Temperature Control in Precalcinator with Dual Heuristic Dynamic Programming

In cement manufacturing, pre-calcining process (PCP) contains an added precalcinator between the preheater and the kiln. Since raw meal decomposition rate in the kiln is over 90%, optimal control is necessary for keeping the temperature stable to ensure normal decomposition. Due to the diversity of raw meal composition and the consistent thermal transformation, temperature control in the precalcinator is a complex nonlinear control problem. Many factors may influence it, and there are couplings between various factors and uncertainties. It is difficult to solve the dynamic stability control problem for the temperature in precalcinator. This paper addresses temperature control in the precalcinator using dual heuristic dynamic programming (DHP). The approach is mainly composed of three parts: model network, action network and critic network. All three parts use neural networks (NN) to simulate the temperature trend. The self-learning and adaptive abilities were analyzed in the MATLAB environment and simulation results demonstrate the advantage of adaptation and optimization solutions compared to conventional control.