Research on CNN-LSTM-Attention based surface temperature prediction model for fermented grains

Ao Zhang; Xianguo Tuo; Rui Yao

doi:10.54097/g3if9kzs

Authors

Ao Zhang
Xianguo Tuo
Rui Yao

DOI:

https://doi.org/10.54097/g3if9kzs

Keywords:

Baijiu brewing process, Prediction of fermentation grains temperature, Attention mechanism, CNN, LSTM architecture

Abstract

The prediction of the temperature on the surface of the fermented grains during the steaming process holds significant importance in improving the alcohol yield and quality. To accurately forecast the temperature variations on the surface of the fermented grains, a predictive model based on CNN-LSTM-Attention is proposed. Leveraging convolutional neural networks, latent features of the temperature data on the fermented grains surface are extracted. These extracted feature vectors, representing a time series, are then inputted into a long short-term memory network to further capture the temporal characteristics of the sequence. Finally, employing an attention mechanism, the influential features are highlighted to achieve precise prediction of the fermented grains surface temperature. Historical temperature data from the steaming process of the fermented grains is utilized, and experimental comparisons are conducted with other neural network prediction models. The results demonstrate that the CNN-LSTM-Attention model achieves optimal root mean square error of 1.282 and average absolute error of 0.647, surpassing other models. The experimental findings substantiate the superior accuracy of the CNN-LSTM-Attention model in forecasting the changing trend of the fermented grains surface temperature.

References

Yang Bo, The innovation of traditional solid-state fermentation technology in China: the example of traditional solid-state brewing of Fenjiu. Brewing Science and Technology, 2021(07): pp. 106-109.

Yang, et al. Study on the effect of retort barrel height and structural design on distillation efficiency and quality of spirits. Brewery Technology, 2012(10): pp. 94-98.

Liu, W.B. et al, Progress in the application of upper retort robot in white wine brewing. Journal of Sichuan Light Chemical University (Natural Science Edition), 2023. 36(01): pp. 24-32.

Li D. & Li G. H., Relationship between top retort distillation technology and quality of liquor production. Brewery Technology, 2012(01): pp. 65-66+69.

Wei, Jingjun et al. Study on the effect of "eight moves of Yijiu on retort" on distillation effect and quality of white wine. Brewing, 2014. 41(06): pp. 50-52.

Qing Yihui et al. Kinematic analysis and trajectory study of the upper retort robot. Food and Machinery, 2020. 36(12): pp. 70-73.

Li L. et al. Study on the application of wine spirits on retort robot in the brewing production of soy sauce type white wine. Modern Food, 2023. 29(02): pp. 127-129.

Li Yao et al. Structural analysis of wine spirits on retort robot and its application in the production of clear spiced white wine brewing. Brewing Science and Technology, 2021(12): pp. 95-99+107.

Najwa, M.R.N., et al., Comparison between Regression Models, Support Vector Machine (SVM), and Artificial Neural Network (ANN) in River Water Quality Prediction. Processes, 2022. 10(8).

Abreu, L.R., et al., A decision tree model for the prediction of the stay time of ships in Brazilian ports. Engineering Applications of Artificial Intelligence, 2023. 117(PB).

Yu, X. T. & Liu, P., Long-term and short-term memory network-convolutional neural network (LSTM-CNN) based PM_(2.5) concentration prediction in Beijing. Environmental Engineering, 2020. 38(06): pp. 176-180+66.

X., W. and L. W., Time Series Prediction Based on LSTM-Attention-LSTM Model. IEEE Access, 2023. 11: p. 48322-48331.

Hao, Shilin, Research on LSTM-based temperature prediction model for upper retort wine spirits, 2020, Hubei University of Technology. Page 63.

Zhang, J. & Zhang, Z. P., Research on the improved GRU-based prediction model for liquor steam operation. Journal of Hubei University of Technology, 2022. 37(04): pp. 43-48+61.

Chen, J., Y. Li and S. Zhang, Fast Prediction of Urban Flooding Water Depth Based on CNN−LSTM. Water, 2023. 15(7): p. 1397.

Yan, R., et al., Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering. Expert Systems with Applications, 2021. 169(prepublish).

Sepp Hochreiter, jürgen Schmidhuber, Long Short-Term Memory.Neural Comput 1997; 9(8):1735-1780.

Jia, X., et al., Prediction of Sea Surface Temperature in the East China Sea Based on LSTM Neural Network. Remote Sensing, 2022. 14(14).

Tianjun, X., et al. The application of two-level attention models in deep convolutional neural network for fine-grained image classification. in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015.