Search

The wheat harvesting boundary line is vital reference information for the path tracking of an autonomously driving combine harvester. However, unfavorable factors, such as a complex light environment, tree shade, weeds, and wheat stubble color interference in the field, make it challenging to identify the wheat harvest boundary line accurately and quickly. Therefore, this paper proposes a harvest boundary line recognition model for wheat harvesting based on the MV3_DeepLabV3+ network framework, which can quickly and accurately complete the identification in complex environments. The model uses the lightweight MobileNetV3_Large as the backbone network and the LeakyReLU activation function to avoid the neural death problem. Depth-separable convolution is introduced into Atrous Spatial Pyramid Pooling (ASPP) to reduce the complexity of network parameters. The cubic B-spline curve-fitting method extracts the wheat harvesting boundary line. A prototype harvester for wheat harvesting boundary recognition was built, and field tests were conducted. The test results show that the wheat harvest boundary line recognition model proposed in this paper achieves a segmentation accuracy of 98.04% for unharvested wheat regions in complex environments, with an IoU of 95.02%. When the combine harvester travels at 0~1.5 m/s, the normal speed for operation, the average processing time and pixel error for a single image are 0.15 s and 7.3 pixels, respectively. This method could achieve high recognition accuracy and fast recognition speed. This paper provides a practical reference for the autonomous harvesting operation of a combine harvester.

To solve the problems of the low driving efficiency of a fuel cell tractor power source and the high hydrogen consumption caused by the irrational power allocation of the energy source, the power system was divided into two parts, power source and energy source, and a dual-source cooperative optimization energy management strategy was proposed. Firstly, a general energy efficiency optimization method was designed for the power source composed of a traction motor and PTO motor, and the energy source was composed of a fuel cell and power battery. Secondly, the unified objective function and constraint conditions were established, and the instantaneous optimization algorithm was used to construct the weight factor. The instantaneous optimal drive efficiency energy management strategy and the instantaneous optimal equivalent hydrogen consumption energy management strategy were designed, respectively. Finally, with the demand power as the transfer parameter, the instantaneous optimal drive efficiency energy management strategy and the instantaneous optimal equivalent hydrogen consumption energy management strategy were integrated to form a dual-source collaborative optimal energy management strategy. In order to verify the effectiveness of the proposed strategy, a rule-based energy management strategy was developed as a comparison strategy and tested in an HIL test under plowing and rotary plowing conditions. The results show that the average fuel cell efficiency of the proposed strategy increased by 7.86% and 8.17%, respectively, and the proposed strategy’s equivalent hydrogen consumption decreased by 24.21% and 9.82%, respectively, compared with the comparison strategy under the two conditions. It can significantly reduce the SOC fluctuation of the power battery and extend the service life of the power battery.

Transmission efficiency is a key characteristic of Hydro-mechanical Continuously Variable Transmission (HMCVT), which is related to the performance of heavy-duty tractors. Predicting the HMCVT transmission efficiency is beneficial for the real-time adjustment of transmission ratio during heavy-duty tractor operations, so as to obtain better performance. Aiming at the problems of accurate method, low accuracy, and high noise in the prediction of HMCVT transmission efficiency, this paper proposes a method based on Variational Mode Decomposition (VMD), Particle Swarm Optimization (PSO), and Back Propagation (BP) neural networks to improve the quality of transmission efficiency prediction. Firstly, a simple theoretical model was established to obtain the influencing factors of transmission efficiency. Then, based on these factors, the transmission efficiency was tested on the bench under multiple conditions and the influence degree of each factor on transmission efficiency was divided using Partial Least Squares (PLS) method. Finally, the VMD method was used to denoise the test data, and a BP model, which was improved using the PSO method, was established to predict the processed data. The results showed that transmission efficiency of HMCVT is most affected by output speed, followed by power, and least by input speed. The VMD method can accurately extract effective signals and noise signals from the original data, and reconstruct signals, reducing the noise proportion. Using three conditions, the prediction regression accuracy of the PSO–BP model is 7.02%, 7.88%, and 9.26% higher than that of the BP model, respectively. In the three prediction experiments, the maximum differences in the MAE, the MAPE, and the RMSE of the PSO–BP model are 0.002, 0.463%, and 0.004, respectively, which are 0.006, 0.796%, and 0.003 lower than those of the BP model.

When shifting gears around a tractor’s power shift transmission, it is necessary to coordinate the control of multiple clutches and formulate a reasonable clutch engagement law to ensure the reliability and power of the power system. This paper explores the impact of different clutch engagement patterns on shifting characteristics in a power-shift tractor with multiple clutches. Shifting performance is comprehensively evaluated using indicators such as shifting time, impact degree, slip energies, and transmission output torque. The aim is to enhance the quality of power shifting, operational efficiency, and the service life of the transmission system. This paper takes the YTO TX4A transmission system as the research object, analyzes its working principle, and establishes a mathematical model of a power shift transmission system under different clutch engagement rules. This model of power shift transmission is established based on Matlab2021/Simulink and the AMESim2021 software platform. A simulation analysis is carried out for four clutches working simultaneously in a tractor’s advance gear II and lift gear III. The simulation results indicate that switching rule C is superior to switching rule A and switching rule B. Compared with the engagement scheme in which the torque exchange overlap time for both sets of clutches is 0.3 s, the scheme with a torque exchange overlap time of 0.15 s indicated a shifting time increase of 0.2 s, a slip energy increase of 4%, and a minimum output torque of the transmission increase of 2%. In the scheme with a torque exchange overlap time of 0 s, the shifting time increased by 0.15 s, the slip energy decreased by 13.5%, and the minimum output torque of the transmission decreased by 17%. Through the study of shifting performance under three different clutch engagement patterns, it is concluded that, during the shift from forward gear II to gear III in the YTO TX4A transmission system, appropriately reducing the torque exchange overlap time for both sets of clutches and avoiding simultaneous torque exchange can reduce the complexity of clutch control. This leads to smoother, more powerful, and more comfortable power shifting, effectively prolonging the service life of the transmission system.

To overcome the limitations of the hybrid tractor bumping tests, which include extended cycle times, high costs, and impracticality for single-part reliability verification, this study focuses on the exhaust system mounting bracket of a hybrid tractor. A novel approach that combines multi-objective particle swarm optimization (MOPSO) and wavelet decomposition algorithms was employed to enhance the reconstruction of shock vibration signals. This approach aims to enable the efficient acquisition of input signals for subsequent shaker table testing. The methodology involves a systematic evaluation of the spectral correlation between the original signal and the reconstructed signal at the stent’s response position, along with signal compression time. These parameters collectively constitute the objective function. The multi-objective particle swarm optimization algorithm is then deployed to explore a range of crucial parameters, including wavelet basic functions, the number of wavelet decomposition layers, and the selection of wavelet components. This exhaustive exploration identifies an optimized signal reconstruction method that accurately represents shock vibration loads. Upon rigorous screening based on our defined objectives, the optimal solution vector was determined, which includes the utilization of the dB10 wavelet basic function, employing a 12-layer wavelet decomposition, and selecting wavelet components a12 and d3~d11. This specific configuration enables the retention of 95% of the damage coefficients while significantly compressing the test time to just 46% of the original signal duration. The implications of our findings are substantial as the reconstructed signal obtained through our optimized approach can be readily applied to shaker excitation. This innovation results in a notable reduction in test cycle time and associated costs, making it particularly valuable for engineering applications, especially in tractor design and testing.