The yield and quality of sweet potatoes are significantly influenced by the transplantation posture of sweet potato seedlings. The performance of the sweet potato seedling transplanting opener directly affects the transplantation posture of sweet potato seedlings. In order to improve the yield and quality of sweet potatoes, this study proposes a joint simulation method based on discrete element and flexible multi body dynamics (DEM-FMBD), which optimizes the structure of a self-covering soil opener. By exploring the influence of self-covering soil trenchers on the planting depth and posture of sweet potato seedlings during horizontal transplantation, it was determined that the influencing factors of the experiment were wing spacing, soil reflux height, and soil reflux length. Based on the DEM-FMBD coupling simulation platform, single factor, and quadratic rotation orthogonal experiments were carried out. According to the results of the simulation test, the effect of the interaction of test factors on planting depth and planting attitude was analyzed by the response surface method. Finally, the optimal structural parameter combination was obtained by a multi-objective optimization method: the spacing of the wings was 58 mm, the height of the soil backflow port was 71 mm, and the length of the soil backflow port was 163 mm; thus, the quality of transplanting is improved effectively. This study provides the method and theory reference for the study of sweet potato transplanting.

Aiming to address the problems of low detection accuracy and poor stability due to the weak anti-interference ability of the bridge circuit and operational amplifier circuit, and the influence on the capacitance of the bulk density and temperature of the straw bale, an on-line detection device for the moisture content of straw bales in a square baler was developed based on the capacitance method. The device integrates a capacitance sensor, pressure sensor, and temperature sensor. The optimal structure size of the capacitor plate was determined through the simulation test of the capacitor sensor plate structure. A moisture content monitoring system based on the MATLAB language is built, and the moisture content detection model was constructed based on the backpropagation neural network (BPNN) algorithm. Finally, a test bench for a square baling machine was designed, and a performance verification test of the moisture content detection device was carried out. The simulation results of the capacitor plate show that when the length, width, and spacing of the capacitor plate are 148.6, 47.7, and 5.1 mm, respectively, the detection sensitivity of the capacitor plate is the highest. The modeling results show that the R², RMSE, and RPD of the BPNN model are 0.986, 0.008998, and 5.99, respectively, with solid data fitting ability and high prediction accuracy. The bench test results show that for the samples having moisture content between 13.1 and 28.04%, the coefficient of determination R² of the fitting curve between the predicted value of moisture content and the actual value is 0.949. The relative error range of the predicted value of moisture content is −6.51–8.66%, and the absolute error range is −1.63–1.72%. The on-line detection device for moisture content of straw bales has good accuracy and stability.

The existing methods of measuring the baler feed rate seldom consider the influence of machine vibration on the sensor signal during field operation, which leads to the low detection accuracy and poor stability of feeding quantity detection. We established a feed rate detection model of a baler based on power monitoring of the pickup platform. Through the dynamic analysis of the pickup platform, the functional relationship between the working power of the pickup platform and the feed rate was constructed. A power monitoring system of the pickup platform was developed, and the model construction experiment of the working power and the feed rate was performed. The influence mechanism of different running speeds on the torque noise signal of the power input shaft of the pickup platform was explored. The frequency of the noise signal was mainly concentrated at 0.5–6 Hz and 9–13 Hz employing a fast Fourier transform, and the noise signal was eliminated by the frequency-domain-filtering method. The function model of working power and feed rate of the pickup platform was established based on signal processing, and the determination coefficient R² of the model was 0.9796. The field experiment results show that when the feed rate of the baler is between 1.6 and 4.88 kg/s, the determination coefficient R² and RMSE between the actual and predicted feed rate are 0.989 and 0.2, respectively. The relative error range of feed-rate prediction is −9.37–8.77%, which indicates that the model has high detection accuracy and good stability and meets the requirements of feed-rate monitoring of a baler in field operation.

With the development of smart agricultural machinery technology, the application of intelligent voice technology in smart agricultural machinery is becoming increasingly widespread. As a new interactive method, intelligent voice technology can reduce operator workload, improve operational quality, and enhance operational safety in agricultural machinery. This article reviews the current state of development of intelligent voice technology in agriculture, summarizing the bottlenecks and challenges in its application within the agricultural machinery field. It further proposes a framework for intelligent voice technology in agricultural machinery and presents technical implementation plans for two typical application scenarios: intelligent control and fault diagnosis/early warning of agricultural machinery. These findings aim to provide a reference for the application of intelligent voice technology in the agricultural machinery sector. Finally, development suggestions are proposed, including building specialized voice recognition vocabularies and semantic parsing models, exploring the application of artificial intelligence in agricultural machinery voice technology, and establishing relevant technical standards for intelligent voice applications in agricultural machinery. This article provides important references and insightful ideas for the development of intelligent voice technology in the agricultural machinery field, which will facilitate the promotion and adoption of intelligent agricultural machinery technologies.

In unmanned farms, machinery transfer between fields and access to field entrances are essential prerequisites for autonomous field operations, and both require support from an accurately structured farm-road network. However, existing road data are typically maintained as vector layers and lack the topological relationships and geometric attributes needed for transfer-route and field-entrance planning. This study proposes a method for constructing farm-road topological maps from road and field vector data. The method converts road polygons into a node–edge graph containing centerline geometry, estimates road-segment widths to support the safe passage of agricultural machinery, and establishes bidirectional road–field associations based on field-access nodes. Experiments in three farm areas show that the proposed method achieves a mean symmetric centerline error of 0.094 m; width-estimation mean absolute error (MAE) and root mean square error (RMSE) of 0.032 m and 0.060 m, respectively; and a 100% success rate in 50 random path-planning tasks. The farm-road topological map constructed by this method provides spatial infrastructure for agricultural-machinery path planning and operation scheduling in unmanned farms.