There are some problems in the shifting process of hydraulic CVT, such as irregularity, low stability and high failure rate. In this paper, the BP neural network and convolutional neural network are used for fault diagnosis of the HMCVT hydraulic system. Firstly, through experiments, 120 groups of pressure and flow data under normal and four typical fault modes were obtained and preprocessed; they were divided into 80 groups of training samples and 40 groups of test samples via random extraction, using the BP neural network model and convolutional neural network model for fault classification. The results show that compared with BP, PSO-BP and other models, the fault diagnosis rate of the BAS-BP neural network model can reach 92.5%, and the average diagnosis accuracy rate of the convolutional neural network can reach 97.5%, which can be effectively applied to the fault diagnosis of the HMCVT hydraulic system and provide some reference for the shifting reliability of hydraulic CVT.

Fuel economy of multiple conditions self-adaptive tractors with hydro-mechanical CVT

A three-planetary-row linkage HMCVT scheme is designed for the operation requirements of low speed and high torque of tractors. The HM1 section adopts hydraulic mechanical power to begin its operations so that the tractor can obtain a greater transmission ratio at a low speed. The HM2 and HM3 sections adopt an “equal ratio” design so that the system has a better speed-regulation performance. The clutches controlling forward and backward movements are placed on the output shaft so that the forward and backward sections have a wider speed range. The stepless speed-regulation characteristics and torque characteristics of HMCVT are analyzed, and they can meet the kinematic and dynamic requirements. The transmission ratios of the three sections are as follows: HM1 section, 14-1.85; HM2 section, 1.85-1.04; HM3 section, 1.04-0.6. The corresponding tractor speed ranges are as follows: HM1 section, 0.2–14 km/h; HM2 section, 14–26 km/h; HM3 section, 32–46 km/h. According to energy conservation, the transmission efficiency of the system is analyzed in combination with the power flow characteristics; the highest transmission efficiencies are as follows: HM1 section, 0.85; HM2 section, 0.88; HM3 section, 0.92. When the system has cycle power, the overall transmission efficiency of the system is low and is greatly affected by the change in displacement ratio; when the system does not have cycle power, the transmission efficiency is less affected by the displacement ratio.

A positioning system for ultra-wideband (UWB) electric micro-tillers suitable for complex greenhouse environments was designed as the basis for realizing unmanned micro-tillers to address the problem of the frequent safety accidents of existing micro-tillers. First, the positioning base station and tag were designed on the basis of the STM32 and DW1000 chip hardware. The real-time coordinate display of the micro-tiller in the greenhouse could also be realized with the design of the upper computer software. Then, the realization method of the positioning function, including the analysis of time difference of arrival (TDOA) and two-way ranging (TWR) positioning methods, and the selection of the best Taylor positioning algorithm through a MATLAB simulation were studied to reduce the influence of noise and measurement errors on measurement accuracy. Finally, a positioning system accuracy test was conducted. Test results revealed that the maximum positioning error of the micro-tiller positioning system is no more than 6 cm, and the average error is 4.4 cm. The optimized positioning error is reduced by 10.2 %, considering that the influence of the base station location on the accuracy. The positioning system of the greenhouse electric micro-tiller designed in this paper demonstrates a stable performance and positioning accuracy to meet the needs of greenhouse rotary tillage operations. This system has certain theoretical importance and reference value for the development of precise positioning technology for working tools in the greenhouse and the further realization of unmanned rotary tillage operations.

Mode switching torque distribution strategy of timely four-wheel driven high-gap plant protection machine

Tracked vehicles operating in hilly and mountainous agricultural environments are frequently subjected to pitch, roll, and vibration, which can introduce time-varying errors into ultra-wideband phase-difference-of-arrival (UWB-PDOA) relative localization. Aiming to improve localization accuracy under such disturbances, this study proposes a relative localization error compensation method that integrates long short-term memory (LSTM) residual learning with a residual-adaptive extended Kalman filter (RAEKF), referred to as LSTM-RAEKF. The proposed method combines UWB-PDOA measurements with inertial measurement unit information to learn disturbance-related localization residuals and adaptively compensate for relative position and theta observations before filtering. A UWB/IMU relative localization test bench was developed, and experiments were performed under static, pitch, roll, and vibration conditions. Across different fixed-point tests, the proposed method reduced the planar position RMSE and theta RMSE by 35.0–62.9% and 54.7–70.8%, respectively. Considering all experimental conditions, the position RMSE decreased from 4.00 cm to 1.81 cm, while the theta RMSE decreased from 5.64° to 2.17°, corresponding to reductions of 54.8% and 61.5%, respectively. Furthermore, LSTM-RAEKF outperformed the standard extended Kalman filter and the innovation-based adaptive estimation extended Kalman filter. Overall, these results demonstrate that LSTM-RAEKF can effectively suppress localization errors induced by attitude disturbances and provide stable relative localization information for subsequent tracked vehicle following control.