The prediction of crop yield plays a crucial role in national economic development, encompassing grain storage, processing, and grain price trends. Employing multiple sensors to acquire remote sensing data and utilizing machine learning algorithms can enable accurate, fast, and nondestructive yield prediction for maize crops. However, current research heavily relies on single-type remote sensing data and traditional machine learning methods, resulting in the limited robustness of yield prediction models. To address these limitations, this study introduces a field-scale maize yield prediction model named the convolutional neural network–attention–long short-term memory network (CNN-attention-LSTM) model, which utilizes multimodal remote sensing data collected by multispectral and light detection and ranging (LIDAR) sensors mounted on unmanned aerial vehicles (UAVs). The model incorporates meteorological data throughout the crop reproductive stages and employs the normalized difference vegetation index (NDVI), normalized difference red edge (NDRE), soil-adjusted vegetation index (SAVI), and enhanced vegetation index (EVI) for the initial part of the vegetative stage (initial part of the V period), the later part of the vegetative stage (later part of the V period), the reproductive stage (R period), and the maturity stage (M period), along with LIDAR data for Point_75–100 in the later part of the V period, Point_80–100 in the R period, and Point_50–100 in the M period, complemented by corresponding meteorological data as inputs. The resulting yield estimation demonstrates exceptional performance, with an R² value of 0.78 and an rRMSE of 8.27%. These results surpass previous research and validate the effectiveness of multimodal data in enhancing yield prediction models. Furthermore, to assess the superiority of the proposed model, four machine learning algorithms—multiple linear regression (MLR), random forest regression (RF), support vector machine (SVM), and backpropagation (BP)—are compared to the CNN-attention-LSTM model through experimental analysis. The outcomes indicate that all alternative models exhibit inferior prediction accuracy compared to the CNN-attention-LSTM model. Across the test dataset within the study area, the R² values for various nitrogen fertilizer levels consistently exceed 0.75, illustrating the robustness of the proposed model. This study introduces a novel approach for assessing maize crop yield and provides valuable insights for estimating the yield of other crops.

Given the problems of targeted variable deep application of liquid fertilizer in the field, such as low precision, inaccurate fertilization amount, and poor fertilization effect, a targeted variable fertilization control system of liquid fertilizer based on a fuzzy PID algorithm was designed in this study to realize the combination of precise variable fertilization technology and targeted deep-fertilization technology. Specifically, the fertilization equipment and adaptive fuzzy PID control strategy of targeted variable fertilization were designed first. Then, the mathematical model of the targeted variable fertilization control system of liquid fertilizer was established following the requirements of intertillage and fertilization of corn crops. Afterward, the response time and overshoot of the control system were simulated through the Simulink tool of MATLAB software, in which the fuzzy PID control and traditional PID control were compared. Then, the control effect of the targeted variable fertilization control system was verified through field experiments. The test results demonstrated that in the process of simulation analysis, the response time of the variable fertilization control system based on fuzzy PID control was shortened by nearly 5 s on average compared to the system based on traditional PID control, and the error was controlled within 10%. In the field test, the target rate of targeted variable fertilization equipment for liquid fertilizer reached more than 80%, and the control accuracy of the liquid fertilizer application amount also remained above 90%. Finally, the tracking experiment to check the fertilization effect proved that the targeted variable deep-fertilization method of liquid fertilizer could further improve the yield of maize crops under the premise of reducing the fertilization cost. The study provides a feasible solution for the method of precise variable fertilization combined with targeted fertilization.

Aiming at the common problems of the high working resistance, low soil disturbance, and high rates of missed extraction in the operation of carrot combine harvesters, a high-efficiency drag-reducing bionic soil-loosening shovel was designed in this study. The physical parameters of the soil and carrots were measured, and the bionic drag-reducing shovel was designed using the badger claw toe as a bionic prototype. The shovel wing structures were designed. Based on the EDEM discrete element simulation technology, a multi-element simulation model of the shovel–soil–carrot contact was established to determine the effects of the operating speed and sliding angle of the shovel handle on the resistance. The effects of the blade inclination angle and blade opening angle on the resistance, carrot extraction force, and soil disturbance rate were also studied. The results show that the resistance increases with an increase in operating speed. With a blade angle (α) and blade inclination angle (β) of 120.27° and 47.37°, respectively, the performance of the high-efficiency drag-reducing soil-loosening shovel is the best, with the resistance and carrot extraction force being 1908.76 N and 55.37 N, respectively. The virtual simulation experiment shows that this efficient drag-reducing shovel can effectively solve the problems of the low soil disturbance, high resistance, and high missing carrot rates of carrot combine harvester shovels, while also improving the harvesting quality and efficiency of carrot combine harvesters and meeting the agronomic requirements of carrot harvesting.

Successive years of straw mulching and returning straw to the fields in Northeast China have made strip-tillage necessary, and reasonable strip-tillage operations can create conditions for crop growth. However, there are limited research studies on the related equipment applicable to this area. In this paper, an automatic control strip-tillage machine is designed. According to the conventional planting pattern of maize in this region, the operative processes of the machine were determined, and a suitable strip seedbed structure could then be constructed under straw mulching conditions. The type of coulters and the structural parameters of the V-type soil-crushing wheel were determined through theoretical analysis. Based on the air spring and electric linear actuator, the plowing depth control system and the straw width control system were developed, respectively, so as to improve the stability of the machine operation. Field tests showed that when the forward speed, tillage depth, and theoretical width were 6–12 km/h, 6–12 cm, and 18–24 cm, respectively, the straw clearing rate, soil crushing rate, and tillage depth and breadth stability were higher than 90%, and the soil flatness was less than 2 cm. All the indexes satisfied the agronomic and technological requirements of corn cultivation. The results of this study can provide equipment and technical support for the further popularization of conservation tillage technology.

In order to solve the problem of vigorous vibration of agricultural machinery frames, taking a vegetable precision seeder as an example, the concept of vibration reduction was proposed. The modal analysis of the frame was carried out, and the accuracy of the finite element model was verified by comparing the modal test of multipoint input and multipoint output (MIMO) and simulation results. Additionally, the main frequency of engine vibration was the main excitation source of frame resonance. According to the modal shapes, it was proposed to increase the fixed beam structure and to carry out simulation tests. The time-domain signal of the maximum deformation position in the first-order vibration mode was measured, and the vibration spectrum analysis maps before and after optimization were obtained by Fourier transform. A field experiment showed that the seeding quality of the whole machine was significantly improved after optimization. This study provides a reference for the analysis of vibration characteristics and the vibration reduction design of the agricultural machinery equipment.

It is difficult to determine the coefficient of restitution accurately due to the small size, light weight, and complex influencing factors of rice grain. In the study, the experimental principle of restitution coefficient was described by the impact method, and the restitution coefficients of four typical rice varieties in Northeast China were measured. According to the orthogonal experiment, the primary and secondary factors affecting the restitution coefficient of rice grain were collision material, spring compression (initial collision velocity), moisture content, and rice variety. A single factor test was carried out for the significant factors, and the results showed that: The restitution coefficient of rice grain to a Q235 steel plate, plexiglass plate, seed plate, and rubber plate decreased in turn, and the restitution coefficient gradually decreased with the increase of spring compression (initial collision velocity), and with the increase of water content. The restitution coefficient was obtained by a bench test and simulation test, and the results were 0.429 and 0.423, respectively. The reason for the error was discussed and analyzed, which effectively verified the validity of the measurement of the restitution coefficient of small grain size. This study provides a method for the determination of the restitution coefficient of small grain, and provides a reference for the optimization design of threshing and a cleaning device of the combine harvester and high-speed precision seeder.