Research on Deep Learning-Based Intelligent Prediction Models for Quality Deterioration in Grain and Oil Storage

Siyi Li

doi:10.71222/jwetf723

Authors

Siyi Li Food Science and Engineering, Tianjin Agricultural University, Tianjin, 300384, China Author

DOI:

https://doi.org/10.71222/jwetf723

Keywords:

deep learning, grain and oil storage, quality deterioration, intelligent prediction, model

Abstract

Stored grain and oil quality are linked to a nation's food security and economic benefits. Traditional grain and oil monitoring methods are mostly performed by practitioners using their experience which can lead to poor timeliness and accuracy of information. Therefore, the purpose of this research is to use deep learning technology to build an intelligent predictive model which helps to overcome the issue of maintaining stored grain and oil quality in complicated storage conditions. The model uses multiple types of monitoring data such as temperature, humidity, and pictures to create an advanced quality deterioration early warning system that can support many different practical storage scenarios. Findings from this research indicate that the model can successfully analyze the complex nonlinear relationships among many of the critical components that affect quality. The findings provide a new technical approach for the intelligent and proactive management of grain oil storage quality.

References

1. Y. Zhao, X. Ran, T. Yin, H. Guo, X. Zhang, Y. Shen, and S. Tang, "Nitrogen alleviated the deterioration of rice quality by affecting the accumulation of grain storage protein under elevated temperature," Journal of Plant Growth Regulation, vol. 42, no. 6, pp. 3388-3404, 2023. doi: 10.1007/s00344-022-10798-9

2. S. Das, V. K. Singh, A. K. Chaudhari, A. K. Dwivedy, and N. K. Dubey, "Efficacy of Cinnamomum camphora essential oil loaded chitosan nanoemulsion coating against fungal association, aflatoxin B1 contamination and storage quality deterioration of Citrus aurantifolia fruits," International Journal of Food Science & Technology, vol. 57, no. 12, pp. 7486-7495, 2022.

3. Y. F. Markov, A. N. Buriak, and L. G. Eresko, "Equipment and scientific studies of experimental data on storage of wheat grain," Food systems, vol. 2, no. 4, pp. 25-30, 2019. doi: 10.21323/2618-9771-2019-2-4-25-30

4. N. Gómez-Calderón, K. Villagra-Mendoza, I. Guzmán-Arias, M. Solórzano-Quintana, A. E. Chavarría-Vidal, and A. Soto-Grant, "Process for Improvement and Evaluation of the Agricultural Engineering Curriculum at the Instituto Tecnologico de Costa Rica," In Agricultural, Biosystems, and Biological Engineering Education, 2024, pp. 176-192.

5. B. Bennett, C. Jiang, and S. R. Larter, "Deterioration of oil quality during sample storage: are stored reservoir core samples a viable resource for oil viscosity determination?," Fuel, vol. 245, pp. 115-121, 2019. doi: 10.1016/j.fuel.2019.02.002