The Research of the Temperature Decoupling Control Based on QDRNN in Ammonia Synthesis Converter

Considering the coupling of the bed temperature control of sections in ammonia synthesis converter, by means of the analysis for quasi-diagonal recurrent neural network (QDRNN) and the gradient descent method (GMD), a dual-variable decoupling control scheme based on QDRNN is designed in temperature control system of ammonia synthesis converter. The structure and principle of the algorithm has been illustrated in this paper. Through the comparison of simulation results, it shows that the proposed scheme has better control effect than the conventional PID decoupling control scheme.