This paper presents a robust strategy for estimating tool wear in meta
l-cutting operations. The proposed estimation algorithm consists of tw
o components: a recurrent neural network to model the tool wear dynami
cs, and it robust observer to estimate the tool wear from this model u
sing measurements of cutting force. The authors show that the algorith
m ensures that the tool wear estimation error is uniformly bounded in
the presence of bounded unmodelled effects, and that the ultimate boun
d on this error can be made as small as desired. The proposed approach
is applied to the problem of estimating tool wear in turning and is s
hown to provide wear estimates that are in close agreement with experi
mental results.