Abstract
To address the issue that the control timeliness of the drying process is affected by the unavoidable time delay of moisture content measurement, a soft sensing approach for moisture content in tobacco is proposed, which is based on a multi-channel convolutional neural network (MC-CNN). Firstly, the filtered parameter features are sampled within the lag time and converted into a two-dimensional matrix. Then the parameters of different categories are cyclically transformed to build the input image-like data with multiple channels. Through multiple convolution layers and pooling layers, the MC-CNN model extracts multi-channel features from the feature maps. Moreover, the model effectively perceives the time-sequential and state-spatial coupling characteristics from the raw production data. The proposed method is then validated based on the production data collected from the real production process in the cigarette factory. An online prediction application has been finally achieved to measure the moisture content. Therefore, the detection delay is eliminated and the response time for exceptions is greatly decreased. The amount of tobacco with abnormal moisture content is greatly reduced in the drying process. As the result, the MAE and RMSE of the data measured by the proposed method in a normal production batch are 0.0136 and 0.0257, respectively. Through comparison and analysis of a variety of prediction models, the proposed model has a greater improvement in performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chai, T.: Operational optimization and feedback control for complex industrial processes. Acta Autom. Sin. 39(11), 1744–1757 (2013)
Murthy, T.P.K., Manohar, B.: Microwave drying of mango ginger (Curcuma amada Roxb): prediction of drying kinetics by mathematical modeling and artificial neural network. Int. J. Food Sci. Technol. 47(6), 1229–1236 (2012)
Balbay, A., Avci, E., Sahin, O., et al.: Modeling of drying process of bittim nuts (pistacia terebinthus) in a fixed bed dryer system by using extreme learning machine. Int. J. Food Eng. 8(4), 1–16 (2012)
Yu, H., Qin, S., Ding, G., et al.: Development of prediction model for machining precision of five-axis flank milling based on tool runout error. Comput. Integr. Manufact. Syst. 26(12): 3359–3367 (2020)
Yao, L., Ge, Z.: Deep learning of semisupervised process data with hierarchical extreme learning machine and soft sensor application. IEEE Trans. Industr. Electron. 65(2), 1490–1498 (2018)
Yan, W., Tang, D., Lin, Y.: A data-driven soft sensor modeling method based on deep learning and its application. IEEE Trans. Industr. Electron. 64(5), 4237–4245 (2016)
Graziani, S., **bilia, M.G.: Design of a soft sensor for an industrial plant with unknown delay by using deep learning. In: 2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), pp. 977–982 (2019)
Yuan, X.F., Li, L., Shardt, Y.A.W., et al.: Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development. IEEE Trans. Industr. Electron. 68(5), 4404–4414 (2021)
Mozaffari, M., Mahmoudi, A., Mollazade, K., et al.: Low-cost optical approach for noncontact predicting moisture content of apple slices during hot air drying. Drying Technol. 35(12), 1530–1542 (2017)
Liu, Z.L., et al.: Prediction of energy and exergy of mushroom slices. drying in hot air im**ement dryer by artificial neural network. Drying Technol. (Online) (2019)
Vieira, G.N.A., Olazar, M., Freire, J.T., et al.: Real-time monitoring of milk powder moisture content during drying in a spouted bed dryer using a hybrid neural soft sensor. Drying Technol. 37(9), 1184–1190 (2019)
Balbay, A., Kaya, Y., Sahin, O.: Drying of black cumin (Nigella sativa) in a microwave assisted drying system and modeling using extreme learning machine. Energy 44(1), 352–357 (2012)
Li, J.S., **ong, Q.Y., Wang, K., et al.: A recurrent self-evolving fuzzy neural network predictive control for microwave drying process. Drying Technol. 34(12), 1434–1444 (2016)
Zhu, J.L., Ge, Z.Q., Song, Z.H., Gao, F.R.: Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data. Annu. Rev. Control 46, 107–133 (2018)
Administration, S.T.M.: Cigarette Making Process Specification. China Light Industry Press, Bei**g (2016)
Ma, L., Fan, S.H.: CURE-SMOTE algorithm and hybrid algorithm for feature selection and parameter optimization based on random forests. BMC Bioinf. 18, 1–18 (2017)
Martinez-Munoz, G., Suarez, A.: Out-of-bag estimation of the optimal sample size in bagging. Pattern Recognit. 43, 143–152 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yu, S., Bi, S., Ding, X., Zhang, G. (2022). Multichannel Convolutional Neural Network Based Soft Sensing Approach for Measuring Moisture Content in Tobacco Drying Process. In: Hung, J.C., Yen, N.Y., Chang, JW. (eds) Frontier Computing. FC 2021. Lecture Notes in Electrical Engineering, vol 827. Springer, Singapore. https://doi.org/10.1007/978-981-16-8052-6_14
Download citation
DOI: https://doi.org/10.1007/978-981-16-8052-6_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8051-9
Online ISBN: 978-981-16-8052-6
eBook Packages: EngineeringEngineering (R0)