Impurity rate is one of the key performance indicators of the rice combine harvester and is also the main basis for parameter regulation. At present, the tracked rice combine harvester impurity rates cannot be monitored in real time. Due to the lack of parameter regulation basis, the harvest working parameters are set according to the operator’s experience and not adjusted during the operation, which leads to the harvest quality fluctuating greatly in a complex environment. In this paper, an impurity-detection system, including a grain-sampling device and machine vision system, was developed. Sampling device structure and impurity extraction algorithm were studied to enhance the impurity identification accuracy. To reduce the effect of impurity occlusion on visual recognition, an infusion-type sampling device was designed. The sampling device light source form was determined based on the brightness histogram analysis of a captured image under different light irradiations. The effect of sampling device structures on impurity visualization, grain distribution, and mass flow rate was investigated by the discrete element method (DEM). The impurity recognition algorithm was proposed based on Mask R-CNN, which mainly includes an impurity feature extraction network, an ROI generation network, and a target segmentation network. The test set experiment showed that the precision rate, recall rate, average precision, and comprehensive evaluation indicator of the impurity recognition model were 92.49%, 88.63%, 81.47%, and 90.52%, respectively. The conversion between impurity pixel number and its actual mass was realized according to the pixel density calibration test and impurity rate correction factor. The bench test result showed that the designed system has a good detection accuracy of 91.15~97.26% for the five varieties. The result relative error was in a range of 5.71~11.72% between the impurity-detection system and manual method in field conditions. The impurity-detection system could be applied to tracked rice combine harvesters to provide a reference for the adjustment of operating parameters.

The discrete element method (DEM) is an effective technical tool for simulating the dynamic behavior of granular materials in agricultural engineering. However, most of the agricultural materials, such as rape stems, are flexible bodies, and it is difficult to simulate their elastic-plastic characteristics such as bending and failure using the rigid discrete element model. In this research, a flexible DEM model for rape stems was developed and the related parameters were calibrated. The proposed model consists of sequentially arranged rigid units, which were bonded together by the Hertz–Mindlin bonding contact model in the EDEM. The range of the contact parameters of a rape stem was first determined by bench test. The rape stem repose angle test was carried out as an evaluation indicator for the calibration of the DEM contact parameters. The significant factors affecting the repose angle in the contact parameters were discovered using the Plackett–Burman simulation test, and the optimal combination of these parameters was determined based on the response surface simulation test. The rape stem repose angle simulation result was 26.55° with a relative error of 2.2% for the physical tests. The rape-stem flexible DEM model’s bonding parameters were calibrated based on a three-point bending physical test and a Box–Behnken simulation test. The test results show that a rape stem’s maximum damage force obtained from the constructed model was 16.76 N, and the relative error of the measured values from the physical tests was 3.5%. The flexible DEM model could demonstrate the deformation and fracture of rape stems under an external force and can be used for the simulation of harvesting processes such as cutting, conveying, and threshing.

Due to the commitment to the target of green mechanized production and precision agriculture, the operating parameters of the main functional components of a combine harvester need to be adjusted according to the feeding quantity. Therefore, feeding quantity monitoring is one of the key technologies of intelligent control for a combine harvester. In order to obtain the accurate information of feeding quantity in the harvesting operation process in real time, a monitoring system was set up to obtain the accurate information of feeding quantity in real time. The torque signal corresponding to different feeding quantity was obtained through bench calibration experiments. The signal was decomposed, noise reduced, and reconstructed through the analysis of the frequency range of the noise based on the wavelet transform. A fitting relationship between the torque and the feeding quantity was obtained. Field validation experiment results showed good consistency of the measured data and the actual quantity. This paper provides a theoretical basis and technical reference for subsequent research on intelligent control of combine harvesters.

Rape undersowing rice is an effective method to solve the problem of short crop rotation in rice-rape rotation. Applying of ground fertilizer to rape is one of the most critical aspects in this planting pattern. However, a special fertilizer spreading is required after the rice is harvested, which increases the labor intensity and the compaction of rape and soil and is also hindered by a lack of equipment to complete the harvesting and fertilizer spreading simultaneously. In response to the above issues, a centrifugal disc spreader on a tracked combine harvester for rape undersowing rice was developed. The basic parameters of the spreader were designed based on the agronomic requirements for fertilization and tracked combine harvester. Kinematic and kinetic models of fertilizer particles were developed to determine the key parameters that affect fertilizer spreading. Based on discrete element simulations, the effects of single structure and interaction of centrifugal disc spreader on fertilizer distribution pattern were investigated. The spreading range and coefficient of variation of fertilizer lateral distribution regression models were constructed, and the spreader parameters were optimized based on the regression models. The simulation results and fertilizer spreading performance were verified by bench tests. The results show that the distribution of fertilizer from simulation tests and bench tests was consistent. The coefficient of variation of fertilizer lateral distribution was 13.1% for the simulation test and 14.6% for the bench test. The error of simulation test was 10.3%, which indicates that the simulation result was reliable. The developed centrifugal disc spreader can meet the needs of fertilizer spreading for rape undersowing rice. The results serve as a theoretical basis for the design of a fertilizer spreader and provide new ways to promote accurate and efficient spreading of fertilizer.

The impurity rate is one of the core indicators for evaluating the quality of rapeseed combine harvesters. It directly affects the economic value of rapeseed. At present, the impurity rate of rapeseed combine harvesters mainly relies on manual detection during shutdown, which cannot be monitored in real time. Due to the lack of accurate real-time impurity rate data, the operation parameters of rapeseed harvesters mainly depend on the driver’s experience, which results in large fluctuations in field harvest quality. In this research, a machine vision-based method of impurity detection for rapeseed harvesters, including an image acquisition device and impurity detection algorithm, was developed. The image acquisition device is equipped with a direct-current light source, a conveyor belt, and an industrial camera for taking real-time images of rapeseed samples. Based on the color and shape characteristics of impurity and rapeseed, the detection of rapeseed and impurity was achieved. A quantitative model for the rapeseed impurity rate was constructed to calculate the real-time impurity rate of machine-harvested rapeseed accurately. The field experiment showed that the average accuracy of the detection system for the impurity rate in rapeseed was 86.36% compared with the manual detection data. The impurity detection system proposed in this paper can swiftly and effectively identify rapeseed and impurity and accurately calculate the impurity rate, which can be applied to rapeseed harvesters to provide data support for the adjustment of operating parameters.