The authors present a methodology that can monitor machine degradation behavior. A pattern discrimination model based on a cerebellar model articulation controller (CMAC) neural network was developed. An example in monitoring robot performance was used to study the feasibility of the developed technique. Experimental results showed that the technique can monitor machine degradation and detect faults quantitatively and adaptively. This methodology could help operators set up machines for a given criterion, determine whether the machine is running correctly, and predict problems before they occur. As a result, maintenance hours could be used more effectively and productively. >