New Sensing Technologies for Grain Moisture

Flor, Omar; Palacios, Héctor Abel; Carreño, Franyelit María Suárez; Salazar, Katherine; Reyes, Luis; González, Mario; Jiménez, Karina

doi:10.3390/agriculture12030386

Cited by 11 publications

(6 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 26 ], the authors summarize sensing methods for grain moisture measurement, including the methods and techniques developed over the last 15 years, based, e.g., on radio frequency, hydrogen nuclear magnetic resonance and visible spectrum analysis. NIR (Near-InfraRed) has been used for many years for the measurement of leaf water content [ 27 ].…”

Section: Related Workmentioning

confidence: 99%

Moisture Determination for Fine-Sized Copper Ore by Computer Vision and Thermovision Methods

Buchczik

Budzan

Krauze

et al. 2023

Sensors

View full text Add to dashboard Cite

The moisture of bulk material has a significant impact on the energetic efficiency of dry grinding, resultant particle size distribution and particle shape, and conditions of powder transport. This research aims to develop computer vision and thermovision techniques for the on-site estimation of moisture content in copper ore, for use, e.g., in dry grinding installations. The influence of particle size on the results of moisture estimation is also studied. The tested granular material was copper ore of particle size 0–2 mm and relative moisture content of 0.5–11%. Both vision and thermovision images were taken at standard and macro scales. The results suggest that median-intensity vision images monotonically reflect copper ore moisture in the range of about 0.5–5%. Suitable models were identified and cross-validated here. In contrary, thermograms should not be analyzed simply for their mean temperature but treated with computer vision processing algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Moisture Determination for Fine-Sized Copper Ore by Computer Vision and Thermovision Methods

Buchczik

Budzan

Krauze

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The three main approaches for automatic control of paddy drying are feedback control, computer simulation control, and model predictive control (MPC). Feedback control, represented by proportional, integral, and derivative (PID) tuning, adjusts the drying process in real-time based on the detected grain moisture to reduce deviations [ 7 , 8 ], but it may not align well with the independent events of the inlet grain, drying conditions, and outlet grain in paddy drying. Computer simulation control involves modeling and solving nonlinear processes using artificial intelligence (AI) algorithms [ 9 , 10 ], but obtaining effective coefficients is difficult due to the randomness in field drying.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Model Predictive Control of an Industrial-Scale Multistate Counter-Flow Paddy Drying Process

Zhang,

Fang,

et al. 2023

Foods

View full text Add to dashboard Cite

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.

show abstract

“…The most widely used online detection methods are the capacitance method and resistance method. The resistance method generally requires the sample to be ground before detection and is a type of lossy detection [ 15 , 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

Design and Experiment of Capacitive Rice Online Moisture Detection Device

Sun

Wan

Che

et al. 2023

Sensors

View full text Add to dashboard Cite

To solve the problems of poor stability and low monitoring precision in the online detection of rice moisture in the drying tower, we designed an online detection device for rice moisture at the outlet of the drying tower. The structure of a tri-plate capacitor was adopted, and the electrostatic field of the tri-plate capacitor was simulated using COMSOL software. A central composite design of three factors and five levels was carried out with the thickness, spacing, and area of the plates as the influencing factors and the capacitance-specific sensitivity as the test index. This device was composed of a dynamic acquisition device and a detection system. The dynamic sampling device was found to achieve dynamic continuous sampling and static intermittent measurements of rice using a ten-shaped leaf plate structure. The hardware circuit of the inspection system with STM32F407ZGT6 as the main control chip was designed to realize stable communication between the master and slave computers. Additionally, an optimized BP neural network prediction model based on the genetic algorithm was established using the MATLAB software. Indoor static and dynamic verification tests were also carried out. The results showed that the optimal plate structure parameter combination includes a plate thickness of 1 mm, plate spacing of 100 mm, and relative area of 18,000.069 mm2 while satisfying the mechanical design and practical application needs of the device. The structure of the BP neural network was 2-90-1, the length of individual code in the genetic algorithm was 361, and the prediction model was trained 765 times to obtain a minimum MSE value of 1.9683 × 10−5, which was lower than that of the unoptimized BP neural network with an MSE of 7.1215 × 10−4. The mean relative error of the device was 1.44% under the static test and 2.103% under the dynamic test, which met the accuracy requirements for the design of the device.

show abstract

New Sensing Technologies for Grain Moisture

Cited by 11 publications

References 53 publications

Moisture Determination for Fine-Sized Copper Ore by Computer Vision and Thermovision Methods

Moisture Determination for Fine-Sized Copper Ore by Computer Vision and Thermovision Methods

Deep-Learning-Based Model Predictive Control of an Industrial-Scale Multistate Counter-Flow Paddy Drying Process

Design and Experiment of Capacitive Rice Online Moisture Detection Device

Contact Info

Product

Resources

About