Premium
Dynamic Process Modelling using a PCA‐based Output Integrated Recurrent Neural Network
Author(s) -
Qian Yu,
Cheng Huag,
Li Xiuxi,
Jiang Yanbin
Publication year - 2002
Publication title -
the canadian journal of chemical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.404
H-Index - 67
eISSN - 1939-019X
pISSN - 0008-4034
DOI - 10.1002/cjce.5450800415
Subject(s) - principal component analysis , artificial neural network , dimension (graph theory) , process (computing) , computer science , feedforward neural network , feed forward , dimensionality reduction , recurrent neural network , component (thermodynamics) , artificial intelligence , machine learning , control engineering , engineering , mathematics , physics , pure mathematics , thermodynamics , operating system
Abstract A new methodology for modelling of dynamic process systems, the output integrated recurrent neural network (OIRNN), is presented in this paper. OIRNN can be regarded as a modified Jordan recurrent neural network, in which the past values for certain steps of the output variables are integrated with the input variables, and the original input variables are pre‐processed using principal component analysis (PCA) for the purpose of dimension reduction. The main advantage of the PCA‐based OIRNN is that the input dimension is reduced, so that the network can be used to model the dynamic behavior of multiple input multiple output (MIMO) systems effectively. The new method is illustrated with reference to the Tennessee‐Eastman process and compared with principal component regression and feedforward neural networks.