Jian Zhang, Fengchun Tian, Simon X. Yang, Yan Liu, Zhifang Liang, and Di Wang
Electronic nose, tobacco, intelligent, automatic curing, artificial neural network
An intelligent and automatic control method for tobacco flue-curing based on machine learning was proposed which makes use both of a priori rules (human knowledge) of tobacco curing and collected feature data about tobacco during the curing period. An artificial neural network (ANN) model had been established to build the relationship between the inputs including smell, image, moisture and other extracted features of tobacco and the outputs, i.e., the parameters of flue-curing process. Then an automatic flue-curing process emerged out with the ANN. The preliminary results obtained from performance analysis and field experiment are very promising and acceptable.
Important Links:
Go Back
