ABSTRACT
Storage is the key part of grain logistics where aeration is very essential to keep the grain safe. Exploring the intelligent method in modeling of stored grain aeration is helpful to effectively predict the aeration process and solve the problem of on-line calculation. The BP neural network was used for modeling in this paper. Firstly, the mechanical model used to collect data for modeling was presented and the topology of the neural network was determined. The initial grain moisture, initial grain temperature, air inlet air velocity, inlet air temperature, inlet air relative humidity and aeration time were chosen as the input variables, and the temperature and moisture of grain, the intergranular air temperature and humidity were the output variables. Then the BP neural network was trained and tested using the collected data. The simulation results showed that the BP neural network model could accurately predict the temperature and moisture content of grain during aeration, and provided an intelligent solution for stored grain aeration modeling.
- Zhang Xiaojing. Ventilation model of stored grai n pile and numerical simulation of grain temperature and moisture change during ventilation. Shandong Jianzhu University, 2017. CNKI: CDMD:2.1017.161863Google Scholar
- Gao Shuai, Wang Yuancheng, Qiu Huayu, Yang Jun. Numerical simulation of anisotropic resistance of wheat mechanical ventilation. Chinese Journal of cereals and oils, 2017,32 (02): 116-119+129. Doi. 10.3969/j.issn.1003-0174.2017.02.020Google Scholar
- Shubham Subrot Panigrahi, Chandra B. Singh, John Fielke. CFD modelling of physical velocity and anisotropic resistance components in a peaked stored grain with aeration ducting systems. Computers and Electronics in Agriculture,2020,179. Doi. 10.1016/j.compag.2020.105820Google Scholar
- Wang Ke, Wang Yuancheng, Yu Xiaojing, Yu Hai. Numerical simulation study on transverse cooling and water retaining ventilation of grain storage bin under different ventilation temperatures. Grain, oil and food science and technology, 2021,29 (03): 198-207. Doi. 10.16210/j.cnki.1007-7561.2021.03.027Google Scholar
- Zhang Yan, Guo Lei, Liu Jie. Application of inner circulation uniform temperature grain storage technology in summer storage of rice silos. Grain processing, 2021,46 (05): 76-79.Google Scholar
- Shen Bing. Research on prediction model of grain storage safety based on BP neural network. Traffic information and safety, 2013,31 (06): 140-143. Doi. 10.3963/j.issn.1674-4861.2013.06.027Google Scholar
- Sun Biaorui, Lian Feiyu, Wang Ke, Su Tingyi, Zhang Yuan. Research on intelligent decision-making of grain storage ventilation based on radial basis function neural network. Grain and feed industry, 2014 (09): 12-15. Doi. 10.7633/j.issn.1003-6202.2014.09.004Google Scholar
- Gao Song, Song Hui. Research on temperature field prediction of large bungalow warehouse based on BP neural network method. Grain, oil and food science and technology, 2015,23 (01): 94-97. DOI. 10.16210/j.cnki. 1007-7561.2015.01.024. Doi: 10.3969/j.issn.1007-7561.2015.01.023Google Scholar
- Ouyang Hui, Liu Jingyun, Wu Xu, Jiao Hua. Prediction model of drying and ventilation duration of stored grain warehouse based on BP neural network. Grain storage, 2016,45 (01): 21-25. Doi. 10.3969/j.issn.1000-6958.2016.01.005Google Scholar
- Lan Xueping, Chen Jinying, Jiang Youjun, Zou Xiao, Chen Meng. Construction of grain storage quality prediction model based on BP neural network algorithm. Chinese Journal of cereals and oils, 2020,35 (11): 147-151. Doi: 10.3969/j.issn.1003-0174.2020.11.024Google Scholar
- A. Iguaz, C. Arroqui, A. Esnoz, Modeling and simulation of heat transfer in stored rough rice with aeration, Biosystems Engineering, 2004, 89 (1): 69-77. Doi. 10.1016/j.biosystemseng.2004.03.013Google ScholarCross Ref
- T. L. Thompson, R. M. Peart. Mathematical simulation of corn drying - a new model. Transactions of the ASAE, 1968, 11(4): 582-586. Doi. 10.13031/2013.39473Google ScholarCross Ref
- Modeling of stored grain aeration based on BP neural network
Recommendations
Airflow simulation and inlet pressure profile optimization of a grain storage bin aeration system
Highlights- Observational data of a storage bin were obtained.
- A mathematical model of the ...
AbstractThe quality and conservation of grains depends directly on the storage system. Storage problems and inefficiency can lead to significant losses of the stored product, and high expenditure in energy and resources. To minimize these ...
Model of Online Grain Moisture Test System Based on Improved BP Neural Network
ICICTA '09: Proceedings of the 2009 Second International Conference on Intelligent Computation Technology and Automation - Volume 01This paper introduces the multiple sensing mechanism of online moisture test for grain and improved BP neural network. Using BP neural network to construct multi-input single-output model, applying gradient descent method with forgetting factor for ...
Modeling of liquid desiccant cooling and dehumidification system based on artificial neural network
IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics SocietyLiquid desiccant dehumidification system (LDDS) has emerged as an energy-efficient approach for air dehumidification. In this paper, a simple model for the liquid desiccant cooling and dehumidification air conditioning (LDCDAC) system is proposed. The ...
Comments