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.

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.

As the sheep industry rapidly moves towards modernization, digitization, and intelligence, there is a need to build breeding farms integrated with big data. By collecting individual information on sheep, precision breeding can be conducted to improve breeding efficiency, reduce costs, and promote healthy breeding practices. In this context, the accurate identification of individual sheep is essential for establishing digitized sheep farms and precision animal husbandry. Currently, scholars utilize deep learning technology to construct recognition models, learning the biological features of sheep faces to achieve accurate identification. However, existing research methods are limited to pattern recognition at the image level, leading to a lack of diversity in recognition methods. Therefore, this study focuses on the small-tailed Han sheep and develops a sheep face recognition method based on three-dimensional reconstruction technology and feature point matching, aiming to enrich the theoretical research of sheep face recognition technology. The specific recognition approach is as follows: full-angle sheep face images of experimental sheep are collected, and corresponding three-dimensional sheep face models are generated using three-dimensional reconstruction technology, further obtaining three-dimensional sheep face images from three different perspectives. Additionally, this study developed a sheep face orientation recognition algorithm called the sheep face orientation recognition algorithm (SFORA). The SFORA incorporates the ECA mechanism to further enhance recognition performance. Ultimately, the SFORA has a model size of only 5.3 MB, with accuracy and F1 score reaching 99.6% and 99.5%, respectively. During the recognition task, the SFORA is first used for sheep face orientation recognition, followed by matching the recognition image with the corresponding three-dimensional sheep face image based on the established SuperGlue feature-matching algorithm, ultimately outputting the recognition result. Experimental results indicate that when the confidence threshold is set to 0.4, SuperGlue achieves the best matching performance, with matching accuracies for the front, left, and right faces reaching 96.0%, 94.2%, and 96.3%, respectively. This study enriches the theoretical research on sheep face recognition technology and provides technical support.

The crude protein (CP) content is an important determining factor for the quality of alfalfa, and its accurate and rapid evaluation is a challenge for the industry. A model was developed by combining Fourier transform infrared spectroscopy (FTIS) and chemometric analysis. Fourier spectra were collected in the range of 4000~400 cm⁻¹. Adaptive iteratively reweighted penalized least squares (airPLS) and Savitzky–Golay (SG) were used for preprocessing the spectral data; competitive adaptive reweighted sampling (CARS) and the characteristic peaks of CP functional groups and moieties were used for feature selection; partial least squares regression (PLSR) and random forest regression (RFR) were used for quantitative prediction modelling. By comparing the combined prediction results of CP content, the predictive performance of airPLST-cars-PLSR-CV was the best, with an $R_P^2$ of 0.99 and an RMSEP of 0.053, which is suitable for establishing a small-sample prediction model. The research results show that the combination of the PLSR model can achieve an accurate prediction of the crude protein content of alfalfa forage, which can provide a reliable and effective new detection method for the crude protein content of alfalfa forage.

In this study, the wear characteristics of the die were tested and analyzed through compaction tests, and the distribution of wear depth along the direction toward the extrusion outlet was obtained. A discrete element method (DEM) model of the die’s wear process was established. The results show that the severe wear area is located near the stop position of the compression rod, forming a plow-shaped wear area along the extrusion direction, accompanied by fatigue peeling. The wear depth gradually decreases towards the extrusion outlet. The DEM model partially reveals the occurrence of the wear phenomenon, but the particle motion speed deviates from the actual situation. The maximum compression force value range during the DEM compression stage is within the actual maximum compression force value range, and the relative error range of the average maximum compression force is less than 2%. By verifying the formula to calibrate the model, the calibrated model is compared with the actual mold wear, and the predicted value is close to the actual test result. The DEM can be used to explore the wear mechanism and predict the die’s wear failure process, laying the foundation for optimizing die wear resistance design.