A Self-Organizing Recurrent Neural Network Based on Dynamic Analysis

摘要

A recurrent neural network with a self-organizing structure based on the dynamic analysis of atask is presented in this paper. The stability of the recurrent neural network is guaranteed bydesign. A dynamic analysis method to sequence the subsystems of the recurrent neural networkaccording to the fitness between the subsystems and the target system is developed. The networkis trained with the network's structure self-organized by dynamically activating subsystems ofthe network according to tasks. The experiments showed the proposed network is capable ofactivating appropriate subsystems to approximate different nonlinear dynamic systemsregardless of the inputs. When the network was applied to the problem of simultaneously softmeasuring the chemical oxygen demand (COD) and NH3-N in wastewater treatment process, itshowed its ability of avoiding the coupling influence of the two parameters and thus achieved amore desirable outcome.