The classification of plug seedling quality plays an active role in enhancing the quality of seedlings. The EfficientNet-B7-CBAM model, an improved convolutional neural network (CNN) model, was proposed to improve classification efficiency and reduce high cost. To ensure that the EfficientNet-B7 model simultaneously learns crucial channel and spatial location information, the convolutional block attention module (CBAM) has been incorporated. To improve the model’s ability to generalize, a transfer learning strategy and Adam optimization algorithm were introduced. A system for image acquisition collected 8,109 images of pepper plug seedlings, and data augmentation techniques improved the resulting data set. The proposed EfficientNet-B7-CBAM model achieved an average accuracy of 97.99% on the test set, 7.32% higher than before the improvement. Under the same experimental conditions, the classification accuracy increased by 8.88–20.05% to classical network models such as AlexNet, VGG16, InceptionV3, ResNet50, and DenseNet121. The proposed method had high accuracy in the plug seedling quality classification task. It was well-adapted to numerous types of plug seedlings, providing a reference for developing a fast and accurate algorithm for plug seedling quality classification.

The accurate and rapid detection of cotton seed quality is crucial for safeguarding cotton cultivation. To increase the accuracy and efficiency of cotton seed detection, a deep learning model, which was called the improved ResNet50 (Impro-ResNet50), was used to detect cotton seed quality. First, the convolutional block attention module (CBAM) was embedded into the ResNet50 model to allow the model to learn both the vital channel information and spatial location information of the image, thereby enhancing the model’s feature extraction capability and robustness. The model’s fully connected layer was then modified to accommodate the cotton seed quality detection task. An improved LRelu-Softplus activation function was implemented to facilitate the rapid and straightforward quantification of the model training procedure. Transfer learning and the Adam optimization algorithm were used to train the model to reduce the number of parameters and accelerate the model’s convergence. Finally, 4419 images of cotton seeds were collected for training models under controlled conditions. Experimental results demonstrated that the Impro-ResNet50 model could achieve an average detection accuracy of 97.23% and process a single image in 0.11s. Compared with Squeeze-and-Excitation Networks (SE) and Coordination Attention (CA), the model’s feature extraction capability was superior. At the same time, compared with classical models such as AlexNet, VGG16, GoogLeNet, EfficientNet, and ResNet18, this model had superior detection accuracy and complexity balances. The results indicate that the Impro-ResNet50 model has a high detection accuracy and a short recognition time, which meet the requirements for accurate and rapid detection of cotton seed quality.

In view of the plugged-out end-effector that can adapt only to a specific size of the tray, the needle spacing and angle of the seedling needle are fixed. In this paper, a new type of plugged-out transplanting end-effector is proposed. The end-effector adopts a double-cam structure to automatically adjust the spacing and angle of the seedling needle, which solves the problem of picking seedlings for different sizes of trays. Firstly, the working principle of 72-hole, 128-hole, and 200-hole trays and a plugged-out end-effector was analyzed. The overall structure of the end-effector was designed. Subsequently, the EDEM software was used to construct the pot seedling model and conduct single-factor simulation experiments to identify the range of factors for the subsequent regression orthogonal experiment. Finally, a tray transplanting test platform was built. With the grasping acceleration, penetration angle, insertion depth, and insertion margin ratio as the test factors and the pot seedling breakage rate as the test evaluation indicators. A four-factor three-level orthogonal regression experiment was conducted to establish a regression model of the seedling breakage rate, and its parameters were optimized. The optimal combination is detailed as follows: a 72-hole tray grasping acceleration of 0.28 m/s2, a penetration angle of 13°, an insertion depth of 40 mm, and an insertion margin ratio of 15%; a 128-hole tray grasping acceleration of 0.28 m/s2, a penetration angle of 12°, an insertion depth of 36 mm, and an insertion margin ratio of 15%; a 200-hole tray grasping acceleration of 0.28 m/s2, a penetration angle of 11°, an insertion depth of 32 mm, and an insertion margin ratio of 10%. Under the optimal combination, the breakage rate of 72 holes reached 2.92%. The breakage rate of 128 holes was stable at 1.76%, while that of 200 holes was stable at 0.68%, which is conducive to the study of a general end-effector. The device developed in this study provides an effective solution to taking and throwing different sizes of cavitation trays, thus providing a practical reference for the study of a generic end-effector.