No abstract

This study develops a novel self-sensing cement composite by simply mixing reduced graphene oxide (rGO) in cementitious material. The experimental results indicate that, owing to the excellent dispersion method, the nucleation and two-dimensional morphological effect of rGO optimizes the microstructure inside cement-based material. This would increase the electric conductivity, thermal property and self-induction system of cement material, making it much easier for cementitious material to better warn about impending damage. The use of rGO can improve the electric conductivity and electric shielding property of rGO-paste by 23% and 45%. The remarkable enhancement was that the voltage change rate of 1.00 wt.%-rGO paste under six-cycle loads increased from 4% to 12.6%, with strain sensitivity up to 363.10, without compromising the mechanical properties. The maximum compressive strength of the rGO-mortar can be increased from 55 MPa to 71 MPa. In conclusion, the research findings provide an effective strategy to functionalize cement materials by mixing rGO and to achieve the stronger electric shielding property and higher-pressure sensitivity of rGO–cement composites, leading to the development of a novel high strength self-sensing cement material with a flexural strength up to 49%.

No abstract

Accurate knowledge of the vehicle states is the foundation of vehicle motion control. However, in real implementations, sensory signals are always corrupted by delays and noises. Network induced time-varying delays and measurement noises can be a hazard in the active safety of over-actuated electric vehicles (EVs). In this paper, a brain-inspired proprioceptive system based on state-of-the-art deep learning and data fusion technique is proposed to solve this problem in autonomous four-wheel actuated EVs. A deep recurrent neural network (RNN) is trained by the noisy and delayed measurement signals to make accurate predictions of the vehicle motion states. Then unscented Kalman predictor, which is the adaption of unscented Kalman filter in time-varying-delay situations, combines the predictions of the RNN and corrupted sensory signals to provide better perceptions of the locomotion. Simulations with a high-fidelity, CarSim, full-vehicle model are carried out to show the effectiveness of our RNN framework and the entire proprioceptive system. Index Terms-Deep learning (DL), four-wheel independently actuated (FWIA) autonomous electric vehicles, network-induced delays, recurrent neural networks (RNNs), unscented Kalman predictor (UKP).

For the improvement of automotive active safety and the reduction of traffic collisions, significant efforts have been made on developing a vehicle coordinated collision avoidance system. However, the majority of the current solutions can only work in simple driving conditions, and cannot be dynamically optimized as the driving experience grows. In this study, a novel self-learning control framework for coordinated collision avoidance is proposed to address these gaps. First, a dynamic decision model is designed to provide initial braking and steering control inputs based on real-time traffic information. Then, a multilayer artificial neural networks controller is developed to optimize the braking and steering control inputs. Next, a proportional–integral–derivative feedback controller is used to track the optimized control inputs. The effectiveness of the proposed self-learning control method is evaluated using hardware-in-the-loop tests in different scenarios. Experimental results indicate that the proposed method can provide good collision avoidance control effect. Furthermore, vehicle stability during the coordinated collision avoidance control can be gradually improved by the self-learning method as the driving experience grows.

No abstract

No abstract

The influence of braking on dynamic stability of a car-trailer combination (CTC) is studied in this paper. The braking is simply modeled and integrated into a single-track model (STM) with a single-axle trailer. On this basis, some fundamentals and analysis results related to system dynamic stability are given through simulation. Furthermore, it is found that the axle load transfer and braking force distribution have a great influence on system dynamic stability. In order to further analyze the influence of these two factors, both of the braking force distribution and the pitch motion are considered in the modeling. Finally, the ideal braking force distribution domain is proposed. Results can be adopted to explain the experimental phenomenon and serve as a guideline for the differential braking strategy in stability control of the CTC.