Hierarchical Process Neural Network Model within Variable-Sampling Time
The biochemical processes are usually described as seriously time varying and nonlinear dynamic systems. It is very costly and difficult to build their first-principle models due to the absence of inherent mechanism and efficient on-line sensors. In this paper, a hierarchical process neural network (HPNN) model within variable-sampling time has been proposed. Simulation is based on penicillin fed-batch fermentation process, shows that the model established is more accurately and efficient, and suffice for the requirements of control and optimization for biochemical processes.
L. Chen and F. Liu, "Hierarchical Process Neural Network Model within Variable-Sampling Time", Applied Mechanics and Materials, Vols. 20-23, pp. 920-925, 2010