI-ART2 NEURAL-NETWORK

Tool failure and charter are two major problems during machining. To d etect and distinguish the occurrences of these two abnormal conditions , a novel parallel multi-ART2 neural network has been developed. An ad vantage of this network is more reliable identification of a variety o f complex patterns. This is due to the sharing of multi-input feature information by its multiple ART2 subnetworks which allow for finer vig ilance thresholds. Using the maximum frequency-band coherence function of two acceleration signals and the relative weighted frequency-band power ratio of an acoustic emission signal as input feature informatio n, the network has been found to identify various tool failure and cha tter states in turning operations with a total of 96.4% success rate o ver a wide range of cutting conditions, compared to that of 80.4% obta inable with the single-ART2 neural network.