Neurocontrol and elastic fuzzy logic: capabilities, concepts, and applications

摘要

The author shows how elastic fuzzy logic (EFL) nets make it possible to combine the capabilities of expert systems with the learning capabilities of neural networks at a high level. ANN (artificial neural network) implementations have advantages in terms of hardware implementation, ease of use, generality, and links to the brain, which is still the only true intelligent controller available. Neurocontrol is useful in cloning experts, tracking trajectories or setpoints, and optimization (e.g., approximate dynamic programming). There has been substantial success in controlling robot arms (including the main arm of the Space Shuttle), chemical process control, continuous production of high-quality parts, and other aerospace applications. A review of the basic designs and concepts, with reference to both the applications and future research opportunities, is given.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>