Brassica rapa, commonly known as the rapeseed plant, is globally recognized for its nutrient-rich composition and oil-packed seeds, earning its distinction as a substantial oil-seed crop. The seed quality, particularly the germination rate, is instrumental in guaranteeing a high-yield rapeseed crop. Given this, the accurate, quantitative determination and selection of germination rates in seed batches prior to sowing is of paramount importance. However, conventional germination tests, employed to determine the average germination rate of seed batches, are marred by substantial time and cost inefficiencies. This study proposes the use of near-infrared spectral analysis as a proficient, non-invasive approach for assessing germination rates in rapeseed seed batches. The research involved artificial aging of seeds procured from a variety of rapeseed strains, resulting in 228 batches with a broad germination rate spectrum of 15.73% to 99.13%. We recorded near-infrared diffuse reflectance spectra and applied a range of strategies for spectral data preprocessing and feature variable selection. Furthermore, we leveraged support vector regression (SVR) modeling to augment the detection methodology. SVR training and detection were conducted using MATLAB, with selected feature wavelengths undergoing rigorous scrutiny and discussion. The results indicated that employing Savitzky–Golay convolution smoothing for spectral preprocessing, along with Synergy interval Partial Least Squares (SiPLS) in conjunction with Random Frog (RF) for the selection of 50 feature wavelength points, yielded optimal germination rate prediction performance within the SVR model. The coefficients of determination (R²c) for the training set and (R²p) for the testing set were observed to be 0.8559 and 0.8386, respectively, while the Root Mean Square Errors of Calibration (RMSEC) and Prediction (RMSEP) were calculated to be 13.76% and 17.04%. The mechanism of detecting seed vigor through near-infrared spectroscopy was analyzed based on joint variable screening and sensitive variable traceability. Consequently, the SG–SiPLS–RF–SVR model demonstrates its effectiveness in predicting the average germination rate of seed batches, offering a rapid, non-invasive detection method that can be universally applied to various rapeseed strains, thus significantly improving seed production efficiency.

The complex terrain environment in the hilly land directly affects the operational reliability of agricultural robots. In order to study the impact of road irregularity on walking chassis vibration, the 3SYLZ-750 remote-controlled weeding machine which is applied to orchards was taken as the object of study, and the rear roller was selected as the object of observation to reveal the rules under which the vibration of the track chassis changes as there is a sudden change in road surface elevation. A column-type test-to-pass method based on unit excitation was proposed in this study. The excitation behavior and action process were analyzed by category. A critical acceleration prediction model was built and verified by virtual simulation and hard road surface excitation testing. The results showed that at the forward velocity of 0-2.5 km/h and exciter height of 20-100 mm, the vertical vibration acceleration of the target roller was significantly affected by Track Contact Point Centrifugal Acceleration (TCPCA). As TCPCA increased, the change rate of vertical vibration acceleration decreased, reaching a minimum of [−13.8, 28.8]; as TCPCA decreased, the vertical vibration acceleration tended to increase positively at a maximum variation range of [−13.3, 42.2]. The measured and simulated macroscopic change rules were consistent with the theoretical analysis, further verifying the correctness of variable extraction, and providing a research basis for the accurate modification and improvement of the model. The research conclusions can lay a theoretical foundation for analyzing the walking reliability of the track chassis, and provide a design basis and technical support for the development of a tracked agricultural robot chassis for the hilly land in the future. Keywords: track system, unstructured road, vibration test, simulation analysis, hilly land, agricultural robot DOI: 10.25165/j.ijabe.20221504.7249 Citation: Li M T, Li J L, He L, He J, Hu L, Lyu C X. Analysis of the track system in bumpy unstructured hard road environment by vibration test. Int J Agric & Biol Eng, 2022; 15(4): 163–171.

Rapid and green detection of soil nutrients is essential for soil fertility and plant growth. However, traditional methods cannot meet the needs of rapid detection, and the reagents easily cause environmental pollution. Hence, we proposed a multivariable output weighting-network (MW-Net) combined with laser-induced breakdown spectroscopy (LIBS) to achieve rapid and green detection for three soil nutrients. For a better spectral signal-to-background ratio (SBR), the two important parameters of delay time and gate width were optimized. Then, the spectral noise was removed by the near-zero standard deviation method. Three common quantitative models were investigated for single-element prediction, which are usually applied in LIBS analysis. Also, multi-element prediction was investigated using MW-Net. The results showed that MW-Net outperformed other models generally with very good quantification for soil total N and K (the determination coefficients in the prediction set (R_p²) of 0.75 and 0.83 and the relative percent difference in the prediction sets (RPD) of 2.05 and 2.43) and excellent indirect determination for soil exchangeable Ca (R_p² of 0.93 and RPD of 3.91). Finally, the interpretability was realized through feature extraction from MW-Net, indicating its design rationality. The preliminary results indicated that MW-Net combined with LIBS technology could quantify the three soil nutrients simultaneously, improving the detection efficiency, and it could possibly be deployed on a LIBS portable instrument in the future for precision agriculture.