access icon openaccess Performance prediction of tobacco flavouring using response surface methodology and artificial neural network

This is an open access article published by the IET under the Creative Commons Attribution -NonCommercial License (http://creativecommons.org/licenses/by-nc/3.0/)
Received 04/10/2018, Accepted 17/10/2018, Revised 15/10/2018, Published 22/10/2018

This study was to predict the optimum condition for leaf flavouring in cigarette manufacturing. To this purpose, an integrated research was used by using response surface and artificial neural network. A series of tobacco flavouring experiment's factors were designed by Experimental Design software. The MATLAB software's Neural Network function was used to forecast the responses, and the optimal solution configuration was coming out from the Response Surface Analysis Method. In the optimum condition, moisture removal opening, roller speed and tobacco process flow, pressure and feed liquid gas ejector flow are 18.60%, 10.74 rpm, 5314.11 kg/h, 3.70 bar and 243.63 kg/h, uniformity of the evaluation index and the utilization rate of material liquid distribution are 93.088% and 98.694%. With the corresponding experimental, results are consistent, under the condition of the error to less 7%, the test results show that through a few experimental data of predictive results of the neural network and response surface design has a certain practicability.

Inspec keywords: design of experiments; neural nets; response surface methodology; tobacco industry

Other keywords: Expert Response Surface; tobacco flow; roller speed; Experimental Design software; cigarette manufacturing; pressure 3.7 bar; spice ejector flow; artificial neural network; tobacco process flow; feed liquid gas ejector flow; response surface design; Response Surface Analysis Method; response data; MATLAB software; tobacco flavouring experiment; response surface methodology; optimal solution configuration

Subjects: Production engineering computing; Neural computing techniques; Numerical analysis; Industrial processes; Other manufacturing industries; Interpolation and function approximation (numerical analysis); Industrial applications of IT; Engineering materials

References

    1. 1)
      • 1. Qinghui, Z.: ‘A brief discussion on the application of cigarette flavoring technology’, Tob. Technol., 1996, 29, (4), pp. 30–30.
    2. 2)
      • 4. Aliakbarian, B., Sampaio, F.C., Faria, J.D., et al: ‘Optimization of spray drying microencapsulation of olive pomace polyphenols using response surface methodology and artificial neural network’, LWT, 2018, 93, pp. 220–228.
    3. 3)
      • 6. Hua, B.H., Qiong, L., Ze, L., et al: ‘The neural network model and its evaluation of the physical quality of tobacco’, J. Yunnan Agric. Univ., Nat. Sci., 2016, 31, (5), pp. 874–879.
    4. 4)
      • 3. Ji, K.: ‘Evaluation of mining engineering technology innovation ability and application based on BP neural network’. Int. Conf. Industrial Technology and Management, Singapore, 2017, pp. 55–59.
    5. 5)
      • 5. Zhang, J., Peng, L.I., Sun, S.H., et al: ‘Simultaneous determination of 1,2-propylene glycol, glycerol and triethylene glycol of smokeless tobacco products by gas chromatography-mass spectrometry’, Tob. Sci. Technol., 2011, 3, pp. 36–42.
    6. 6)
      • 2. Li, L., Sai, Z., Qiang, H., et al: ‘Application of response surface method in test design and optimization’, Lab. Res. Explor., 2015, 34, (8), pp. 41–45.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2018.9038
Loading

Related content

content/journals/10.1049/joe.2018.9038
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading