Abstract
A novel architecture of hierarchical adaptive neuro-fuzzy inference systems was developed, which was tuned using a genetic algorithm and particle swarm optimization algorithm, separately. It was used to establish input-output relationships of a plasma spray coating process. The parameters, namely primary gas flow rate, stand-off distance, powder flow rate and arc current were considered as inputs of the process and the quality of coating was represented using three responses, such as its thickness, porosity and microhardness. Particle swarm optimization-based approach was found to perform better than the genetic algorithm-based approach on some test cases.