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.

Alfalfa blocks are an important commercial roughage, and their crude protein (CP), starch, fat, neutral detergent fibre (NDF), and acid detergent fibre (ADF) contents are key indicators of nutritional quality. This study investigated Fourier-transform infrared (FTIR) spectroscopy combined with machine learning for rapid quantitative prediction of these constituents. Different spectral preprocessing strategies and variable-selection methods were compared using partial least squares regression (PLSR), random forest regression (RFR), and back-propagation (BP) neural networks. The effects of spectral preprocessing and preceding baseline correction varied among constituents, indicating that baseline correction did not uniformly improve predictive performance. Competitive adaptive reweighted sampling (CARS) reduced spectral dimensionality, and the resulting PLSR models outperformed the RFR and BP models for all five constituents in the reported comparisons, with values reported as mean ± standard deviation across 20 repeated data partitions. For CP, the PLSR model combining first-derivative Savitzky–Golay preprocessing with CARS (SG1D-CARS-PLSR) achieved a prediction-set coefficient of determination (R²) of 0.961 ± 0.021 and a residual predictive deviation (RPD) of 5.629 ± 1.245. For starch, SG1D-CARS-PLSR achieved an R² of 0.877 ± 0.023 and an RPD of 2.959 ± 0.291. For NDF, the PLSR model combining adaptive iteratively reweighted penalised least-squares baseline correction with CARS (BC-airPLS-CARS-PLSR) achieved an R² of 0.986 ± 0.006 and an RPD of 9.355 ± 1.947. For ADF, BC-airPLS-CARS-PLSR achieved an R² of 0.839 ± 0.031 and an RPD of 2.591 ± 0.287. For fat, BC-MSC-CARS-PLSR achieved an R² of 0.697 ± 0.058 and an RPD of 2.1.883 ± 0.164, and did not deliver the expected stable prediction performance as predefined. These findings highlight the importance of constituent-specific preprocessing and variable selection and demonstrate that the optimised FTIR-based models provide a rapid for estimating the five constituents from a single spectrum, with an analysis time considerably shorter than that of the reference wet-chemistry methods.