Title :
Multi-moving-window neural network for modeling of purified terephthalic acid solvent system
Author :
Xu, Yuan ; Zhu, Qunxiong
Author_Institution :
Coll. of Inf. Sci. & Technol., Beijing Univ. of Chem. Technol., Beijing, China
Abstract :
To explore the unsteady-state and dynamics of purified terephthalic acid (PTA) solvent system, a multi-moving-window neural network (MMWNN) is proposed for process modeling. The core of this modeling approach is that multi-moving-window concept is incorporated in combination with auto-associative neural network (AANN) and generalized regression neural network (GRNN). The integrated neural network model is developed with different moving windows for process inputs, AANN for data compression and GRNN for model prediction, which can effectively capture the changing process dynamics, reduce the data dimension and reveal the nonlinear relationship between process variables and final output. For comparison, single-moving-window with AANN and GRNN (SMWNN), none-moving-window with AANN and GRNN (NMWNN) are also established for process modeling. Through the actual application in PTA solvent system of a chemical plant, the predicted results show that the proposed MMWNN is supervior to other neural networks with smaller prediction error that is more consistent with actual process. It is considered that MMWNN modeling could provide a useful guideline to explore the complicated dynamics of industry process.
Keywords :
chemical reactors; industrial plants; neurocontrollers; oxidation; purification; regression analysis; solvents (industrial); autoassociative neural network; chemical plant; data compression; data dimension; generalized regression neural network; industry process; model prediction; multimoving-window neural network; none-moving-window; nonlinear relationship; process dynamics; process modeling; process variable; purified terephthalic acid solvent system; single-moving-window; unsteady-state system; Artificial neural networks; Data models; Indexes; Poles and towers; Predictive models; Solvents; PTA solvent system; auto-associative neural network; generalized regression neural network; modeling; multi-moving window;
Conference_Titel :
Intelligent Control and Automation (WCICA), 2010 8th World Congress on
Conference_Location :
Jinan
Print_ISBN :
978-1-4244-6712-9
DOI :
10.1109/WCICA.2010.5553789