Accurate identification of individual animals plays a pivotal role in enhancing animal welfare and optimising farm production. Although Radio Frequency Identification technology has been widely applied in animal identification, this method still exhibits several limitations that make it difficult to meet current practical application requirements. In this study, we proposed ViT-Sheep, a sheep face recognition model based on the Vision Transformer (ViT) architecture, to facilitate precise animal management and enhance livestock welfare. Compared to Convolutional Neural Network (CNN), ViT is renowned for its competitive performance. The experimental procedure of this study consisted of three main steps. Firstly, we collected face images of 160 experimental sheep to construct the sheep face image dataset. Secondly, we developed two sets of sheep face recognition models based on CNN and ViT, respectively. To enhance the ability to learn sheep face biological features, we proposed targeted improvement strategies for the sheep face recognition model. Specifically, we introduced the LayerScale module into the encoder of the ViT-Base-16 model and employed transfer learning to improve recognition accuracy. Finally, we compared the training results of different recognition models and the ViT-Sheep model. The results demonstrated that our proposed method achieved the highest performance on the sheep face image dataset, with a recognition accuracy of 97.9%. This study demonstrates that ViT can successfully achieve sheep face recognition tasks with good robustness. Furthermore, the findings of this research will promote the practical application of artificial intelligence animal recognition technology in sheep production.

The accurate identification of sheep is crucial for breeding, behavioral research, food quality tracking, and disease prevention on modern farms. As a result of the time-consuming, expensive, and unreliable problems of traditional sheep-identification methods, relevant studies have built sheep face recognition models to recognize sheep through facial images. However, the existing sheep face recognition models face problems such as high computational costs, large model sizes, and weak practicality. In response to the above issues, this study proposes a lightweight sheep face recognition model named LSR-YOLO. Specifically, the ShuffleNetv2 module and Ghost module were used to replace the feature extraction module in the backbone and neck of YOLOv5s to reduce floating-point operations per second (FLOPs) and parameters. In addition, the coordinated attention (CA) module was introduced into the backbone to suppress non-critical information and improve the feature extraction ability of the recognition model. We collected facial images of 63 small-tailed Han sheep to construct a sheep face dataset and further evaluate the proposed method. Compared to YOLOv5s, the FLOPs and parameters of LSR-YOLO decreased by 25.5% and 33.4%, respectively. LSR-YOLO achieved the best performance on the sheep face dataset, and the mAP@0.5 reached 97.8% when the model size was only 9.5 MB. The experimental results show that LSR-YOLO has significant advantages in recognition accuracy and model size. Finally, we integrated LSR-YOLO into mobile devices and further developed a recognition system to achieve real-time recognition. The results show that LSR-YOLO is an effective method for identifying sheep. The method has high recognition accuracy and fast recognition speed, which gives it a high application value in mobile recognition and welfare breeding.

Resistance spot welding has been widely used for joining sheet metals, especially in automotive and aerospace industries. However, since the formation of weld nugget is invisible in resistance spot welding, traditionally off-line destructive test is applied for inspection of the weld quality, which is costly and inefficient. Therefore, in recent years, a lot of efforts have been made in estimating or detecting the weld quality nondestructively by on-line welding parameter monitoring. This paper presents a review on techniques of monitoring resistance spot welding process or weld quality, and the advantages as well as limitations of these techniques are discussed.

To quickly realize facial identity recognition in sheep, this paper proposes a lightweight detection algorithm based on SSD with a self-constructed dataset. Firstly, the algorithm replaces the VGG16 backbone of SSD with the lightweight neural network SqueezeNet, creating a lightweight hybrid network model. Secondly, an ECA mechanism is introduced at the front end of the pooling layer with a parameter volume of 1² × 1000 into the feature extraction network. Lastly, the smoothL1 loss function is replaced with the BalancedL1 loss function. The optimal model size has been reduced from the original SSD’s 132 MB to 35.8 MB. The average precision is 82.39%, and the mean frame rate is 66.11 frames per second. Compared to the baseline SSD model, the average precision has improved by 2.17%, the model volume has decreased by 96.2 MB, and the detection speed has increased by 7.13 frames per second. Using the same dataset on different target detection models for comparison tests, the average accuracy mean values are improved by 2.17%, 3.63%, and 1.30% compared to the SSD model, Faster R-CNN model, and Retinanet model, respectively, which substantiates a better overall performance compared to the pre-improvement model. This paper proposes an improved model that significantly reduces the model size and its computation while keeping the model performance at a high level, providing a methodological reference for the digitization of livestock farming.

In the arid grasslands of northern China, unreasonable grazing methods can reduce the water content and species numbers of grassland vegetation. This project uses solar-powered GPS collars to obtain track data for sheep grazing. In order to eliminate the trajectory data of the rest area and the drinking area, the kernel density analysis method was used to cluster the trajectory point data. At the same time, the vegetation index of the experimental area, including elevation, slope and aspect data, was obtained through satellite remote sensing images. Therefore, using trajectory data and remote sensing image data to establish a neural network model of grazing intensity of sheep, the accuracy of the model could be high. The results showed that the best input parameters of the model were the combination of vegetation index, sheep weight, duration, moving distance and ambient temperature, where the coefficient of determination $R^2=0.97$, and the mean square error MSE = 0.73. The error of grazing intensity obtained by the model is the smallest, and the spatial-temporal distribution of grazing intensity can reflect the actual situation of grazing intensity in different locations. Monitoring the grazing behavior of sheep in real time and obtaining the spatial-temporal distribution of their grazing intensity can provide a basis for scientific grazing.