A neural-fuzzy controller with heterogeneous neurons

Abstract

For engineering applications, complex pre-calculations may be necessary to evaluate the fuzzy degree of a simple linguistic term in the conditional part. If these pre-calculations are excluded from the system, it is difficult to discriminate the physical meaning of the rule from the neural nets. Therefore, this work applies feature extraction to replace these pre-calculations. The proposed neural fuzzy system extracts features by heterogeneous neurons. The proposed system's structure and its advantages are described in detailed. A controller designed by the proposed neural fuzzy system is presented as well.