Fuzzy Nets Based on-line Cutting Power Recognition in Milling Operations

A self-organising fuzzy-nets optimisation system was developed to generate a knowledge bank able to demonstrate the required cutting power on-line for a short length of time in an NC verifier. This fuzzy-nets system (FNS) uses a five-step self-learning procedure, and was examined for end-milling operations on a Fadal VMC40 vertical machining centre. Data collected from the operations were used to train and test the FNS. Three approaches were employed to predict the cutting power:

1. Metal cutting theory model.

2. Fuzzy-nets model using theoretical data for training.

3. Fuzzy-nets model using experimental data for training.

To compare the quality of the data obtained from these approaches, three hypotheses were formulated for this study. The results showed that the FNS possessed a satisfactory range of accuracy with the intended applications of the model.