With the application of new energy technology, hybrid agricultural machinery has been developed. This article designs a hybrid tractor energy management method to solve the problem of high energy consumption caused by significant load fluctuation of the tractor in field operation. This article first analyzes the characteristics of the hydrogen fuel cell, power battery, and ultracapacitor and designs a hybrid energy system for the tractor. Second, the energy management strategy (EMS) of multi-layer decoupling control based on the Haar wavelet and logic rule is designed to realize the multi-layer decoupling of high-frequency, low-frequency, and steady-state signals of load demand power. Then, the EMS redistributes the decoupled power signals to each energy source. Finally, a hardware-in-loop simulation experiment was carried out through the model. The results show that, compared with single-layer control strategies such as fuzzy control and power-following control, the multi-layer control strategy can allocate the demand power more reasonably, and the efficiency of the hydrogen fuel cell is the highest. The average efficiency of the hydrogen fuel cell was increased by 2.87% and 1.2%, respectively. Furthermore, the equivalent hydrogen consumption of the tractor was reduced by 17.06% and 5.41%, respectively, within the experimental cycle. It is shown that the multi-layer control strategy considering power fluctuation can improve the vehicle economy based on meeting the power demanded by the whole vehicle load.

Multi-objective optimization design of the transmission system parameters of a dual-motor-driven electric tractor based on improved deep deterministic policy gradient algorithm

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.