A grafting machine is a kind of machine that can quickly graft scion to rootstock instead of manual grafting. Currently, an inclined inserted grafting machine uses the mechanical clamping method, which can easily damage the rootstock seedlings due to its high stiffness, thus, reducing the success rate of grafting. This study proposed an effective, flexible clamping device for grafting. The suction hole diameter (HD), the negative pressure (NP), and the surface inclination angle (IA) of the clamping device were studied via a single factor experiment to obtain optimal parameter ranges. Optimal HD, NP, and IA were 2–3 mm, 4–8 kPa, and 10–20°, respectively. The orthogonal experiment results showed that the optimal parameter combination for maximum holding success rate was HD, 2.5 mm; NP, 6 kPa; and IA, 10°. The experimental verification was carried out using the optimal parameter combination, with a holding success rate of 98.3% and no damage. This study provides a reference for the optimal design of an inclined inserted grafting machine.

The Chinese mitten crab (Eriocheir sinensis) is a high-value seafood. Efficient quality-grading methods are needed to meet rapid increases in demand. The current grading system for crabs primarily relies on manual observations and weights; it is thus inefficient, requires large amounts of labor, is costly, and no longer meets the requirements for the market. Here, we employed computer vision techniques combined with deep learning modeling to efficiently quantify key physiological traits, such as sex identification, carapace dimensions (length and width), and fatness assessment for quality classification. To this end, a YOLOv5-seg integrated with an SE attention model was developed using 2282 RGB images and manual measurements of the physiological traits of 300 crabs. The RGB dataset was further augmented by rotating and resizing. The results revealed that the accuracy of sex recognition was 100%, and the mAP for carapace segmentation was 0.995, which was superior to YOLOv8-seg and other variants. In addition, we proposed an improved conditional factor K to evaluate the fatness of crabs and classify their quality based on fatness. The consistency between the grading method proposed in this article and manual grading was 100%. This study could aid in developing precise and non-destructive grading systems for the aquaculture and food industries.

Fish vaccination plays a vital role in the prevention of fish diseases. Inappropriate injection positions will cause a low immunization rate and even death. Currently, traditional visual algorithms have poor robustness and low accuracy due to the specificity of the placement of turbot fins in the application of automatic vaccination machines. To address this problem, we propose a new method for estimating the injection position of the turbot based on semantic segmentation. Many semantic segmentation networks were used to extract the background, fish body, pectoral fin, and caudal fin. In the subsequent step, the segmentations obtained from the best network were used for calculating body length (BL) and body width (BW). These parameters were employed for estimating the injection position. The proposed Atten-Deeplabv3+ achieved the best segmentation results for intersection over union (IoU) on the test set, with 99.3, 96.5, 85.8, and 91.7 percent for background, fish body, pectoral fin, and caudal fin, respectively. On this basis, the estimation error of the injection position was 0.2 mm–4.4 mm, which is almost within the allowable injection area. In conclusion, the devised method was able to correctly differentiate the fish body from the background and fins, meaning that the extracted area could be successfully used for the estimation of injection position.

The fragile structure of a rootstock predisposes the stem to mechanical damage during grafting. Thus, it is necessary to take into account the rootstock’s rheological properties under mechanical compression when designing a clamping mechanism. This study focused on cucurbit, a typical rootstock for watermelon grafting. Firstly, we adopted a four-element Burgers model to analyze viscoelastic behavior and deformation characteristics of the rootstock, then conducted creep tests to obtain the parameters of the viscoelastic model. Next, we developed a model for the rootstock during holding based on viscoelastic parameters, loading force and contact time. Moreover, we evaluated the effect of various loading forces and test velocities on creep deformation to reveal the least damage on the rootstock. Results showed that the influence of loading force on the creep deformation was greater than test velocity. Finally, the holding test indicated that the clamping mechanism with silicone rubber can effectively prevent the damage to the stem. Specifically, the loading force should be controlled below 4 N to reduce the associated damage. Taken together, our findings provide a theoretical basis for analyzing the holding damage mechanism during watermelon grafting.

Background: Modern aquaculture is increasingly adopting industrialized recirculating aquaculture systems, in which the stable operation of its circulating water pump is essential. Yet, given the complex working conditions, this pump is prone to malfunctioning, so its timely fault prediction and accurate diagnosis are imperative. Traditional fault detection methods rely on manual feature extraction, limiting their ability to identify complex faults, and deep learning methods suffer from unstable recognition accuracy. To address these issues, a three-class fault detection method for water pumps based on a convolutional neural network, transformer, and bidirectional gated recurrent unit (CNN-transformer-BiGRU) is proposed here. Methods: It first uses the continuous wavelet transform to convert one-dimensional vibration signals into time–frequency images for input into a CNN to extract the time-domain and frequency-domain features. Next, the transformer enhances the model’s hierarchical learning ability. Finally, the BiGRU captures the forward/backward feature information in the signal sequence. Results: The experimental results show that this method’s accuracy in fault detection is 91.43%, significantly outperforming traditional machine learning models. Using it improved the accuracy, precision, and recall by 1.86%, 1.97%, and 1.86%, respectively, relative to the convolutional neural network and long short-term memory (CNN-LSTM) model. Conclusions: Hence, the proposed model has superior performance indicators. Applying it to aquaculture systems can effectively ensure their stable operation.

Rootstock has a soft tissue that should be held carefully to avoid mechanical damage. Holding the rootstock stem is a significant factor in the grafting process, with direct consequences on the survival rate of grafting. To analyze the damage mechanism of clamping rootstock, a finite element model of the clamping mechanism was established, and different clamping velocities and silicone rubber thicknesses were then studied in this study using the finite element method (FEM). The density and elasticity modulus of the rootstock stem and silicone rubber were determined experimentally using standard methods. The results show that as the clamping velocity increased, the contact force on the rootstock stem increased, and the clamping velocity should be lower than the critical velocity to reduce the probability of damage occurrence on the stem. The increase in silicone rubber thickness would decrease the force on the stem, while also resulting in the instability of the rootstock clamping. A silicone rubber thickness of 4 mm was confirmed as an appropriate thickness for this device. The simulation results were compared with the experimental results, and the mean error was 7.01% within the allowable range, which indicated that the FEM simulation model was reliable.