In practical industrial-scale paddy drying production, manual empirical operation is still widely used for process control. This often leads to poor uniformity in the moisture content distribution of discharged grains, affecting product quality. Model Predictive Control (MPC) is considered the most effective control method for paddy drying, but its implementation in industrial-scale drying is hindered by its high computational cost. This study aims to address this challenge by proposing a deep-learning-based model predictive control (DL-MPC) strategy for paddy drying. By establishing a mapping relation between the inlet and outlet paddy moisture content and paddy flow velocity, a DL-MPC strategy suitable for multistage counter-flow paddy drying systems is proposed. DL-MPC systems are developed using long short-term memory (LSTM) neural networks and trained using datasets from single-drying-stage and multistage drying systems. Simulation and analysis are conducted, followed by verification experiments on a 5HNH-15 multistage counter-flow paddy dryer. The results show that the DL-MPC system significantly improves computational speed while achieving satisfactory control performance. The predicted paddy flow velocity exhibits a smooth variation and matches field data obtained from multiple transition points, confirming the effectiveness of the designed DL-MPC system. The mean absolute error between the predicted and actual paddy moisture content under the DL-MPC system is 0.190% d.b., further supporting the effectiveness of the control system.

The improvement of the design and operation of energy conversion systems is a theme of global concern. As an energy intensive operation, industrial agricultural product drying has also attracted significant attention in recent years. Taking a novel industrial corn drying system with drying capacity of 5.5 t/h as a study case, based on existing exergoeconomic and exergetic analysis methodology, the present work investigated the exergetic and economic performance of the drying system and identified its energy use deficiencies. The results showed that the average drying rate for corn drying in the system is 1.98 g_water/g_{dry matter} h. The average exergy rate for dehydrating the moisture from the corn kernel is 345.22 kW and the exergy efficiency of the drying chamber ranges from 14.81% to 40.10%. The average cost of producing 1 GJ exergy for removing water from wet corn kernels is USD 25.971, while the average cost of removing 1 kg water is USD 0.159. These results might help to further understand the drying process from the exergoeconomic perspective and aid formulation of a scientific index for agricultural product industrial drying. Additionally, the results also indicated that, from an energy perspective, the combustion chamber should be firstly optimized, while the drying chamber should be given priority from the exergoeconomics perspective. The main results would be helpful for further optimizing the drying process from both energetic and economic perspectives and provide new thinking about agricultural product industrial drying from the perspective of exergoeconomics.

The online measurement of moisture content for grains is an essential technology to realize real-time tracking and control, improve drying quality and reduce energy consumption of the drying process. To improve the measurement accuracy and reliability of the dynamic measurement process as well as expand the application scope of the device, the present work constructed an experimental equipment for determining dynamic resistance characteristics of a single grain. The relations between moisture content and real-time resistance waveform were revealed, and an analytical calculation method of peak value and peak area of waveform was proposed, which correctly revealed the electrical measurement properties of grain. The results demonstrated that the gap width between the electrodes had large influence on the sensor’s performance. Moreover, an online measuring device was developed based on the experimental analysis and calculation method, and the test results in both lab and field for different grains showed that online real-time absolute measurement error are within ±0.5% in the varied moisture content (10–35%w.b.) and the temperature (−20–50 °C). The main results and the developed device might provide technical support for developing intelligent grain drying equipment.

The present work proposes a novel industrial multi-field synergistic dryer with a drying capacity of 3.45 t/h. The energy, exergy, and quality aspects of the drying process were studied. An energy–exergy methodology was employed to estimate the energetic and exergetic performance, heat loss characteristics and heat recovery behavior of the dryer. Additionally, the quality of the dried paddy seeds was evaluated by its crackle ratio, generation potential, and generation rate. The results showed that the overall energy and exergy efficiency ranged from 13.26% to 56.63% and 39.03% to 60.23%, respectively. The improvement potential rates of the whole system varied from the lowest 8.49 kW to the highest 15.83 kW and respectively accounted for 15.81–29.48% of the total exergy input, indicating that the performance of the dryer is acceptable. The total recovered radiant energy and radiant exergy recover rate were respectively ascertained to be 237.64 MJ and 0.26 kW. As for the quality aspect, the generation potential and generation rate of the dried paddy seeds respectively ranged from 75% to 90% and 69% to 88% while the crackle ratio of the paddy seeds was 1%, which indicated that the quality performance of the dried seed is of economic viability.

Energy consumption performance evaluation of an industrial grain dryer is an essential step to check its current status and to put forward suggestions for more effective operation. The present work proposed a combined IRCC dryer with drying capacity of 4.2 t/h that uses a novel drying technology. Moreover, the existing energy–exergy methodology was applied to evaluate the performance of the dryer on the basis of energy efficiency, heat loss characteristics, energy recovery, exergy flow and exegetic efficiency. The results demonstrated that the average drying rate of the present drying system was 1.1 g_water/g_{wet matter} h. The energy efficiency of the whole drying system varied from 2.16% to 35.21% during the drying process. The overall recovered radiant energy and the average radiant exergy rate were 674,339.3 kJ and 3.54 kW, respectively. However, the average heat-loss rate of 3145.26 MJ/h indicated that measures should be put in place to improve its performance. Concerning the exergy aspect, the average exergy rate for dehydration was 462 kW and the exergy efficiency of the whole drying system ranged from 5.16% to 38.21%. Additionally, the exergy analysis of the components indicated that the combustion chamber should be primarily optimized among the whole drying system. The main conclusions of the present work may provide theoretical basis for the optimum design of the industrial drying process from the viewpoint of energetics.

Uncontrollable ambient conditions are the main factors limiting the self-adaption control of an industrial drying system. To achieve the goal of accurate control of the drying process, the influence of the ambient conditions on the drying behavior should be taken into consideration when modeling the drying process. Present work introduced an industrial drying system with a loading capacity of 50 t, two artificial neural network prediction models with (IANN) and without (OANN) considering the ambient conditions were established using artificial neural network modeling approach. The ambient conditions on the moisture content (MC), exergy efficiency of the heat exchanger (η_ex,h) and specific recovered radiant energy (Er) of the drying process were also investigated. The results showed that the η_ex,h and Er increase with the increase of ambient temperature while the drying time decrease with the increase of the ambient temperature. The IANN model has a better prediction performance that that of OANN model. An optimal architecture of 9-2-12-3 artificial neuron network model was developed and the best prediction performance of the artificial neural network (ANN) model were found at a training epoch number of 30, and a momentum coefficient of 0.4, where the coefficient of determination of moisture content, exergy efficiency of heat exchanger, and the specific recovered radiant energy, respectively are 0.998, 0.992, and 0.980, indicating that the model has an excellent prediction performance and can be used in engineering practice.