Fuzzy adaptive networks in machining process modeling: surface roughness prediction for turning operations

Due to the complexity of the machine tool structure and the cutting process, the dynamics of machining processes are still not completely understood. This is especially true due to the demand of high-speed machining to increase productivity. In order to model and control these complex processes, new approaches, which can represent complex phenomenon combined with learning ability, are needed. The combined neural–fuzzy approach appears to be ideally suited for this purpose. In this paper, the recently developed fuzzy adaptive network (FAN) is used to model surface roughness in turning operations. The FAN network has both the learning ability of neural network and linguistic representation of complex, not well-understood, vague phenomenon. Furthermore, it can continuously improve the initially obtained rough model based on the daily operating data. To illustrate this approach, a model representing the influences of machining parameters on surface roughness is established and then the model is verified by the use of the results of pilot experiments. Finally, a comparison with the results based on statistical regression is provided.