Fuzzy Adaptive Control of Machining Processes With a Self-Learning Algorithm

Abstract

When machining conditions change significantly, applying parameter-adaptive control to the cutting system by varying the table feedrate allows a constant cutting force to be maintained. Although several controller schemes have been proposed, their cutting control performance is limited especially when the cutting conditions vary significantly. This paper presents an adaptive fuzzy logic control (FLC) developed for cutting processes under various cutting conditions. The controller adopts on-line scaling factors for cases with varied cutting parameters. In addition, a reliable self-learning (SL) algorithm is proposed to achieve even better cutting performance by modifying the adaptive FLC rule base according to properly weighted performance measurements. Both simulation and experimental results show that given a sufficient number of learning cases, the adaptive SL-FLC is effective for a wide range of applications. The successful implementation of the proposed adaptive SL-FLC algorithm on an industrial heavy-duty machining center indicates that the proposed adaptive SL-FLC is feasible for use in manufacturing industries.