Title :
Soft-Sensing Modeling Method of Vinyl Acetate Polymerization Rate Based on BP Neural Network
Author :
Huang Jiangping ; Tao Huihui ; Zhu Zhigao
Author_Institution :
East China Jiaotong Univ., Nanchang, China
Abstract :
Providing a soft-sensing modeling method of vinyl acetate (VAC) polymerization rate based on BP neural network. Solving the current problem that the VAC polymerization rate in the polyvinyl alcohol (PVA) producing process is hard to real-time measuring. Using the data samples collected from the scene to train the network. In the network learning process, using the Levenberg-Marquardt optimization algorithm. Finally, testing the network which has completed training. Test result shows that soft-sensing model of VAC polymerization rate based on BP neural network is accurate and effective.
Keywords :
backpropagation; neural nets; optimisation; polymerisation; real-time systems; resins; BP neural network; Levenberg-Marquardt optimization algorithm; PVA; VAC; network learning process; polyvinyl alcohol; real-time measurement; soft sensing modeling method; vinyl acetate polymerization rate; Layout; Methanol; Multi-layer neural network; Neural networks; Neurons; Polymers; Production; Software measurement; Temperature; Testing; BP network; Modeling; Soft-sensing; VAC polymerization rate;
Conference_Titel :
Measuring Technology and Mechatronics Automation (ICMTMA), 2010 International Conference on
Conference_Location :
Changsha City
Print_ISBN :
978-1-4244-5001-5
Electronic_ISBN :
978-1-4244-5739-7
DOI :
10.1109/ICMTMA.2010.326
