A new on-line tool wear states detecting method, with spindle and feed curr
ent signal in boring, is presented. By analyzing the effects of tool wear,
as well as the cutting parameters on the current signals, the models of the
relationship between the current signals and the cutting parameters are es
tablished under different tool wear states with partial experimental design
and regression analysis. Fuzzy classification method is then used to obtai
n the membership degree of each tool wear classification with measured spin
dle and feed current values. Finally, the membership results of the spindle
current and feed current are fused by the fuzzy inference method, and the
tool wear state may be detected effectively. The validity and reliability o
f the method are verified by experimental results. The method can be effect
ively employed in practice.