Food security is an influential factor for the development and future of humanity. Stored grain temperature is a key physical variable for grain quality control and management in stored-grain ecosystem. In this study, a prediction model using Fourier series based on least-squares method is introduced to describe the average temperature movement of grain pile and the daily air temperature, naming hysteresis cycle model (HCM). Then the HCM based on the Fourier analysis is proposed that incorporating with the least-squares method, the Fourier series model is applied to forecast the grain pile temperature from the daily air temperature. The HCM is built by finding relationship called conversion coefficients between the air and grain pile temperature that is constructed on the basis of Fourier analysis, and the optimal order of the model is determined by Akaike information criteria. Our method can reflect the time lag of the grain pile temperature changes with the change of air temperature and requires only a single variable (i.e. air temperature). Experiments including model fitting, temperature prediction, and results comparison for a period of 425 days from a real-world granary, yield satisfied results agreeing well with actual observation values. As a result of model validation, the proposed method has the root mean square error (RMSE) values ranging from 1.6°C to 2.3°C with average RMSE of 1.9°C. In other words, the proposed model can predict grain pile temperature with a high accuracy once an acceptable relationship between air temperature and grain pile temperature has been constructed from previously temperature data. Result analysis indicates effectiveness and workability of the proposed model for stored grain temperature prediction.

Grain quality changes during the storage period, and an important grain quality indictor is the free fatty acid (FFA) content. Understanding real-time change of FFA content in stored grain is significant for grain storage safety. However, the FFA content requires manual detection with time-consuming and complex procedures. Thus, this paper is dedicated to developing a method to estimate FFA content in stored grain accurately. We proposed a machine learning approach—multiple-kernel support vector regression—to complete this goal, which improved the accuracy and robustness of the FFA estimation. The effectiveness of the proposed approach was validated by the grain storage data collected from northeast China. To show the merits of the proposed method, several prevailing prediction methods, such as single-kernel support vector regression, multiple linear regression, and back propagation neural network, were introduced for comparative purposes, and several quantitative statistical indexes were adopted to evaluate the performance of different models. The results showed that the proposed approach can achieve a high accuracy with mean absolute error of 0.341 mg KOH/100 g, root mean square error of 0.442 mg KOH/100 g, and mean absolute percentage error of 2.026%. Among the four models tested, the multiple-kernel support vector regression model performed best and made the most robust forecasts of FFA content in stored grain.