Abstract
The temperature of grain while in storage in a silo is an important indicator used to determine food security. Therefore, monitoring and reasonable prediction of grain temperature can safeguard grain to a great extent. For the characteristics of grain pile temperature with nonlinear sequence, this paper adopts a hybrid neural network algorithm based on Convolutional Neural Network (CNN) and Gated Recurrent Unit Network (GRU) for grain pile temperature prediction model, which extracts the vector features of input data by CNN model, then learns the input features by GRU model, and finally predicts the grain pile temperature. In this paper, we build a model based on the existing grain bin data, train and test the model, and set up experimental comparisons. The experimental results show that the RMSE of the model is 0.049 and the mean absolute error MAE is 0.036. The temperature prediction is more accurate and has less error than other methods.
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
Tian, W., Chen, L.: Some thoughts about grain storage safety. Mod. Food (15), 65–68 (2015)
Hsieh, S.: Tourism demand forecasting based on an LSTM network and its variants. Algorithms 14(8), 243 (2021)
Tan, X., Zhang, X.: GRU deep neural network based short-term railway freight demand forecasting. J. China Railw. Soc. 42(12), 28–35 (2020)
Jian, F., Jayas, D.S., White, N.D.G., Alagusundaram, K.: A three-dimensional, asymmetric, and transient model to predict grain temperatures in grain storage bins. Trans. ASAE 48(1), 263–271 (2005)
Wang, Z., Zhang, X., Chen, X.: Study on temperature field of grain heap under non-manual intervention. J. Huaiyin Inst. Technol. 30(1), 60–64 (2021)
Duan, S., Yang, W., Xiao, L., Zhang, Y.: A method for predicting surface temperature of storage grain depot based on meteorological data. J. Chin. Cereals Oils Assoc. 35(2),152–158 (2020)
Han, J., Nan, S., Li, J., Guo, C.: Research on prediction and control of mechanical ventilation temperature of grain pile based on random forest algorithm. J. Henan Univ. Technol. (Nat. Sci. Ed.) 40(5), 108–114 (2019)
Guo, L., Lian, F.: Temperature prediction of granary based on SOM clustering algorithm and grey improved neural network. Cereals Oils 32(11), 97–100 (2019)
Shi, R.: Application of BP neural network in forecasting average temperature of granary. Softw. Guide 14(08), 42–44 (2015)
Chen, L., Pei, X., Liu, Y.: Prediction of greenhouse environment variables based on LSTM. J. Shenyang Ligong Univ. 37(05), 13–19 (2018)
Yan, Z., Dong, Z.J., Shuang, R.S.: Research on grain pile temperature prediction based on deep learning algorithm. Grain Sci. Econ. 44(11), 52–56 (2019)
Zheng, Y., Li, G., Li, Y.: Survey of application of deep learning in image recognition. Comput. Eng. Appl. 55(12), 20–36 (2019)
Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: International Conference on Acoustics Speech & Signal Processing, Picasso, pp. 6645–6649 (2013)
Hochester, S., Schmid Huber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Bengio, Y.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)
Ge, F., Lei, J.: Research on short-term power load forecasting based on CNN-GRU SA model. Mod. Inf. Technol. 5(07), 150–154 (2021). https://doi.org/10.19850/j.cnki.2096-4706.2021.07.039
Dang, J., Cong, X.: Research on hybrid stock index prediction model based on CNN and GRU. Comput. Eng. Appl. 57(16), 167–174 (2021)
Zhou, F., Jin, L., Dong, J.: Review of convolutional neural network research. Chin. J. Comput. 40(06), 1229–1251 (2017)
Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8(1), 6085 (2018)
Gao, S., et al.: Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation. J. Hydrol. 589, 125188 (2020)
Elmaz, F., Eyckerman, R., Casteels, W., Latré, S., Hellinckx, P.: CNN-LSTM architecture for predictive indoor temperature modeling. Build. Environ. 206, 108327 (2021)
Cao, X.H., Stojkovic, I., Obradovic, Z.: A robust data scaling algorithm to improve classification accuracies in biomedical data. BMC Bioinform. 17, 359 (2016)
Acknowledgment
Hubei Provincial Outstanding Young and middle-aged Science and Technology Innovation Team project: Research on multi-source perception and intelligent detection technology of grain quality information. Project Number: T2021009.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, W., Liu, S., Wang, Y., Li, G., Yu, L. (2022). Research on Grain Pile Temperature Prediction Based on CNN-GRU Neural Network. In: Hu, Z., Gavriushin, S., Petoukhov, S., He, M. (eds) Advances in Intelligent Systems, Computer Science and Digital Economics III. CSDEIS 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 121. Springer, Cham. https://doi.org/10.1007/978-3-030-97057-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-97057-4_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97056-7
Online ISBN: 978-3-030-97057-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)