A recurrent neural fuzzy network controller for a temperature control system

Temperature control by a TSK-type Recurrent Neural Fuzzy Network (TRNFN) controller based on the direct inverse control configuration is proposed in this paper. The TRNFN is a recurrent fuzzy network developed from a series of TSK type fuzzy if-then rules, and is on-line constructed by concurrent structure/parameter learning. The TRNFN has the following advantages when applied to temperature control problems (1) high learning ability, which considerably reduces the controller training time, (2) no a priori knowledge of the plant order is required, which eases the design process, (3) high control performance. These advantages are verified by applying TRNFN to a real water bath temperature control plant, where the performance of a backpropagation neural network is compared.