A neuro-fuzzy system is used to predict the condition of the tool in a milling process. Specifically the relationship between the sensor readings and tool wear state is first captured via a neural network and is subsequently reflected in linguistic form in terms of a fuzzy logic based diagnostic algorithm. In this approach, the neural network serves as an interpolative mechanism for the generation of data that is consistent with the behavior of the process, whereas fuzzy logic provides a transparent view of the relationship between the measured variables and the tool wear state. The methodology used in this paper incorporates an error-based, density-driven adaptation scheme in conjunction with a neural network based reference model to adapt the fuzzy membership functions associated with the tool condition monitoring algorithm to ensure that the rule set reflects the true nature of the inter-relationship between the sensor readings and the tool condition. Experimental results show that the proposed fuzzy mechanism correctly predicts the condition of the tool in 97 percent of the cases where it is applied.