Process application of a nonlinear adaptive control strategy based on radial basis function networks

A nonlinear adaptive control strategy based on radial basis function networks is applied to a simulated polymerization reactor. Two modifications of the basic control scheme are proposed to enhance computational efficiency. The effective system dimension is reduced by applying nonlinear principal component analysis to state variable data obtained from open-loop tests. This allows the radial basis functions to be placed in a reduced dimensional space rather than the original state space. The total number of basis functions is specified a priori and an algorithm which adjusts the location of the basis function centers to surround the current operating point is proposed. This avoids computational problems associated with online addition of basis functions. The modified adaptive control strategy is evaluated for setpoint changes and unmeasured disturbances