Quality Prediction Model Based on PCA-BP Neural Network for Tobacco Leaves Redrying Process

Abstract:

Aiming to the problem that is very difficult to establish the mechanism model of quality for the process of tobacco leaves redrying, this paper proposes a quality prediction model based on principal component analysis (PCA) and improved back propagation (BP)neural network for tobacco leaves redrying process. Firstly, 12 input variables are confirmed by analyzing the factors on quality of tobacco leaves redrying process. Second, the methods of PCA is used to eliminate the correlation of original input layer data, in which 12 input variables are transformed into 6 uncorrelated indicators. Then, the quality prediction model based on improved BP neural network is established. Finally, a simulation experiment is conducted and the average prediction error is as low as 1.03%, the absolute error for forecasting is fluctuated in the range of 0.16% - 2.49%. The result indicates that the model is simpler and has higher stability for prediction, which can completely meet the actual requirements of the tobacco leaves redrying process.

• Periodical: Advanced Materials Research (Volumes 201-203)
• Pages: 1627-1631
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.201-203.1627
• Online since: February 2011
• Authors: Jian Kang Yin, Chang Hua Chen, Jing Min Li, Fei Zhang, Jin Yao
• Keywords: BP Neural Network (BPNN), Principal Component Analysis (PCA), Quality Prediction Model, Tobacco Leaves Redrying Process

References

[1] LIU Huan. Technology and equipment of tobacco threshing and redrying. Henan: Science and Technology Press, (2005).

[2] DONG Ling-jiao , YAN Xiao-he. The Application of Self-adaptation Fuzzy PID in the Tobacco-redrying System. Journal of Wenzhou Vocational ＆ Technical College, 2006, 6(2): 40-42.

[3] SONG Bei-guang. An Application of Fuzzy Neural Adaptive PID Control in a Tobacco Leaf Re-Baking System. Henan Science, 2004, 24(6): 899-901.

[4] GUAN Gui-chun, HU Peng. Research on the Heat Transfer and Mass Transfer of Tobacco during Drying Process in Redryer. Light Industry Machinery, 2006, 24(3): 40-42.

[5] Wilson J A, Zorzetto L R M. A generalized approach to process state estimation using hybrid artificial neural network/mechanistic models. Computer Chemistry Engineering, 1997, 21(9): 951-963.

DOI: 10.1016/s0098-1354(96)00336-5

[6] Yang, C.H.; Deconinck, G. et al. 2002. An optimal power-dispatching system using neural network for the electrochemical process of zinc depending on varying prices of electricity. IEEE Transactions on Neural Networks 13(1): 229-236.

DOI: 10.1109/72.977311

[7] Xu, C.H.; Wu, M. 2009. Quantity-quality Prediction Model Based on Neural Networks in Lead-zinc Sintering Process. Journal of System Simulation 21(4): 1024-1028.

[8] GUAN Zi-ming, Chang Wen-bing. Estimating Approach for Aviation Spare Parts Based on Principal Component Analysis and RBF Artificial Neural Network [J]. Journal of Beijing Technology and Business University (Natural Science Edition), 2009, 27(3): 60-64.

[9] ZHANG Jie, YAN Xian-hui. Multivariate Statistical Process Control. Beijing: Chemical Industry Press, (2000).

[10] Hagan M T, Demuth H B, Beale M H. Neural Network Design. Boston, USA: PWS Publishing, (1996).