Title :
Soft sensor modeling of AlCl3·6H2O content based on Powell-BP
Author :
Yang, Jie ; Gao, Zengliang ; Liu, Yi
Author_Institution :
Inst. of Process Equip. & Control Eng., Zhejiang Univ. of Technol., Hangzhou, China
Abstract :
The production period of the crystalline aluminium chloride is considerably long. However, the offline assay of AlCl3·6H2O content has large time delay. Thus soft sensor modeling is needed to analyze its content, and estimate the value to improve the product quality. The conventional back-propagation (BP) neural network training is easily trapped to the local minimum, To overcome this embarrassment, the Powell method is adopted to optimize the training algorithm, improve the method of extremum computing, and reduce the difficulty of network realization. Finally, the soft sensor model of AlCl3·6H2O is established. Test results show that, compared with conventional neural network algorithms, the prediction of Powell-BP is more accurate and the convergence time is shorter.
Keywords :
backpropagation; chemistry computing; learning (artificial intelligence); manufacturing processes; neural nets; optimisation; production engineering computing; AlCl3; H2O; Powell-BP method; backpropagation; crystalline aluminium chloride; neural network training; production period; soft sensor modeling; Aluminum; Computer networks; Convergence; Crystallization; Delay effects; Neural networks; Optimization methods; Prediction algorithms; Production; Testing; BP neural network; Powell method; crystalline aluminium chloride; soft sensor;
Conference_Titel :
Informatics in Control, Automation and Robotics (CAR), 2010 2nd International Asia Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5192-0
Electronic_ISBN :
1948-3414
DOI :
10.1109/CAR.2010.5456584
