Skip to Main Content
In modern process control systems, Ethernet is achieving a leading position, proposing itself as a network capable of supporting all communication needs at all levels in the Computer Integrated Manufacturing hierarchy. The main obstacle to using Ethernet at the Field level is the nondeterminism of the Ethernet MAC protocol, which cannot provide real-time traffic with bounded channel access times. This paper focuses on industrial applications featuring soft real-time constraints, such as periodic control or industrial multimedia, which do not require deterministic guarantees on deadline meeting. To cope with this class of applications, Ethernet should be able to guarantee the timely delivery of real-time packets in statistical terms. The paper presents fuzzy traffic smoothing, a technique to perform adaptive traffic smoothing over Ethernet networks at the Field level thus enabling them to provide a statistical bound on packet delivery time. Previous work showed that the fuzzy smoother outperforms other adaptive smoothers proposed in the literature. This paper addresses fuzzy smoother optimization through genetic algorithms. The proposed optimization is applied to tune the inference engine membership functions. The results obtained show the effectiveness of the approach.