By using acoustic emission (AE) it is possible to control deviations and surface quality during micro milling operations. The controlling of such deviations are based on large amounts of associated wear especially in rapid micro machining environments With an increase in AE it is possible to see when tool wear is approaching critical levels and requires swap out. AE is very sensitive to tool wear especially in some micro environments where other measurements can be prone to errors and difficulties. In addition, in the case of drilling both force and power are considered sensitive to tool wear. In the case of drilling it was possible to use rules based on both Classification and Regression Trees (CART) and Neural Networks (NN) to implement a simulation displaying how such a control regime could be used in a real time environment; corrective measures correlated to wear levels providing control automated tool changes.