Artificial Neural Network tuned cascade control for temperature control of polymerization reactor

The temperature control of a polymerization reactor described by Chylla and Haase, which is a control engineering benchmark problem, is used to illustrate the potential of adaptive control design by extending the conventional cascade control concept. In the benchmark scenario, the operation of the reactor must be guaranteed under various disturbing influences, e.g., changing ambient temperatures or impurity of the monomer. The cascade control provides a robust operation, but often lacks in control performance concerning the required strict temperature tolerances. The control concept presented in this contribution solves the problem by employing a self tuning cascade control concept in order to improve the performance of the temperature control. This design calculates a trajectory for the cooling jacket temperature in order to follow a predefined trajectory of the reactor temperature. Thereby, the reaction heat as well as the heat transfer coefficient in the energy balance is estimated by using Artificial Neural Network (ANN). Two simple physically motivated relations are employed, which allow the non-delayed estimation of both quantities. Simulation results under model uncertainties show the effectiveness of the self tuning cascade control concept.