Constructive transparent direction basis function network learning for non-linear control

A constructive direction basis function network (DBFN) learning method is applied. This approach uses the functional equivalence principles between DBFN and fuzzy systems in order to achieve a minimal structure network. Firstly, an initial network based on linguistic descriptions is constructed. Secondly, a constrained constructive adaptation law, based on a minimal resource allocating algorithm, is applied in order to adjust on-line the structure and parameters of the DBFN, keeping the transparency property and guaranteeing the linguistic interpretation. Thus, at any instant, knowledge from the network can be easily extracted, validating its structure. Experimental results in a benchmark process show the effectiveness of the presented approach.