Optimal energy management strategy for dual-power coupling tractor based on the adaptive control technology.

Hybrid tractors (HT) are regarded as the efficient agricultural machine due to their energy conservation performance and faster torque response to deal with load fluctuations. However, the strategy to allocate the battery and fuel energy for demand power should be discussed. In this paper, an on-line management strategy of the HT is proposed to optimize the energy consumption of engine and motor and to reduce torque ripple for power units. A new architecture for replacing power shift and continuously variable transmission technology is proposed. Then, the modified equivalent consumption minimization strategy (ECMS) is used to optimize the torque distribution in which the equivalent factor is further calculated for the real-time process. Besides, the modification of ECMS in variable working conditions can effectively analyse the torque distribution between the motor and engine. The numerical test is implemented that the effectiveness of the proposed energy strategy is validated in plowing conditions. The consequences indicated that the proposed power distribution strategy can adaptively allocate the torque demand according to the fluctuation load. Comparing with the traditional rule-based strategy, the proposed strategy can reduce 6.2% of the energy, and decrease torque ripple with the proposed tractor architecture.

Torque coordinated control of the through-the-road (TTR) 4-wheel-drive (4WD) hybrid vehicle under extreme road conditions.

Vehicular safety is of considerable significance to the intelligent development of hybrid vehicles. However, the real-time stability control or reasonable torque distribution under the extreme road conditions remain a huge challenge due to the multiple uncertain parameters and difficulties to reconcile the handling and stability performance. To address the above problems for a through-the-road (TTR) 4-wheel-drive (4WD) hybrid vehicle, this study provides a handling and stability management (HSM) approach by incorporating the offline optimization rules and on-line model predictive control (MPC). Firstly, the vehicle dynamic model with seven degrees of freedom (7-DOF) is used to offline extract torque distribution rules (Offline-ETDR), and the online MPC feedback (Online-MPCF) is utilized to compensate the extra torque requirements for the poor effect under the extreme conditions. Accordingly, the offline optimization results and online correction are fused to provide the total torque demand given the real-time road condition detection. Finally, the real vehicle test are implemented to validate the effectiveness of the proposed torque coordination strategy. In comparison to the vehicle with no torque control strategy, the proposed method significantly improves the vehicle's cornering ability while also ensuring the high stability performance.

SNAL: sensitive non-associative learning network configuration for the automatic driving strategy.

Nowadays, there is a huge gap between autonomous vehicles and mankind in terms of the decision response against some dangerous scenarios, which would has stressed the potential users out and even made them nervous. To efficiently identify the possible sensitivity scenarios, a new neural network configuration, named sensitive non-associative learning network (SNAL), is proposed. In such structure, the modulated interneurons, excited by abnormal scene stimulation for scene processing, are well processed and utilized to improve the training structure which refers to the sensitization mechanism in non-associative learning in neurobiology and the neural structure of Aplysia. When encountering the sensitivity scenes that the automatic driving agent is not good at or has not seen, the modulated interneuron facilitates the full connection layer neurons for the decision-making process, so as to change the final automatic driving strategy. In the process of constructing the model, a method to measure the similarity of the convolution feature map is proposed, which provides a new investigation tool for the properties of convolution networks after the feature extraction. Based on the Morris-Lecar equation in neurobiology, the dynamic model of modulating interneurons in the network is constructed. The automatic control optimization of the model is carried out by imitating the biological properties. The optimization method provides a reference for introducing neurobiological mechanism into deep learning and automatic control. To validate the effectiveness of the proposed method, the simulation test are executed and the existing methods are compared accordingly. The results show that the proposed SNAL algorithm can effectively recognize the sensitivity mechanism. Furthermore, compared with the existing algorithms, such as CNN, LSTM, ViT, the proposed algorithm can make better defensive strategies for potentially dangerous scenes rarely seen or not seen in the training stage. This sensitivity mechanism is more in line with the human driving intuition when dealing with abnormal driving scenes, and makes the decision more interpretable, significantly improving the traffic ability of autonomous vehicles under the sensitive scenes. In addition, this configuration can be easily combined with the existing mainstream neural network models and has good expansibility.