A nonlinear gain scheduling control strategy based on neuro-fuzzy network models is proposed. In neuro-fuzzy-network-based modeling, the process operation is partitioned into several fuzzy operating regions, and within each region, a local linear model is used to model the process. The global model output is obtained through center-of-gravity defuzzification. Process knowledge is used to initially set up the network structure, and process input-output data are used to train the network. Based on a neuro-fuzzy network model, a nonlinear controller can be developed by combining several local linear controllers that are tuned on the basis of the local model parameters. This strategy represents a nonlinear gain scheduled controller. The techniques have been successfully applied to the modeling and control of pH dynamics in a simulated continuous stirred tank reactor.