ESTIMATION OF TOOL WEAR LENGTH IN FINISH MILLING USING A FUZZY INFERENCE ALGORITHM

The geometric accuracy and surface roughness are mainly affected by th e flank wear at the minor cutting edge in finish machining. A fuzzy es timator obtained by a fuzzy inference algorithm with a max-min composi tion rule to evaluate the minor flank wear length in finish milling is introduced. The features sensitive to minor flank wear are extracted from the dispersion analysis of a time series AR model of the feed dir ectional acceleration of the spindle housing. Linguistic rules for fuz zy estimation are constructed using these features, and then fuzzy inf erences are carried out with test data sets under various cutting cond itions. The proposed system turns out to be effective for estimating m inor flank wear length, and its mean error is less than 12%.