Search

In order to solve the difficulties of sowing for foxtail millet and improve the low germination rate of millet after sowing in dry land of North China, we firstly studied the agricultural requirements of precision drill of millet without thinning out seedlings. We prepared a mixed suspension of foxtail millet using water and agricultural super absorbent polymers, because the agricultural super absorbent polymers can promote crop growth. We did some experiments to find suitable super absorbent polymers and the optimal proportion for mixed suspension according to the requirement of fluid seeding. At the same time we designed a kind of seed metering device by small-amount liquid for foxtail millet. This paper determined the number of rollers, dimension parameter and combination form of tube. It also expounded sucking seeds, delivering seeds and metering seeds of this seed metering device. This device consists of seed box, delivery pump, pump tube, three-way tube, long bent tube, end drainage tube and short bent tube. The function of delivery pump is providing power for the seed metering device, the function of three-way tube is dividing and combining the mixed suspension, the long bent tube or the short bent tube can improve the uniformity of seeding, and the end drainage tube can decrease every drop volume of mixed suspension to ensure that every drop has 2-3 seeds. Because the delivery pump has impulsive motion, we greatly reduced the impulsive motion of this device by using 6 rollers of .delivery pump and designing the structural style of tube, which has long bent tube, short bent tube, three-way tube and end drainage tube. The length of long bent tube is 100 mm, and the length of short bent tube is 74.4 mm. We also chose the material and diameter of tube. The material of tube is silica gel, which has the advantages of good elasticity and long service life. The diameter of pump tube, long bent tube, short bent tube and end drainage tube is 4.8, 4, 4 and 4 mm, respectively. Finally we designed and conducted the experiments of the uniformity and steadiness for mixed suspension of millet, and the variability coefficient of seed number was adopted. And we performed the performance tests with 4 indices adopted, including the percentage of damaged seeds, qualified rate of hill distance, qualified rate of seed number per hill, and rate of no seed hill for seed metering device in laboratory. We also carried out the field experiment of sowing with 3 indices including the qualified rate of hill distance, qualified rate of plant number per hill and seedling emergence rate for this device. The results showed that the suitable agricultural super absorbent polymer was Anxin for preparing the mixed suspension of foxtail millet, and the quality ratio of super absorbent polymers, grain of millet seed and water was 1.1 : 10 : 200 in mixed suspension; the variability coefficient of seed number was 9.8% in this mixed suspension, and was 9.7%-10.4% within 5 hours, and the seeds in mixed suspension had no obvious settlement. The percentage of damaged seeds was less than 0.01%, the qualified rate of hill distance was greater than 86%, the qualified rate of seed number per hill was greater than 75%, and the rate of no seed hill was less than 4% in laboratory test. The qualified rate of hill distance was greater than 77%, the qualified rate of plant number per hill was greater than 74%, and the seedling emergence rate was greater than 87% in field experiment of sowing. The results provide a theoretical reference for the design and analysis of seed metering device by small-amount liquid for small grain seeds. [ABSTRACT FROM AUTHOR]

Weeds have been one of the main factors to affect the growth of crops in the seedling stage. Timely weeding is a necessary measure to ensure crop yield. An intelligent field weeding equipment can also be a promising potential deployment in the unmanned farm system at the current stage of intelligent agriculture. Effective recognition of crops and weeds has been a high demand to promote the development of intelligent weeding equipment. Previous research was focused mainly on object detection and semantic segmentation using deep learning. A great challenge is still remained in the performance of target detection, in the case of overlap images between the crops and weeds under the complex field. The reason was that the different target areas cannot be further divided when the generated anchor box overlaps in a large area. The pixel level annotation can also be required to train the semantic segmentation, where the data samples cannot be easy to obtain. The weak real-time performance cannot be conducive to practical application. In this study, an improved model was proposed using shifted window Transformer (Swin Transformer) network, in order to enhance the accuracy and real-time performance of crop and weed recognition. The specific procedure was as follows. 1) A semantic segmentation model of corn was established for the real and complex field scene. The backbone of the model was the Swin Transformer architecture, which was denoted by Swin-Base. The full self-attention mechanism was also adopted to significantly enhance the modeling ability in the Swin Transformer using the shift window division configuration. Self-attention was then calculated locally in the non-overlapping window of the segmented image block, where the cross-window connection was allowed. The computational complexity of the backbone presented a linear relationship with the image size, thereby elevating the inference speed of the model. The hierarchical feature representation was constructed through the Swin Transformer for the dense prediction of the model at the pixel level. 2) The Unified perceptual parsing Network (UperNet) was used as an efficient semantic segmentation framework. Among them, the feature extractor was the Feature Pyramid Network (FPN) using the Swin Transformer backbone. The multi-level features obtained by Swin Transformer were used by the FPN to represent the corresponding pyramid level. An effective global prior feature expression was added in the Pyramid Pooling Module (PPM). Better performance of semantic segmentation was achieved using the fusion of the hierarchical semantic information. The Swing transformer backbone and UperNet framework were combined into one model through the Decoder-Encoder structure, denoted by Swin-Base-UN. 3) The structure of the Swin-Base backbone was improved to enhance the inference speed. The number of network parameters and calculation cost were reduced to decrease the number of hidden layer channels, headers, and Swin Transformer blocks. Therefore, four improved models were generated, including the Swin-Large-UN, Swin-Small-UN, Swin-Tiny-UN, and Swin-Nano-UN. The model size and computational complexity of improved models were about 2, 1/2, 1/4, and 1/8 times of Swin-Base-UN, respectively. 4) Taking the segmentation of corn morphological region as the case study, an improved image morphological processing combination was established to recognize and segment all the weed regions in real time. The segmentation of corn was also used to segment the weeds. The weed pixel annotation was removed from the training data of the model. As such, a large number of annotation data at the pixel level was obtained in the semantic segmentation of the improved model, compared with the original one. A comparison was made on the performance of all models in training, validation, and testing. Consequently, the Swin-Tiny-UN was determined as the best model to achieve the optimal balance between accuracy and speed. Specifically, the mean Intersection over Union (mIoU) and mean Pixel Accuracy (mPA) on the test set were 94.83% and 97.18%, respectively, which increased by 3.27 and 4.71 percentage points, respectively, compared with the RestNet-101-UN using traditional Convolutional Neural Networks (CNN) backbone. The inference speed of the model was achieved by 18.94 frames/s. The best model of semantic segmentation was superior to the traditional one, in terms of the region segmentation accuracy, pixel recognition accuracy, and inference speed. The image segmentation showed that the improved model can be expected to accurately recognize and segment maize and weeds in complex field scenes. The average correct detection rate of the improved model was 95.04% for the video stream data in the process of field work, whereas, the average detection time per frame was 5.51×10-2 s. Consequently, the improved model can be expected to detect the corn and weeds in the process of field work, indicating higher accuracy and real-time performance under practical application conditions. The findings can provide a strong reference for the development of intelligent weeding equipment. [ABSTRACT FROM AUTHOR]

Weed control is an inevitably necessary task in field management. Effective recognition of crops and weeds has therefore been an essential basis to promote the development of intelligent weeding equipment. Nevertheless, the recognition targets are not fixed in images except for crops, due mainly to the variety of weeds and random distribution of their positions. It is highly demanded for better recognition performance to detect the crops from all categories of weeds in the image. All weed targets are required to be labeled in the dataset, where there are comprehensive all-inclusive weed species. However, human vision can only identify the target crops from the weeds. The species and quantity of weeds are still lacking in the identification. Moreover, the crops and weeds are usually overlapped in the field images with complex scenes. It is also difficult to accurately segment the boundary of various objects, especially when the generated anchor box was superimposed by a large area in deep overlapping. In this study, a recognition and semantic segmentation of maize at the seeding stage was proposed to identify the weeds on the premise of maize recognition using a dual attention network. Fine segmentation of morphological boundary was obtained. The main contents were as follows. 1) The original architecture of the model was determined to compare 6 state-of-the-art semantic segmentation networks. It was found that the architecture of the dual attention network presented the best performance for the training, validation, and testing dataset, thereby realizing the pixel-wise recognition and segmentation of maize field images. In the validation set, the mean intersection over union (mIoU) and mean pixel accuracy (mPA) at the end of iteration were 92.73% and 96.88%, respectively. In the test set, the mIoU and mPA were 92.8% and 94.66%, respectively, and the speed of segmentation was 15.2 frames/s. 2) The semantic segmentation model of maize at the seeding stage was established using the improved network architecture. The function of the model was a binary classification of maize pixels and all of the other pixels, suitable for the recognition and morphological segmentation of maize in complex field scenes at the seeding stage. The improved backbone was used to enhance the feature representation. More details of features were retained, while the amount of computation was reduced. Recurrent criss-cross and channel attention modules were combined to compose a dual attention mechanism, in order to synchronously construct long-range contextual dependencies in spatial and channel dimensions of the feature map. The discriminability of feature representation was improved significantly. The encoder-decoder structure was used to build the model, and then the auxiliary head was attached to optimize the underlying features. The loss function was improved, while the transfer learning strategy was formulated. 3) The segmentation map of weeds was obtained via image morphological processing on the segmentation map of maize at the seeding stage. The regions of weed were identified by the segmentation of maize, particularly without considering the pixel-wise prediction of the weed region. The results showed that the performance of the model was better than the original network in the whole training process. At the end of the iteration, the mIoU and mPA were 93.98% and 97.48%, increasing 1.35% and 0.62%, respectively, compared with the original network. There was an obvious increase in the accuracy of region segmentation, the accuracy of pixel recognition, and segmentation speed, indicating better comprehensive performance of the model. The mIoU and mPA of the test set were 94.16% and 95.68%, exceeding the baseline by 1.47% and 1.08%, respectively. The speed of segmentation achieved 15.9 frames/s, which was increased 4.61% compared with the original network. The finding can provide a promising reference for the development of intelligent weeding equipment, thereby accurately recognizing and segment the maize and weeds at the seeding stage in complex field scenes. [ABSTRACT FROM AUTHOR]

Foxtail millet is a kind of minor coarse cereal. It is not one of the main grain crops, and is a kind of rainfed crop. So, it is mainly planted in the hilly and mountainous areas in northern China. Foxtail millet is becoming more and more popular in congee because of its mellow taste and abundant nutritional value. Given the characteristics of small and scattered planting plots for foxtail millet in northern hilly and mountainous areas, small seeder is more suitable for this kind of plot. According to the agronomic requirements of fine and small-amount sowing for foxtail millet, we design and manufacture the 2BZ-2 type fine and small-amount seeder for foxtail millet. This seeder consists of 2 sowing units, transmission system, ground wheels and body frame. Every unit is mainly made up of seed-metering device, furrow opener, soil coverer and press wheel. We use the tilt dise-type fine and small-amount seed-metering device for foxtail millet that was designed previously, and its working angle is 45°, and it has 36 filling holes and 36 seeding grooves. This device has got the national invention patent in China, and we have published an academic paper about it on Transactions of the Chinese Society of Agricultural Engineering. We design a kind of ship-shaped shovel type furrow opener, and its penetrating angle is 60°, its soil-cutting angle is 30°, its trenching width is 30 mm, and its height is 100 mm. We design a kind of scraper type soil coverer, and it mainly consists of 2 covering boards, connecting board and pull rod. The covering board is trapezoid-shaped, and its length is 100 mm, its front width is 80 mm, its back width is 40 mm, and its thickness is 3 mm. The included angle between the 2 covering boards is 50°, the inclined angle of the covering board toward the ground is 70°, and the width of the back opening between the 2 covering boards is 30 mm. We push the seeder and provide the driving force. The ground wheels pass the driving force to the seed-metering device via the transmission system. The transmission system is composed of two-stage chain drive and one-stage bevel gear drive. The chain drive uses the 08B roller chains and the matched chain wheels to drive down. The bevel gear drive uses 45° straight bevel gears to realize constant speed drive. According to the experimental requirements of Chinese National Standards, we design and conduct the seeding performance experiments and the field sowing experiments to test the working performance of this seeder. The seeding performance experiments include the tests of the consistency of every row's seeding quantity, the steadiness of total seeding quantity and the percentage of damaged millet. The field sowing experiments include the tests of the uniformity of sowing quantity and the consistency of sowing depth. The results of the seeding performance experiments indicate that, the coefficient of variation of consistency of every row's seeding quantity is less than or equal to 1.10%, the coefficient of variation of steadiness of total seeding quantity is less than or equal to 0.66%, and the percentage of damaged millet is less than or equal to 0.05%. The results of the field sowing experiments indicate that, the qualified index of hill spacing is greater than 83%, the replay index is less than 7%, the miss-seeding index is less than 12%, the coefficient of variation of qualified hill spacing is less than 10%, and the coefficient of variation of sowing depth is less than 1.5%. All the 8 indices meet the requirements of Chinese machinery industry standards. This study can provide a theoretical reference for the design and analysis of the fine and small-amount seeding equipment for foxtail millet suitable for the hilly and mountainous areas. [ABSTRACT FROM AUTHOR]

Suspension velocity of agricultural material is important basic data for the research of technology and equipment for mechanical cleaning. Given the characteristics of threshed materials to be cleaned of crops harvested by combine harvester, based on the suspension principle of material and the characteristics of mechanical cleaning working condition, we designed a kind of vertical air sweeping suspension velocity testing device for agricultural material. This device mainly consists of 3 kinds of components, including the air force and its controlling components, the flow field structural components and the measuring components. The air force and its controlling components are directly connected with the flow field structural components by flanges in vertical direction, and the measuring components are installed on the flow field structural components. The structure is compact. The air force and its controlling components consist of the centrifugal fan, the frequency converter, the conduit coupler between fan and pipelines, and the protecting net. The flow field structural components consist of the grille tube, the airflow-smoothing grille, flanges, holding net for materials, entrance gate of materials, collecting board for materials, lower airflow-stablizing pipe, tapered observation pipe, upper airflow-stablizing pipe, obstructive net for materials, and so on. The measuring components consist of the L type Pitot tube, bracket of Pitot tube, intelligent pressure air-volume anemometer, air conduit, suspended height ruler, observation platform, and so on. The overall size of this device (length × width × height) is 1.8 m × 1.1 m × 4.2 m. The motor power of fan is 7.5 kW. The airflow velocity can reach 40 m/s in this device. The flow field structural components are mainly formed by the grille tube, lower airflow-stablizing pipe, tapered observation pipe and upper airflow-stablizing pipe connected successively via flange connections in vertical direction. The 4 pipes are all welded with flanges at both ends and made of polymethyl methacrylate. The lengths of the 3 pipes except the grille tube are all 1 m. The inner diameters of the grille tube, lower airflow-stablizing pipe and the small end of the tapered observation pipe are all 240 mm. The dip angle of tapered observation pipe is 4° and its inner diameter of big end is 380 mm. We designed a circular airflow-smoothing grille installed in this device to avoid generating eddy at the outlet of fan, and its height is 100 mm, the side length of its square hole is 30 mm, and the thickness of grille plate is 2 mm. The anemometer can display the temperature, humidity, pressure, airflow velocity and flow rate in real time in the measurement. We designed and conducted staged suspension experiments to measure the suspension velocity of each component of the threshed materials to be cleaned by combine harvester during the harvesting time of foxtail millet, buckwheat and oat, respectively. The results show that the range of suspension velocity of grains, spikelets, stalks and leaves of threshed materials to be cleaned of foxtail millet is respectively 4.29-8.88, 1.03-6.48, 1.71-6.09 and 1.03-3.09 m/s. The range of suspension velocity of grains, ramulus, stalks and leaves of threshed materials to be cleaned of buckwheat is respectively 4.47-10.18, 1.85-5.18, 2.80-8.37 and 0.76-2.99 m/s. The range of suspension velocity of grains, testas, ramulus, stalks, leaves and unpeeled grains of threshed materials to be cleaned of oat is respectively 4.35-11.01, 0.62-1.71, 1.62-4.52, 1.14-6.28, 0.91-3.56 and 3.24-9.48 m/s. The grains’ suspension velocities of foxtail millet and oat are both different from their most light impurities’, the grains’ suspension velocity of oat is similar to its unpeeled grains’, and the grains’ suspension velocity of buckwheat is different from its minor light impurities’. This study can provide reference for the research and development of cleaning technology and equipment for agricultural materials. [ABSTRACT FROM AUTHOR]

Millet contains protein, vitamin B1 and other mineral elements needed for human health, which has functions of enhancing blood circulation, brain tonic, and sleep quality. In recent years, the market demand for millet is rising. However, the mechanization level of millet harvesting is low. Manual harvesting is very common, which requires high labor intensity, has low efficiency and results in insufficient supply of millet. In this paper, we systematically investigated effects of moisture content and varieties of millet on its physical parameters, effects of millet varieties and compression azimuth on the compression mechanical properties (including yield load, deformation, failure energy and apparent elastic modulus) of millet, and effects of compression azimuth on crack formation of millet. The study results are expected to provide the basis for the design and optimization of millet harvester and related processing machinery. In this paper, the 1000-grain weight was measured by an electronic balance, the triaxial sizes by a vernier caliper, and the moisture content by fast grain moisture analyzer for four millet varieties: Zhangza-10, Dungu, Jingu-21, Changgu. The sphericity of the millet, the arithmetic mean diameter and the geometric diameter were calculated using the triaxial sizes. The compression tests were carried out along X, Y, Z axis using a texture analyzer and the data were analyzed by SAS statistics software. The yield load, deformation, and failure energy were obtained from the force-distance curve measured by a texture analyzer. At the same time, the apparent elastic modulus was calculated according to the Hertz formula. The experimental results were summarized as follows in six categories. 1) For the physical parameters of the millet, with a moisture content between 15.2% and 25.1%，the length, width, height, 1 000-grain weight, average diameter and geometric mean diameter of millet grain decreased as the moisture content decreased. The millet length, width and thickness range from 2.028 to 2.112 mm, 1.818 to 1.931 mm, 1.413 to 1.513 mm, respectively. The sphericity of millet was more than 84%; the arithmetic mean diameter varied from 1.750 mm to 1.852 mm; and the geometric mean diameter 1.732 mm to 1.834 mm. Therefore, the shape of millet can be regarded as ellipsoid. There were significant differences (P<0.001) in the triaxial sizes, 1000-grain weight, sphericity, arithmetic mean diameter and geometric mean diameter among different varieties. When the moisture content of millet was about 25%, the 1000-grain weight of Jingu-21 was 3.473 g, which was the heaviest millet, while Zhangza-10 was 3.264 g, which was the lightest millet. The moisture content has a negligible effect on the sphericity. The effect of varieties on sphericity was significant (P<0.001). 2) For factors on the compression mechanical properties, the influence of moisture content, compression azimuth, and variety on the compression mechanical properties were significant (P<0.01). The significant factors affecting the compression mechanical properties were compression azimuth, moisture content, and variety in a sequence from the most significant to the least significant. 3) For the effects of the moisture content, for the same kind of millet, the yield load and apparent elastic modulus decreased as the moisture content increased during compression in X, Y, Z axis. The yield load decreased slowly when moisture content ranged from 20.9% to 25.1%. The deformation and failure energy first decreased and then increased as the moisture content increased. For the same azimuth compression, the better the quality of the millet, the more compact the internal structure, and the smaller the deformation. 4) For crack formation of the millet: on the X axial, a crack started from the crest of the grain along the junction of embryo and endosperm, and then extended throughout the X axis. On the Y axis, a crack started from the connection point of grain and probe and the connection point of grain and base throughout the Y axis because of stress concentration. On the Z axis, a crack started from the junction of embryo and endosperm on the back to the ventral hilum along the weakest part of endosperm resistance extending throughout half of the grain. 5) For the effects of compression azimuth, the yield load increased in turn on the X, Y, and Z axis and the deformation and failure energy decreased on the X, Z, and Y axis in turn. The apparent elastic modulus of the millet increased in turn on the X, Y, and Z axis. This result indicated that millet was not uniform and it was an anisotropic body. 6) For the effects of millet varieties, with the same moisture content, the compression mechanical properties of Jingu-21, Dungu, Changgu and Zhangza-10 varied from large to small. This indicated that Jingu-21 had a relatively good compression resistance and quality. [ABSTRACT FROM AUTHOR]