Parallel Type-2 Fuzzy Logic Co-Processors for Engine Management

Abstract

Marine diesel engines operate in highly dynamic and uncertain environments, hence they require robust and accurate speed controllers that can handle the encountered uncertainties. Type-2 fuzzy logic controllers (FLCs) have shown that they can handle such uncertainties and give a superior performance to the existing commercial controllers. However, there are a number of computational bottlenecks that pose as significant barriers to the widespread deployment of type-2 FLCs in commercial embedded control systems. This paper explores the use of parallel hardware implementations of interval type-2 FLC as a means to eradicate these barriers thus producing bespoke co-processors for a soft core implementation of a FPGA based 32 bit RISC micro-processor. These coprocessors will perform functions such as fuzzification and type reduction and are currently utilised as part of a larger embedded interval type-2 fuzzy engine management system (T2FEMS). Numerous timing comparisons were undertaken between the co-processors and their sequential counterparts where the type-2 co-processors reduced significantly the computational cycles required by the type-2 FLC. This reduction in computational cycles allowed the T2FEMS to produce faster control responses whilst offering a superior control performance to the commercial engine management systems. Thus the proposed co-processors enable us to fully explore the potential of interval and possibly general type-2 FLCs in commercial embedded applications.