To date, mechanized picking of famous tea (bud, one bud one leaf) causes a lot of damage. Manual picking results in high-quality tea but the process is inefficient. Therefore, in order to improve the quality of mechanically harvested tea buds, the study of bionic picking is beneficial to reduce the damage rate of mechanical picking. In this paper, the manual flexible picking process is studied, and a bionic bladeless mechanical picking mechanics model is developed. The relationship between the mechanical properties and structural deformation of tea stalks is obtained by microstructural observation and mechanical experimental analysis and determination of the bud bionic picking mechanics flow by combined loading tests is carried out. The results show that the key factor for low damage in tea picking is the precise flexible force applied to different parts of the shoot tip during pinching, upward, and picking. The biological force of tea stalks is closely related to the stalk diameter and maturity of stalk tissue development. The larger the xylem of the tea stalk, the stronger its resistance to bending, stretching, and deformation. The stalks at the tender end of the tea are more resilient than the lower stalks and will not break under the action of large angle bending. Additionally, the stalks at the shoot tip have significantly lower pull-off force than the stalks at other places. By simulating the manual picking process, the mechanical picking mechanical parameters were determined to be a clamping pressure of 340 kPa, bending force of 0.134 N, and pull-off force of 5.1 N. These findings help the design of low-damage pickers for famous tea and provide a reference for low-damage bionic picking of tea.
Fresh tea leaves continuously lose water after harvesting, and the level of water content directly affects the configuration of tea processing parameters. To address this problem, this study established an online detection system for the water content of fresh tea leaves after harvesting based on near-infrared spectroscopy. The online acquisition and analysis system of the temperature and humidity sensor signal data was developed based on LabVIEW and Python software platforms. Near-infrared spectral data, environmental temperature, and humidity were collected from fresh leaves after harvesting. Spectral data were combined with PLS (partial least squares) to develop a prediction model for the water content of fresh tea leaves. Simultaneously, data communication between LabVIEW and PLC was established, laying the foundation for establishing a feedback mechanism to send the prediction results to the main platform of the lower computer. This provides a more objective and accurate basis for the detection of fresh leaves before processing and regulation during processing, thereby effectively promoting the standardisation and intelligent development of tea-processing equipment.
In this study, Near-infrared (NIR) spectroscopy was adopted for the collection of 1200 spectra of three types of walnut materials after breaking the shells. A detection model of the walnut shell-kernel separation accuracy was established. The preprocessing method of de-trending (DT) was adopted. A classification model based on a support vector machine (SVM) and an extreme learning machine (ELM) was established with the principal component factor as the input variable. The effect of the penalty value (C) and kernel width (g) on the SVM model was discussed. The selection criteria of the number of hidden layer nodes (L) in the ELM model were studied, and a genetic algorithm (GA) was used to optimize the input layer weight (W) and the hidden layer threshold value (B) of the ELM. The results revealed that the classification accuracy of SVM and ELM models for the shell, kernel, and chimera was 97.78% and 97.11%. The proposed method can serve as a reference for the detection of walnut shell-kernel separation accuracy.
The sorting of machine-picked fresh tea leaves after mechanized harvesting remains a challenge because of the complex morphological characteristics and physicochemical properties of fresh tea leaves. First, the recognition results of four types of models, namely, YOLOv5, YOLOv3, Fast RCNN, and SSD, were compared. It was found that YOLOv5, with guaranteed recognition accuracy, had a recognition speed of 4.7 ms/frame (about four times that of the second ranked YOLOv3). Therefore, this study presents a novel fresh tea leaf sorting system that provides rapid and high-precision multi-channel sorting for four grades of tea leaves using a tea leaf recognition model based on the You Only Look Once (YOLOv5) deep learning model. Subsequently, a raw dataset, consisting of 6400 target images of different grades and different moisture contents, was used to evaluate three different optimization methods. Among these, the Stochastic Gradient Descent (SGD) optimization method was found to provide the best model training results with an average recognition accuracy of 98.2%. In addition, the recognition efficacy of the recognition model was found to be positively correlated with the gradient coverage of tea’s moisture content in the training set. Theoretical analysis was then conducted, along with the experimental investigation of the air-blowing force on the fresh tea leaves in the sorting process, with 30° determined to be the optimal air-blowing angle. Finally, the overall results showed that the construction of the full moisture content training set enabled a model recognition accuracy of up to 88.8%, a recall of 88.4%, a recognition speed of 4.7 ms/frame, and an overall sorting accuracy of 85.4%. This result is promising for multi-channel sorting of fresh tea leaf grades in complex situations, and as such provides a strong basis for the application of tea leaf sorting equipment.
To address the current problems of large positioning error, low picking efficiency, and high cost of tea shoot picking, a continuous and precise harvesting scheme for tea shoots based on a two-dimensional (2D) perspective is designed in this study. A high-speed harvesting method for tea shoots in a standardized tea plantation assembly line type was proposed. First, a 2D view recognition model of tea shoot tips in a multi-disturbance environment was constructed, and accurate picking point coordinates were determined by combining a skeleton algorithm and curve growth. To avoid the losses of recognition accuracy caused by the mistaken clamping of blades and vibrations during harvester operations, accurate control of the harvester was realized by combining path planning and the S-curve speed control function. The recognition accuracy for the verification set of the recognition model was 99.9%, and the mean average precision (0.5:0.95) value was 0.97. The test results show that the error between the actual picking point position and the position determined by the model was within ± 3 mm, and the picking success rate was 83.6%. Therefore, we can realize fast and accurate picking of tea shoots and lay the foundation for continuous tea picking in the future by simplifying the identification and picking process.
In the tea industry, achieving a high winnowing accuracy to produce high-quality tea is a complex challenge. The complex shape of the tea leaves and the uncertainty of the flow field lead to the difficulty in determining the wind selection parameters. The purpose of this paper was to determine the accurate wind selection parameters of tea through simulation and improve the precision of tea wind selection. This study used three-dimensional modeling to establish a high-precision simulation of dry tea sorting. The simulation environment of the tea material, flow field, and wind field wall were defined using a fluid–solid interaction method. The validity of the simulation was verified via experiments. The actual test found that the velocity and trajectory of tea particles in the actual and simulated environments were consistent. The numerical simulations identified wind speed, wind speed distribution, and wind direction as the main factors affecting the winnowing efficacy. The weight-to-area ratio was used to define the characteristics of different types of tea materials. The indices of discrete degree, drift limiting velocity, stratification height, and drag force were employed to evaluate the winnowing results. The separation of tea leaves and stems is best in the range of the wind angle of 5–25 degrees under the same wind speed. Orthogonal and single-factor experiments were conducted to analyze the influence of wind speed, wind speed distribution, and wind direction on wind sorting. The results of these experiments identified the optimal wind-sorting parameters: a wind speed of 12 m s−1, wind speed distribution of 45%, and wind direction angle of 10°. The larger the difference between the weight-to-area ratios of the tea leaves and stems, the more optimized the wind sorting. The proposed model provides a theoretical basis for the design of wind-based tea-sorting structures.