Arti cial Neural Networks (NNs) are high parallel structures that consist of a large number of elementary non-linear units (called neurons) fully interconnected. In this article we present a hardware implementation of NNs combined with a DSP; both NNs and DSP combined together results in a powerful system used in control applications. NNs process most of the control tasks, while DSP performs signal pre-processing, signal conditioning and learning algorithms. In some cases the DSP performs the control of some discrete states of the plant by implementing nite state automata and/or verifying plant safety boundary operations. With this \marriage", NNs hardware can be very simple because several operations related with the NNs (learning algorithms, weights maintains, etc.) can be performed by the DSP. The system implements intelligent control paradigms mixing Neuro-Fuzzy algorithms with nite state automata and/or digital control algorithms.
[1]
Leonardo Maria Reyneri.
An Introduction to Fuzzy State Automata
,
1997,
IWANN.
[2]
Li-Xin Wang,et al.
Adaptive fuzzy systems and control
,
1994
.
[3]
Jun Zhou,et al.
Hierarchical fuzzy control
,
1991
.
[4]
Eduardo D. Sontag,et al.
Neural Networks for Control
,
1993
.
[5]
Leonardo Maria Reyneri,et al.
Cintia: a neuro-fuzzy real-time controller for low-power embedded systems
,
1995,
IEEE Micro.
[6]
Marcello Chiaberge,et al.
Simulation of an hexapode walking machine controlled by neural network
,
1993
.
[7]
Chuen-Chien Lee,et al.
Fuzzy logic in control systems: fuzzy logic controller. I
,
1990,
IEEE Trans. Syst. Man Cybern..
[8]
Simon Haykin,et al.
Neural Networks: A Comprehensive Foundation
,
1998
.