Tracking control of tendon-driven manipulators has become a prevalent research area.However,the existence of flexible elastic tendons generates substantial residual vibrations,resulting in difficulties for trajectory ...Tracking control of tendon-driven manipulators has become a prevalent research area.However,the existence of flexible elastic tendons generates substantial residual vibrations,resulting in difficulties for trajectory tracking control of the manipulator.This paper proposes the radial basis function neural network adaptive hierarchical sliding mode control(RBFNNA-HSMC)method,which combines the dynamic model of the elastic tendon-driven manipulator(ETDM)with radial basis neural network adaptive control and hierarchical sliding mode control technology.The aim is to achieve trajectory tracking control of ETDM even under conditions of model inaccuracy and disturbance.The Lyapunov stability theory demonstrates the stability of the proposed RBFNNA-HSM controller.In order to assess the effectiveness and adaptability of the proposed control method,simulations and experiments were performed on a two-DOF ETDM.The RBFNNA-HSM method shows superior tracking accuracy compared to traditional modelbased HSM control.The experiment shows that the maximum tracking error for ETDM double-joint trajectory tracking is below 2.593×10-3rad and 1.624×10-3rad,respectively.展开更多
The current automatic scallion-transplanting machine is a complicated mechanism composed of two linkage mechanisms and two band carriers.It delivers seedlings ine ciently because of the movement limitations of the lin...The current automatic scallion-transplanting machine is a complicated mechanism composed of two linkage mechanisms and two band carriers.It delivers seedlings ine ciently because of the movement limitations of the linkage mechanism.This paper proposes a new high-order non-circular gear train for an automatic scallion-seedling feeding mechanism.The proposed gear train has an asymmetrical transmission ratio;i.e.,its transmission ratio varies.This allows the mechanism’s execution component to move in a long displacement and rotate in a large rotation angle.The long displacement enables the execution component to reach the designed working position,and the large rotation angle allows it to feed a scallion in the required pose.A mathematical model for calculating the asymmetrical transmission ratio was established according to the closure requirements and the full-cycle motion of the driven gear pitch curve.Then,the parameter-design model of the new seedling-feeding mechanism was established,based on precise pose points and trajectory-shape control points.Moreover,an aided-design program was developed to obtain the parameter-solution domain of the scallion-seedling feeding mechanism.The mechanism parameters,which met the seedling-feeding function,were optimized to determine the transmission ratio,using a program and a kinematic simulation.Finally,a prototype of the mechanism was produced,and a seedling-feeding experiment was carried out.One-thousand seedlings were tested at a rate of 100 seedlings per minute,and the statistical success rate was 93.4%.Thus,the automatic scallion-seedling feeding mechanism significantly improves the e ciency of automatically transplanting scallions.展开更多
To address the difficulty of locating the picking point of a tea sprout during the intelligent automatic picking of famous tea,this study proposes a method to obtain information on the picking point on the basis of th...To address the difficulty of locating the picking point of a tea sprout during the intelligent automatic picking of famous tea,this study proposes a method to obtain information on the picking point on the basis of the ShiTomasi algorithm.This method can rapidly identify a tea sprout’s picking point and obtain its coordinates.Images of tea sprouts in a tea garden were collected,and the G-B component of tea sprouts was segmented using the Otsu algorithm.The region of interest was set with the lowest point of its contour as the center.The characteristics of tea buds and branches in the area were extracted,and the Otsu algorithm was used for a second segmentation of tea sprout images.The tea buds were segmented using the improved Zhang algorithm.The branch feature binary image was used to refine the skeleton,and the Shi-Tomasi algorithm was used to detect the corners of the skeleton and calculate and mark the picking points of the shoots.Sixty sets of samples were tested.The test identified 1,042 effective shoots for tender buds,and 887 picking points were marked,with a success rate of 85.12%,thereby verifying the effectiveness of the method and providing a theoretical reference for the visual positioning of the automatic picking of famous tea.展开更多
The noncircular synchronous belt drive mechanism has demonstrated certain achievements and has been used in special fields.Research regarding noncircular synchronous belt drive mechanisms has focused on optimization d...The noncircular synchronous belt drive mechanism has demonstrated certain achievements and has been used in special fields.Research regarding noncircular synchronous belt drive mechanisms has focused on optimization design and kinematic analysis in China,whereas two pulley noncircular synchronous belt transmissions have been developed overseas.However,owing to the noncircular characteristics of the belt pulley,the real-time variation in the belt length slack during the transmission of the noncircular synchronous belt is significant,resulting in high probabilities of skipping and vibration.In this study,a noncircular tensioning pulley is added to create a stable three-pulley noncircular synchronous belt driving mechanism and a good synchronous belt tensioning,with no skipping;hence,the non-uniform output characteristic of the driven pulley is consistent with the theoretical value.In the circular noncircular noncircular three-pulley noncircular synchronous belt mechanism,the pitch curve of the driving synchronous belt pulley is circular,whereas those of the driven synchronous belt and tensioning pulleys are noncircular.To minimize the slack of the belt length of the synchronous belt and the constraint of the concavity and circumference of the tensioning pulley,an automatic optimization model of the tensioning pulley pitch curve is established.The motion simulation,analysis,and optimization code for a three-belt-pulley noncircular synchronous belt drive mechanism is written,and the variation in belt length slack under different speed ratios is analyzed based on several examples.The testbed for a circular-noncircular-noncircular three-pulley noncircular synchronous belt transmission mechanism is developed.The test shows that the three-pulley noncircular synchronous belt drives well.This study proposes an automatic optimization algorithm for the tensioning pulley pitch curve of a noncircular synchronous belt transmission mechanism;it yields a stable transmission of the noncircular synchronous belt transmission mechanism as well as non-uniform output characteristics.展开更多
The film-covered sweet potato transplanting method requires ensuring the transplantation conditions of small planting holes and large lateral displacement.In the soil insertion phase,the transplantation machine requir...The film-covered sweet potato transplanting method requires ensuring the transplantation conditions of small planting holes and large lateral displacement.In the soil insertion phase,the transplantation machine requires a mechanism design with multiple timed poses,and the existing design methods are still imperfect.For this reason,this article proposes a multi-target trust region parameter-guided optimization algorithm.This algorithm aims to achieve multi-objective optimization design with more timed pose conditions starting from individual timed pose conditions.First,multi-target problems are decomposed into multiple subproblems,and the parameter arrays are kept with the minimum polymerization value of each subproblem.Then,the approximate function value reduction for each target is calculated using this parameter set,and the step size for the next iteration of each subproblem is determined by comparing this approximate reduction with the actual reduction.After many iteration calculations,the parameter arrays end the calculation when the parameter group is no longer updated.This paper uses the design of a film-covered sweet potato transplanting mechanism as a complex optimized application example.The algorithm is used to obtain the optimization results of the target values of eight groups of institutions.The smallest hole is 2.99 mm,and the horizontal transplanting distance is 108.40 mm.The maximum hole is 17.64 mm,and the horizontal transplanting distance is 124.97 mm.Considering the size of the hole and the horizontal transplanting distance of sweet potato transplanting,the mechanism’s target value of the horizontal transplanting distance at 119.92 mm and the hole size at 0.31 mm were selected to design the sweet potato transplanting machine.The correctness of the results is verified,which reflects the practicability of the algorithm.展开更多
Tea shoot segmentation is crucial for the automation of high-quality tea plucking.However,accurate segmentation of tea shoots in unstructured and complex environments presents significant challenges due to the small s...Tea shoot segmentation is crucial for the automation of high-quality tea plucking.However,accurate segmentation of tea shoots in unstructured and complex environments presents significant challenges due to the small size of the targets and the similarity in color between the shoots and their background.To address these challenges and achieve accurate recognition of tea shoots in complex settings,an advanced tea shoot segmentation network model is proposed based on You Only Look Once version 8 segmentation(YOLOv8-seg)network model.Firstly,to enhance the model’s segmentation capability for small targets,this study designed a feature fusion network that incorporates shallow,large-scale features extracted by the backbone network.Subsequently,the features extracted at different scales by the backbone network are fused to obtain both global and local features,thereby enhancing the overall information representation capability of the features.Furthermore,the Efficient Channel Attention mechanism was integrated into the feature fusion process and combined with a reparameterization technique to refine and improve the efficiency of the fusion process.Finally,Wise-IoU with a dynamic non-monotonic aggregation mechanism was employed to assign varying gradient gains to anchor boxes of differing qualities.Experimental results demonstrate that the improved network model increases the AP50 of box and mask by 4.33%and 4.55%,respectively,while maintaining a smaller parameter count and reduced computational demand.Compared to other classical segmentation algorithms models,the proposed model excels in tea shoot segmentation.Overall,the advancements proposed in this study effectively segment tea shoots in complex environments,offering significant theoretical and practical contributions to the automated plucking of high-quality tea.展开更多
The mechanization of famous tea harvesting is an essential way to develop China’s tea industry.This paper centers on the detection and positioning technologies in famous tea harvesting,systematically reviewing resear...The mechanization of famous tea harvesting is an essential way to develop China’s tea industry.This paper centers on the detection and positioning technologies in famous tea harvesting,systematically reviewing research progress in these domains.In tea detection,traditional methods rely on color space selection and image segmentation,exhibiting limitations such as insufficient accuracy and poor generalization capability.Conversely,deep learning algorithms demonstrate superior detection accuracy and robustness.Current research focuses on enhancing detection accuracy,inference speed,and multivariety recognition.In picking positioning,depth information measurement technology utilizing RGB-D cameras provides foundational support.Positioning methods have evolved from traditional visual processing techniques to deep learning and point cloud approaches,seeking to overcome challenges including occlusion and irregular growth patterns.Notwithstanding notable technological advancements,existing methods confront three primary limitations:difficulties in adapting to diverse growth stage characteristics,reliance on large-scale annotated datasets,and inadequate occlusion handling.Future research ought to concentrate on three directions:developing highly universal tea bud detection models,refining model training techniques for small-sample scenarios,and improving tea-picking point positioning accuracy under occluded conditions.This review aims to furnish critical references for advancing high-end intelligent tea-picking machinery,thereby facilitating the tea industry’s mechanization and intelligentization.展开更多
Achieving high-efficiency and accurate detection of tea shoots in fields are essential for tea robotic plucking. A real-time tea shoot detection method using the channel and layer pruned YOLOv3-SPP deep learning algor...Achieving high-efficiency and accurate detection of tea shoots in fields are essential for tea robotic plucking. A real-time tea shoot detection method using the channel and layer pruned YOLOv3-SPP deep learning algorithm was proposed in this study. First, tea shoot images were collected and data augmentation was performed to increase sample diversity, and then a spatial pyramid pooling module was added to the YOLOv3 model to detect tea shoots. To simplify the tea shoot detection model and improve the detection speed, the channel pruning algorithm and layer pruning algorithm were used to compress the model. Finally, the model was fine-tuned to restore its accuracy, and achieve the fast and accurate detection of tea shoots. The test results demonstrated that the number of parameters, model size, and inference time of the tea shoot detection model after compression reduced by 96.82%, 96.81%, and 59.62%, respectively, whereas the mean average precision of the model was only 0.40% lower than that of the original model. In the field test, the compressed model was deployed on a Jetson Xavier NX to conduct the detection of tea shoots. The experimental results demonstrated that the detection speed of the compressed model was 15.9 fps, which was 3.18 times that of the original model. All the results indicate that the proposed method could be deployed on tea harvesting robots with low computing power to achieve high efficiency and accurate detection.展开更多
Aiming at decreasing the component complexity and cost of flower transplanting machine,an integrated transplanting method for picking and planting flower seedlings was proposed,and a hybrid-driven five-bar parallel me...Aiming at decreasing the component complexity and cost of flower transplanting machine,an integrated transplanting method for picking and planting flower seedlings was proposed,and a hybrid-driven five-bar parallel mechanism was designed.A“beak-shaped”trajectory was designed for integrated transplanting requirements,and meantime,either the posture requirements of transplanting claw were determined.Based on the transplanting trajectory of the mechanism,a corresponding mathematical model for solving the link parameters was established,and then the five-bar mechanism was divided into two bar groups,optimization was conducted in two steps based on genetic algorithm and NSGA-II algorithm.Consequently,the optimal solution of the hybrid-driven five-bar parallel mechanism for flower seedling transplanting was obtained.Compared with similar designs,the trajectory displacement of the proposed mechanism is larger in the condition of smaller link size,which indicates that the mechanism can effectively decrease the machine size.The real-time controllable motor angular acceleration fluctuation is smaller and the commutation times are less,which has the advantage of reducing the difficulty of the mechanism control system.Subsequently,the correctness of the design method is verified by kinematics simulation.Finally,the synchronous linkage motion control methods of the two motors were designed,a transplanting experiment of the prototype was carried out,the picking success rate had reached 90%-93.4%and transplanting success rate was 80.5%-86.9%during experiment,which showed that the integrated operation of picking and planting flower seedlings can be realized by the proposed mechanism.展开更多
In view of the problems of the existing mechanisms based on 2R open-chain planetary gear train for seedling transplanting,such as the bad tracking flexibility,low positioning accuracy,and high structure design difficu...In view of the problems of the existing mechanisms based on 2R open-chain planetary gear train for seedling transplanting,such as the bad tracking flexibility,low positioning accuracy,and high structure design difficulties of the mechanisms based on 3R open-chain planetary gear train for seedling manipulation.In this paper,a transplanting mechanism based on the solution domain synthesis of a 3R open-chain-based complete rotation kinematic pair,a gear train with a single cycle integral rotating pair,is designed.The Burmester curve equation is derived from the given transplanting trajectory and four exact poses corresponding to each other on the rotation center.Then,the open-chain road model of the 3R complete rotation kinematic pair is obtained under the constraint governed by the judgment condition of the hinge integral rotating pair.Meanwhile,combined with our developed in-house optimization software,the solution to the optimal parameters for the transplanting mechanism can be optimized according to the target trajectory.Finally,the feasibility of the design method is verified by transplanting testing,where kale seedlings with ages of about 20 d and heights of about 80-120 mm are used.The experimental results show that the actual motion trajectory of the prototype is basically identical to the theoretical trajectory,validating the feasibility of transplanting mechanism design,parts processing,and test-bed construction.Through the statistical analysis,the average success rate of transplanting is 90.625%,and the reliability of designed mechanism is satisfied.This study provides a promising solution for the seedling transplanting of two-planet scaffold pots.展开更多
At present,there is a lack of miniaturized and highly reliable plug seedling transplanting mechanism in flowerpots planting operation,in order to meet the needs of large displacement and high vertical uprightness for ...At present,there is a lack of miniaturized and highly reliable plug seedling transplanting mechanism in flowerpots planting operation,in order to meet the needs of large displacement and high vertical uprightness for flower transplanting,the paper combined the transmission characteristics of the non-circular gear planetary gear train with the swing flexibility of the cam gear and proposed a double planet carrier planetary gear transplanting mechanism.The linkage of the mechanism performs variable speed rotation relative to the first planet carrier,the linkage serves as the second planet carrier,and the transplanting arm performs variable speed swing relative to the linkage.A mathematical model of a single planetary carrier mechanism was first established using the method of open linkage group solution domain synthesis,then established the kinematic equations of the second planet carrier and the transplanting arm.The two parts are combined to form the mathematical solution model of the proposed mechanism.The initial trajectory was planned according to the trajectory requirements of seedlings planting operation,the non-circular gear pitch curve in the first planet carrier was obtained and the length of the first planet carrier is 120 mm.Then using the key points’angular deviation between the initial trajectory and the improved trajectory to obtain the cam parameters which driving the transplant arm,consequently determined the length of the second planet carrier is 69.25 mm and the length of the transplant arm is 112.4 mm.Finally,the prototype of the mechanism was manufactured,and the test verified the correctness of the design method of the double planet carrier planetary gear flower potting transplanting mechanism.The transplanting success rate of this mechanism reached 94.43%,and the plug seedlings planted in flowerpots had high uprightness.This research can provide a reference for the automatic development of research on flower transplanting machines.展开更多
In order to improve the adaptability of the planting mechanism for different plant spacings,a variable differential gear train planting mechanism based on precise pose and trajectory control was proposed by combining ...In order to improve the adaptability of the planting mechanism for different plant spacings,a variable differential gear train planting mechanism based on precise pose and trajectory control was proposed by combining the open chain 2R rod group and the variable differential gear train.According to the pose requirements of receiving seedling point,transporting seedling point and planting point,three precise pose points of constrained planting trajectory were determined.Through the three-position motion generation structural synthesis method,combined with computer-aided optimization design software,a set of mechanism parameters that meet the planting requirements were optimized.Based on the optimized mechanism parameters,by only changing the coordinates of two trajectory shape control points,three planting trajectories with key point position information adapted to 300 mm,400 mm and 500 mm plant spacing were obtained by interpolation,and three pairs of total transmission ratio of three groups of variable differential gear trains were calculated.When distributing the total transmission ratio of the mechanism,the fixed axis gear train and the differential gear train are combined.The fixed axis gear train included a pair of non-circular gear pairs and a pair of positive gear pairs,which were convenient for disassembly and assembly.The former drives the sun gear at variable speed,and the latter drives the planet carrier at uniform speed.Based on this structure,the transmission ratio of the positive gear pair is-1,and the transmission ratio of the differential gear train is 0.5.The sub-transmission ratio of the single-stage non-circular gear pair was calculated and the pitch curves of three pairs of noncircular gears were solved.Three pairs of non-circular gear pairs with different transmission ratios were replaced in turn and three sets of planting mechanisms were modeled in three dimensions.The virtual prototype motion simulation was completed by ADAMS software,and the physical prototype was built for vegetable pot seedling planting test.The theoretical solution was consistent with the attitude and trajectory of the actual test.When the test sample size was 100 plants,the actual average plant spacing was measured to be 303 mm,402 mm,and 503 mm,with errors of 1.3%,1.25%,and 1.88%.The width of the moving hole was 72 mm,70 mm,and 71 mm,and the planting success rate were 94%,96%,and 95%.The test results verified the correctness of the optimization design results of the mechanism,indicating that the variable differential gear train planting mechanism can adapt to a variety of plant spacing and has good planting effect.展开更多
In this study,the motion characteristics of manual stirring were analyzed to achieve the goal of realizing a highquality mechanized imitation of manual stirring for oolong tea.A test bench for collecting the motion ch...In this study,the motion characteristics of manual stirring were analyzed to achieve the goal of realizing a highquality mechanized imitation of manual stirring for oolong tea.A test bench for collecting the motion characteristics of manual stirring was designed,and the standard manual stirring motion characteristic curve was obtained.According to the requirements of the stirring motion characteristics,a variable-speed and variable-amplitude stirring mechanism was proposed,the kinematics model and reverse design model of the stirring mechanism were established,auxiliary analysis and design software were written,and the non-circular gear pitch curve and cam profile curve were obtained.A three-dimensional model of the stirring machine was established,a virtual prototype of the stirring machine was built,and the simulation experiment was completed by using the ADAMS software.A prototype of the stirring machine was developed,and the stirring experiment was conducted on the prototype.The maximum deviation of the pitch angle is 2.8772°,and the maximum deviation of the roll angle is 1.5948°according to the analysis and comparison of the actual curve data and the theoretical data curve.The experimental results showed that the simulation angle curve and the actual angle curve were consistent with the theoretical standard manual stirring motion characteristic curve,which verified the correctness of the design and modeling of the stirring mechanism.The tea was mechanically stirred by the stirring mechanism to achieve the desired stirring effect,which verified the feasibility of the stirring machine.展开更多
In China,tea products made from fresh leaves characterized by one leaf with one bud(1L1B)are classified as“Famous Tea”,which has better taste and higher economic value,but suffers from a labor shortage.Aiming at pic...In China,tea products made from fresh leaves characterized by one leaf with one bud(1L1B)are classified as“Famous Tea”,which has better taste and higher economic value,but suffers from a labor shortage.Aiming at picking automation,existing studies focus on visual detection of 1L1B,but algorithm validation is limited to a specific variety of tea sprouting in a certain harvest season at a certain location,which limits the engineering application of developed tea picking robots working in various natural tea fields.To address this gap,a deep learning model DMT(detecting multispecies of tea)based on YOLOX-S was proposed in this paper.The DMT network takes YOLOX-S as a baseline and adds ECA-Net to the CSP Darknet and FPN of YOLOX-S.The average precision(AP),precision,and recall of DMT are 94.23%,93.39%,and 88.02%,respectively,for detecting 1L1B sprouting in spring;93.92%,93.56%,and 87.88%,respectively,for detecting 1L1Bsprouting in autumn.These experimental results are better than those of the five current object detection models.After fine-tuning the DMT network with another dataset composed of multiple tea varieties,the DMT network can detect 1L1B for different varieties of tea in multiple picking seasons.The results can promote the engineering application of picking automation of fresh tea leaves.展开更多
基金Supported by Key R&D Project of Zhejiang(Grant No.2022C02052)。
文摘Tracking control of tendon-driven manipulators has become a prevalent research area.However,the existence of flexible elastic tendons generates substantial residual vibrations,resulting in difficulties for trajectory tracking control of the manipulator.This paper proposes the radial basis function neural network adaptive hierarchical sliding mode control(RBFNNA-HSMC)method,which combines the dynamic model of the elastic tendon-driven manipulator(ETDM)with radial basis neural network adaptive control and hierarchical sliding mode control technology.The aim is to achieve trajectory tracking control of ETDM even under conditions of model inaccuracy and disturbance.The Lyapunov stability theory demonstrates the stability of the proposed RBFNNA-HSM controller.In order to assess the effectiveness and adaptability of the proposed control method,simulations and experiments were performed on a two-DOF ETDM.The RBFNNA-HSM method shows superior tracking accuracy compared to traditional modelbased HSM control.The experiment shows that the maximum tracking error for ETDM double-joint trajectory tracking is below 2.593×10-3rad and 1.624×10-3rad,respectively.
基金Supported by the National Key Research and Development Program of China(Grant No.2017YFD0700800)National Natural Science Foundation of China(Grant Nos.51775512,51975536)+1 种基金Zhejiang Provincial Natural Science Foundation of China(Grant No.LQ20E050003)Basic Public Welfare Technology Application Research Projects of Zhejiang Province(Grant Nos.LGN19E050002,LGN20E050006).
文摘The current automatic scallion-transplanting machine is a complicated mechanism composed of two linkage mechanisms and two band carriers.It delivers seedlings ine ciently because of the movement limitations of the linkage mechanism.This paper proposes a new high-order non-circular gear train for an automatic scallion-seedling feeding mechanism.The proposed gear train has an asymmetrical transmission ratio;i.e.,its transmission ratio varies.This allows the mechanism’s execution component to move in a long displacement and rotate in a large rotation angle.The long displacement enables the execution component to reach the designed working position,and the large rotation angle allows it to feed a scallion in the required pose.A mathematical model for calculating the asymmetrical transmission ratio was established according to the closure requirements and the full-cycle motion of the driven gear pitch curve.Then,the parameter-design model of the new seedling-feeding mechanism was established,based on precise pose points and trajectory-shape control points.Moreover,an aided-design program was developed to obtain the parameter-solution domain of the scallion-seedling feeding mechanism.The mechanism parameters,which met the seedling-feeding function,were optimized to determine the transmission ratio,using a program and a kinematic simulation.Finally,a prototype of the mechanism was produced,and a seedling-feeding experiment was carried out.One-thousand seedlings were tested at a rate of 100 seedlings per minute,and the statistical success rate was 93.4%.Thus,the automatic scallion-seedling feeding mechanism significantly improves the e ciency of automatically transplanting scallions.
基金The authors gratefully acknowledge the financial support provided by the Special Fund for the Construction of Modern Agricultural Industrial Technology Systems(CARS-19)in China.
文摘To address the difficulty of locating the picking point of a tea sprout during the intelligent automatic picking of famous tea,this study proposes a method to obtain information on the picking point on the basis of the ShiTomasi algorithm.This method can rapidly identify a tea sprout’s picking point and obtain its coordinates.Images of tea sprouts in a tea garden were collected,and the G-B component of tea sprouts was segmented using the Otsu algorithm.The region of interest was set with the lowest point of its contour as the center.The characteristics of tea buds and branches in the area were extracted,and the Otsu algorithm was used for a second segmentation of tea sprout images.The tea buds were segmented using the improved Zhang algorithm.The branch feature binary image was used to refine the skeleton,and the Shi-Tomasi algorithm was used to detect the corners of the skeleton and calculate and mark the picking points of the shoots.Sixty sets of samples were tested.The test identified 1,042 effective shoots for tender buds,and 887 picking points were marked,with a success rate of 85.12%,thereby verifying the effectiveness of the method and providing a theoretical reference for the visual positioning of the automatic picking of famous tea.
基金Supported by National Natural Science Foundation of China(Grant Nos.51675486,51805487).
文摘The noncircular synchronous belt drive mechanism has demonstrated certain achievements and has been used in special fields.Research regarding noncircular synchronous belt drive mechanisms has focused on optimization design and kinematic analysis in China,whereas two pulley noncircular synchronous belt transmissions have been developed overseas.However,owing to the noncircular characteristics of the belt pulley,the real-time variation in the belt length slack during the transmission of the noncircular synchronous belt is significant,resulting in high probabilities of skipping and vibration.In this study,a noncircular tensioning pulley is added to create a stable three-pulley noncircular synchronous belt driving mechanism and a good synchronous belt tensioning,with no skipping;hence,the non-uniform output characteristic of the driven pulley is consistent with the theoretical value.In the circular noncircular noncircular three-pulley noncircular synchronous belt mechanism,the pitch curve of the driving synchronous belt pulley is circular,whereas those of the driven synchronous belt and tensioning pulleys are noncircular.To minimize the slack of the belt length of the synchronous belt and the constraint of the concavity and circumference of the tensioning pulley,an automatic optimization model of the tensioning pulley pitch curve is established.The motion simulation,analysis,and optimization code for a three-belt-pulley noncircular synchronous belt drive mechanism is written,and the variation in belt length slack under different speed ratios is analyzed based on several examples.The testbed for a circular-noncircular-noncircular three-pulley noncircular synchronous belt transmission mechanism is developed.The test shows that the three-pulley noncircular synchronous belt drives well.This study proposes an automatic optimization algorithm for the tensioning pulley pitch curve of a noncircular synchronous belt transmission mechanism;it yields a stable transmission of the noncircular synchronous belt transmission mechanism as well as non-uniform output characteristics.
基金supported by the Key Research Projects of China(Grant No.2022YFD2001800)the National Natural Science Foundation of China(Grant No.32071909)Zhejiang Provincial Natural Science Foundation(Grant No.LD24E05007).
文摘The film-covered sweet potato transplanting method requires ensuring the transplantation conditions of small planting holes and large lateral displacement.In the soil insertion phase,the transplantation machine requires a mechanism design with multiple timed poses,and the existing design methods are still imperfect.For this reason,this article proposes a multi-target trust region parameter-guided optimization algorithm.This algorithm aims to achieve multi-objective optimization design with more timed pose conditions starting from individual timed pose conditions.First,multi-target problems are decomposed into multiple subproblems,and the parameter arrays are kept with the minimum polymerization value of each subproblem.Then,the approximate function value reduction for each target is calculated using this parameter set,and the step size for the next iteration of each subproblem is determined by comparing this approximate reduction with the actual reduction.After many iteration calculations,the parameter arrays end the calculation when the parameter group is no longer updated.This paper uses the design of a film-covered sweet potato transplanting mechanism as a complex optimized application example.The algorithm is used to obtain the optimization results of the target values of eight groups of institutions.The smallest hole is 2.99 mm,and the horizontal transplanting distance is 108.40 mm.The maximum hole is 17.64 mm,and the horizontal transplanting distance is 124.97 mm.Considering the size of the hole and the horizontal transplanting distance of sweet potato transplanting,the mechanism’s target value of the horizontal transplanting distance at 119.92 mm and the hole size at 0.31 mm were selected to design the sweet potato transplanting machine.The correctness of the results is verified,which reflects the practicability of the algorithm.
基金supported by the National Natural Science Foundation of China(Grant No.52305289,Grant No.U23A20175)the Open Fund of State Key Laboratory of Tea Plant Biology and Utilization(Grant No.NKLTOF20240103)the earmarked fund for CARS-19 and the Open Project Program of Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry,Wuyi University.
文摘Tea shoot segmentation is crucial for the automation of high-quality tea plucking.However,accurate segmentation of tea shoots in unstructured and complex environments presents significant challenges due to the small size of the targets and the similarity in color between the shoots and their background.To address these challenges and achieve accurate recognition of tea shoots in complex settings,an advanced tea shoot segmentation network model is proposed based on You Only Look Once version 8 segmentation(YOLOv8-seg)network model.Firstly,to enhance the model’s segmentation capability for small targets,this study designed a feature fusion network that incorporates shallow,large-scale features extracted by the backbone network.Subsequently,the features extracted at different scales by the backbone network are fused to obtain both global and local features,thereby enhancing the overall information representation capability of the features.Furthermore,the Efficient Channel Attention mechanism was integrated into the feature fusion process and combined with a reparameterization technique to refine and improve the efficiency of the fusion process.Finally,Wise-IoU with a dynamic non-monotonic aggregation mechanism was employed to assign varying gradient gains to anchor boxes of differing qualities.Experimental results demonstrate that the improved network model increases the AP50 of box and mask by 4.33%and 4.55%,respectively,while maintaining a smaller parameter count and reduced computational demand.Compared to other classical segmentation algorithms models,the proposed model excels in tea shoot segmentation.Overall,the advancements proposed in this study effectively segment tea shoots in complex environments,offering significant theoretical and practical contributions to the automated plucking of high-quality tea.
基金the National Natural Science Foundation of China(Grants No.U23A20175,52305289,32472009)China Agriculture Research System of MOF and MARA(CARS-19).
文摘The mechanization of famous tea harvesting is an essential way to develop China’s tea industry.This paper centers on the detection and positioning technologies in famous tea harvesting,systematically reviewing research progress in these domains.In tea detection,traditional methods rely on color space selection and image segmentation,exhibiting limitations such as insufficient accuracy and poor generalization capability.Conversely,deep learning algorithms demonstrate superior detection accuracy and robustness.Current research focuses on enhancing detection accuracy,inference speed,and multivariety recognition.In picking positioning,depth information measurement technology utilizing RGB-D cameras provides foundational support.Positioning methods have evolved from traditional visual processing techniques to deep learning and point cloud approaches,seeking to overcome challenges including occlusion and irregular growth patterns.Notwithstanding notable technological advancements,existing methods confront three primary limitations:difficulties in adapting to diverse growth stage characteristics,reliance on large-scale annotated datasets,and inadequate occlusion handling.Future research ought to concentrate on three directions:developing highly universal tea bud detection models,refining model training techniques for small-sample scenarios,and improving tea-picking point positioning accuracy under occluded conditions.This review aims to furnish critical references for advancing high-end intelligent tea-picking machinery,thereby facilitating the tea industry’s mechanization and intelligentization.
基金This work was financially supported by the China Agriculture Research System of Ministry of Finance and Ministry of Agriculture and Rural Affairs and the National Natural Science Foundation of China(Grant No.51975537).
文摘Achieving high-efficiency and accurate detection of tea shoots in fields are essential for tea robotic plucking. A real-time tea shoot detection method using the channel and layer pruned YOLOv3-SPP deep learning algorithm was proposed in this study. First, tea shoot images were collected and data augmentation was performed to increase sample diversity, and then a spatial pyramid pooling module was added to the YOLOv3 model to detect tea shoots. To simplify the tea shoot detection model and improve the detection speed, the channel pruning algorithm and layer pruning algorithm were used to compress the model. Finally, the model was fine-tuned to restore its accuracy, and achieve the fast and accurate detection of tea shoots. The test results demonstrated that the number of parameters, model size, and inference time of the tea shoot detection model after compression reduced by 96.82%, 96.81%, and 59.62%, respectively, whereas the mean average precision of the model was only 0.40% lower than that of the original model. In the field test, the compressed model was deployed on a Jetson Xavier NX to conduct the detection of tea shoots. The experimental results demonstrated that the detection speed of the compressed model was 15.9 fps, which was 3.18 times that of the original model. All the results indicate that the proposed method could be deployed on tea harvesting robots with low computing power to achieve high efficiency and accurate detection.
基金The research work was financially supported by the National Natural Science Foundation of China(Grant No.51775512,51975536)Key research projects of Zhejiang Province(Grant No.2018C02046)+2 种基金Project funded by China Postdoctoral Science FoundationBasic public welfare research projects of Zhejiang Province(Grant No.LGN19E050002,LGN20E050006)Basic Scientific Research Foundation of Zhejiang Sci-Tech University.
文摘Aiming at decreasing the component complexity and cost of flower transplanting machine,an integrated transplanting method for picking and planting flower seedlings was proposed,and a hybrid-driven five-bar parallel mechanism was designed.A“beak-shaped”trajectory was designed for integrated transplanting requirements,and meantime,either the posture requirements of transplanting claw were determined.Based on the transplanting trajectory of the mechanism,a corresponding mathematical model for solving the link parameters was established,and then the five-bar mechanism was divided into two bar groups,optimization was conducted in two steps based on genetic algorithm and NSGA-II algorithm.Consequently,the optimal solution of the hybrid-driven five-bar parallel mechanism for flower seedling transplanting was obtained.Compared with similar designs,the trajectory displacement of the proposed mechanism is larger in the condition of smaller link size,which indicates that the mechanism can effectively decrease the machine size.The real-time controllable motor angular acceleration fluctuation is smaller and the commutation times are less,which has the advantage of reducing the difficulty of the mechanism control system.Subsequently,the correctness of the design method is verified by kinematics simulation.Finally,the synchronous linkage motion control methods of the two motors were designed,a transplanting experiment of the prototype was carried out,the picking success rate had reached 90%-93.4%and transplanting success rate was 80.5%-86.9%during experiment,which showed that the integrated operation of picking and planting flower seedlings can be realized by the proposed mechanism.
基金The authors acknowledge that this work was financially supported by the National Natural Science Foundation of China(Grant No.32071909,51975536)the Key Research Projects of Zhejiang Province(Grant No.2022C02002,2021C02021)+2 种基金the Basic Public Welfare Research Projects of Zhejiang Province(Grant No.LGN20E050006)the Shanghai Science and technology agricultural Development Project(2021 No 4-1)the General Project of Agriculture and Social Development in Hangzhou(Grant No.20201203B92).
文摘In view of the problems of the existing mechanisms based on 2R open-chain planetary gear train for seedling transplanting,such as the bad tracking flexibility,low positioning accuracy,and high structure design difficulties of the mechanisms based on 3R open-chain planetary gear train for seedling manipulation.In this paper,a transplanting mechanism based on the solution domain synthesis of a 3R open-chain-based complete rotation kinematic pair,a gear train with a single cycle integral rotating pair,is designed.The Burmester curve equation is derived from the given transplanting trajectory and four exact poses corresponding to each other on the rotation center.Then,the open-chain road model of the 3R complete rotation kinematic pair is obtained under the constraint governed by the judgment condition of the hinge integral rotating pair.Meanwhile,combined with our developed in-house optimization software,the solution to the optimal parameters for the transplanting mechanism can be optimized according to the target trajectory.Finally,the feasibility of the design method is verified by transplanting testing,where kale seedlings with ages of about 20 d and heights of about 80-120 mm are used.The experimental results show that the actual motion trajectory of the prototype is basically identical to the theoretical trajectory,validating the feasibility of transplanting mechanism design,parts processing,and test-bed construction.Through the statistical analysis,the average success rate of transplanting is 90.625%,and the reliability of designed mechanism is satisfied.This study provides a promising solution for the seedling transplanting of two-planet scaffold pots.
基金This work was financially supported by the National Key Research and Development Program of China(Grant No.2017YFD0700800)the National Natural Science Foundation of China(Grant No.32071909,No.51775512)+1 种基金Basic public welfare research projects of Zhejiang Province(Grant No.LGN19E050002,No.LGN20E050006)Fundamental Research Funds of Zhejiang Sci-Tech University(Grant No.2020Q013).
文摘At present,there is a lack of miniaturized and highly reliable plug seedling transplanting mechanism in flowerpots planting operation,in order to meet the needs of large displacement and high vertical uprightness for flower transplanting,the paper combined the transmission characteristics of the non-circular gear planetary gear train with the swing flexibility of the cam gear and proposed a double planet carrier planetary gear transplanting mechanism.The linkage of the mechanism performs variable speed rotation relative to the first planet carrier,the linkage serves as the second planet carrier,and the transplanting arm performs variable speed swing relative to the linkage.A mathematical model of a single planetary carrier mechanism was first established using the method of open linkage group solution domain synthesis,then established the kinematic equations of the second planet carrier and the transplanting arm.The two parts are combined to form the mathematical solution model of the proposed mechanism.The initial trajectory was planned according to the trajectory requirements of seedlings planting operation,the non-circular gear pitch curve in the first planet carrier was obtained and the length of the first planet carrier is 120 mm.Then using the key points’angular deviation between the initial trajectory and the improved trajectory to obtain the cam parameters which driving the transplant arm,consequently determined the length of the second planet carrier is 69.25 mm and the length of the transplant arm is 112.4 mm.Finally,the prototype of the mechanism was manufactured,and the test verified the correctness of the design method of the double planet carrier planetary gear flower potting transplanting mechanism.The transplanting success rate of this mechanism reached 94.43%,and the plug seedlings planted in flowerpots had high uprightness.This research can provide a reference for the automatic development of research on flower transplanting machines.
基金financially supported by the Key Research Projects of Zhejiang Province(Grant No.2022C02042,2022C02002)the National Key Research and Development Program of China(Grant No.2022YFD2001803)+2 种基金the National Natural Science Foundation of China(Grant No.32071909)the Shanghai Science and Technology Agricultural Development Project 2021(No.4-1)the General Project of Agriculture and Social Development in Hangzhou(Grant No.202203B08).
文摘In order to improve the adaptability of the planting mechanism for different plant spacings,a variable differential gear train planting mechanism based on precise pose and trajectory control was proposed by combining the open chain 2R rod group and the variable differential gear train.According to the pose requirements of receiving seedling point,transporting seedling point and planting point,three precise pose points of constrained planting trajectory were determined.Through the three-position motion generation structural synthesis method,combined with computer-aided optimization design software,a set of mechanism parameters that meet the planting requirements were optimized.Based on the optimized mechanism parameters,by only changing the coordinates of two trajectory shape control points,three planting trajectories with key point position information adapted to 300 mm,400 mm and 500 mm plant spacing were obtained by interpolation,and three pairs of total transmission ratio of three groups of variable differential gear trains were calculated.When distributing the total transmission ratio of the mechanism,the fixed axis gear train and the differential gear train are combined.The fixed axis gear train included a pair of non-circular gear pairs and a pair of positive gear pairs,which were convenient for disassembly and assembly.The former drives the sun gear at variable speed,and the latter drives the planet carrier at uniform speed.Based on this structure,the transmission ratio of the positive gear pair is-1,and the transmission ratio of the differential gear train is 0.5.The sub-transmission ratio of the single-stage non-circular gear pair was calculated and the pitch curves of three pairs of noncircular gears were solved.Three pairs of non-circular gear pairs with different transmission ratios were replaced in turn and three sets of planting mechanisms were modeled in three dimensions.The virtual prototype motion simulation was completed by ADAMS software,and the physical prototype was built for vegetable pot seedling planting test.The theoretical solution was consistent with the attitude and trajectory of the actual test.When the test sample size was 100 plants,the actual average plant spacing was measured to be 303 mm,402 mm,and 503 mm,with errors of 1.3%,1.25%,and 1.88%.The width of the moving hole was 72 mm,70 mm,and 71 mm,and the planting success rate were 94%,96%,and 95%.The test results verified the correctness of the optimization design results of the mechanism,indicating that the variable differential gear train planting mechanism can adapt to a variety of plant spacing and has good planting effect.
基金supported by the National Natural Science Foundation of China(Grant Nos.51975536 and U23A20175)the China Agriculture Research System of MOF and MARA.The authors also acknowledge American Journal Experts for their language assistance during the preparation of this article.
文摘In this study,the motion characteristics of manual stirring were analyzed to achieve the goal of realizing a highquality mechanized imitation of manual stirring for oolong tea.A test bench for collecting the motion characteristics of manual stirring was designed,and the standard manual stirring motion characteristic curve was obtained.According to the requirements of the stirring motion characteristics,a variable-speed and variable-amplitude stirring mechanism was proposed,the kinematics model and reverse design model of the stirring mechanism were established,auxiliary analysis and design software were written,and the non-circular gear pitch curve and cam profile curve were obtained.A three-dimensional model of the stirring machine was established,a virtual prototype of the stirring machine was built,and the simulation experiment was completed by using the ADAMS software.A prototype of the stirring machine was developed,and the stirring experiment was conducted on the prototype.The maximum deviation of the pitch angle is 2.8772°,and the maximum deviation of the roll angle is 1.5948°according to the analysis and comparison of the actual curve data and the theoretical data curve.The experimental results showed that the simulation angle curve and the actual angle curve were consistent with the theoretical standard manual stirring motion characteristic curve,which verified the correctness of the design and modeling of the stirring mechanism.The tea was mechanically stirred by the stirring mechanism to achieve the desired stirring effect,which verified the feasibility of the stirring machine.
基金the National Natural Science Foundation of China(Grants No.U23A20175No.52305289)+1 种基金“Pioneer”and“Leading Goose”R&D Program of Zhejiang(Grant No.2022C02052)China Agriculture Research System of MOF and MARA and Basic.
文摘In China,tea products made from fresh leaves characterized by one leaf with one bud(1L1B)are classified as“Famous Tea”,which has better taste and higher economic value,but suffers from a labor shortage.Aiming at picking automation,existing studies focus on visual detection of 1L1B,but algorithm validation is limited to a specific variety of tea sprouting in a certain harvest season at a certain location,which limits the engineering application of developed tea picking robots working in various natural tea fields.To address this gap,a deep learning model DMT(detecting multispecies of tea)based on YOLOX-S was proposed in this paper.The DMT network takes YOLOX-S as a baseline and adds ECA-Net to the CSP Darknet and FPN of YOLOX-S.The average precision(AP),precision,and recall of DMT are 94.23%,93.39%,and 88.02%,respectively,for detecting 1L1B sprouting in spring;93.92%,93.56%,and 87.88%,respectively,for detecting 1L1Bsprouting in autumn.These experimental results are better than those of the five current object detection models.After fine-tuning the DMT network with another dataset composed of multiple tea varieties,the DMT network can detect 1L1B for different varieties of tea in multiple picking seasons.The results can promote the engineering application of picking automation of fresh tea leaves.
