Drill wear monitoring using artificial neural network with differential evolution learning

In an advanced manufacturing system, accurate assessment of tool life/tool wear estimation is very essential for optimization of cutting parameters in cutting operations. Estimation of tool fife generally requires considerable time and material and hence it is a relatively expensive procedure. In this present work, artificial neural network (ANN) has been used for the prediction of drill wear. Recently there have been significant research efforts to apply evolutionary computational techniques for determining the network weights. Hence an evolutionary technique named differential evolution has been used and it is proven that the experimental results matched well with the values predicted by both artificial neural network with back-propagation and the proposed method.