Grain drying is a complex heat and mass transfer process, which has the characteristics of a significant delay, multidisturbance, nonlinearity, strong coupling, and parameter uncertainty. Artificial intelligence (AI) control technology is suitable for solving such complex control problems. In this paper, the mechanism and data dual-drive with equivalent accumulated temperature (EAT) mutual-window AI-control method for continuous grain drying were proposed, and a control system was established. The experimental verification was carried out on the test platform of continuous grain drying. The results show that the method has the ability of implicit prediction, high accuracy, strong stability and self-adaptive ability, and the maximum control deviation of moisture at the outlet of the dryer is −0.58–0.3%.

In our study, we developed a system to reduce both energy consumption and pollutant discharge during the drying process. We present a new technology, a stationary bed grain-drying test device based on the internal circulation of the drying medium (ICODM). A rice-drying experiment was carried out inside of it, and the influences of air temperature (AT) and air velocity (AV) on the energy and exergy efficiencies (EEE) as well as the improvement potential rate (IPR) and the sustainability index (SI) of the rice-drying process were studied. The following conclusions were obtained: when the rice was dried at a temperature of below 55 °C and an AV across the grain layer of 0.5 m/s, the average EEE during the drying process was 48.27–72.17% and 40.27–71.07%, respectively, demonstrating an increasing trend as the drying medium temperature increased. When the rice was dried using an AV across the grain layer in the range of 0.33–0.5 m/s and a temperature of 40 °C, the two values were 39.79–73.9% and 49.66–71.04%, respectively, demonstrating a decreasing trend as the drying medium flow velocity increased. IPR and SI were 4.1–8.5 J/s and 1.9–2.7, respectively, at a drying temperature of 30–55 °C and an AV of 0.33–0.5 m/s. These conclusions can provide helpful guidance for the optimization and control of the rice-drying process in terms of saving energy.

Grain moisture is one of the key indexes of grain quality, and acquiring an accurate moisture value is critical for grain storage security. However, the sensors used in the traditional methods for testing grain moisture are based on capacitance, microwave, or radio-frequency methods and still exhibit low accuracy and instability because they are susceptible to the temperature, moisture, and micro gas flow of the air in the granary. In this study, we employed a new design for a radio-frequency moisture sensor for grain. The structure of the sensor is based on the difference method and consists of two parallel probe units. These units are at different distances to the tested grain, resulting in different sensitivities in the moisture measurements. Through a phase difference operation on the test signals, the disturbance variable was reduced. The specific size of the two parallel probes was confirmed by calculation and simulation using High Frequency Structure Simulator (HFSS) software. The simulated and measured parameters of a prototype sensor agreed well. The linear relationship yielded a correlation coefficient of 0.9904, and the average error of the moisture testing was within ±0.3% under the conditions where the VSWR (voltage standing wave ratio) value and return losses were 1.5896 and −20 dB, respectively, at a measured central frequency of 100 MHz. The results indicate that the performance of the sensor was excellent.

In large granaries, maize storage period could last 3–5 years in China. Free fatty acids (FFA) content is commonly used as a sensitivity indicator of grain quality changes during storage. Samples of the stored grain are taken manually and tested in the laboratory monthly for regular quality monitoring. Although substantial labor and time are consumed, the testing way lacks of real-time. Temperature is a main factor influencing the quality of stored grain. In this study, it was analyzed that the effective accumulated temperature (EAT) had a strong correlation coefficient with FFA. Classification and regression trees (CART) and model trees (ML) in machine learning (ML) methods were used to estimate FFA by EAT based on data collected from 11 large granaries in northeastern China. While the minimum number of samples for segmentation was set as 20, the two models both had the optimal performance. The two models were evaluated by mean absolute error (MAE), root mean square error (RMSE) and the coefficient of determination (R²). The MAE, RMSE and R² of CART and MT are 1.296, 1.761, 0.759; 1.247, 1.821, and 0.741, respectively. As CART had the lower RMSE and the larger R², the model performance of CART was better. The model provided a method to estimate the changes of FFA based on the exist temperature monitoring system in large granaries as a way of stored maize quality real-time monitoring.

The scientific rationality of farmers’ grain storage technology and equipment is crucial for the biosecurity of grain in the main grain-producing areas represented by Northeast China. In this paper, four farmer grain storage mock silos of different widths were used as a means to track an experimental cycle of grain storage. The absolute water potential of corn in all four silos at the beginning of the experiment was greater than the absolute water potential of air, prompting moisture migration from the grain interior to the air and down to about 14%. Moisture was influenced by wind direction, and moisture decreased faster with better ventilation on both sides of the grain silos. Therefore, grain silo width has a significant effect on the drying effect under naturally ventilated conditions of maize ears. This research focused on the determination and assessment of mycotoxin contamination under farmers’ storage grain conditions and analyzed the effect of silo structure on the distribution of mycotoxin contamination. When the width was too large, areas of high mycotoxin infection existed in the middle of the grain silo, and ventilation and tipping could be used to reduce the risk of toxin production. This study proved that reasonable farmer grain storage techniques and devices in Northeast China can effectively protect grain from mycotoxin contamination.

Conventional grain monitoring systems often rely on isolated data points (e.g., point-based temperature measurements), limiting holistic condition assessment. This study proposes a novel Mechanism and Data Driven (MDD) framework that integrates physical mechanisms with real-time sensor data. The framework quantitatively analyzes solar radiation and external air temperature effects on silo boundaries and introduces a novel interpolation-optimized model parameter initialization technique to enable comprehensive grain condition perception. Rigorous multidimensional validation confirms the method’s accuracy: The novel initialization technique achieved high precision, demonstrating only 1.89% error in Day-2 low-temperature zone predictions (27.02 m² measured vs. 26.52 m² simulated). Temperature fields were accurately reconstructed (≤0.5 °C deviation in YOZ planes), capturing spatiotemporal dynamics with ≤0.45 m² maximum low-temperature zone deviation. Cloud map comparisons showed superior simulation fidelity (SSIM > 0.97). Further analysis revealed a 22.97% reduction in total low-temperature zone area (XOZ plane), with Zone 1 (near south exterior wall) declining 27.64%, Zone 2 (center) 25.30%, and Zone 3 20.35%. For dynamic evolution patterns, high-temperature zones exhibit low moisture (14%). A strong positive correlation between temperature and relative humidity fields; temperature homogenization drives humidity uniformity. The framework enables holistic monitoring, providing actionable insights for smart ventilation control, condensation risk warnings, and mold prevention. It establishes a robust foundation for intelligent grain storage management, ultimately reducing post-harvest losses.