Formal language techniques may be used to study controlled dynamical systems and lead to a formulation in terms of context-dependent grammars. Using automata as basic units we obtain an on-line implementation of the grammars. The implementation has a hierarchical structure, the lowest level dealing with the identification of alphabet symbols (terminal and non-terminal), and the other with the establishment of the grammar productions. The method provides an automatic construction of the automata network from the experimental data. In particular, the parallel-processing capabilities of automata networks improves the performance of grammar-based models for control and anomaly detection in electromechanical devices of industrial relevance. One such example is presented.
|Journal||Engineering Applications Of Artificial Intelligence|
|Publication status||Published - 1 Jan 2009|