ABSTRACT
Adaptive cruise control (ACC) enables efficient, safe, and intelligent vehicle control by autonomously adjusting speed and ensuring a safe following distance from the vehicle in front. This paper proposes a novel adaptive cruise system, namely the Safety-First Reinforcement Learning Adaptive Cruise Control (SFRL-ACC). This system aims to leverage the model-free nature and high real-time inference efficiency of Deep Reinforcement Learning (DRL) to overcome the challenges of modeling difficulties and lower computational efficiency faced by current optimization control-based ACC methods while simultaneously maintaining safety advantages and optimizing ride comfort. Firstly, we transform the ACC problem into a safe DRL formulation Constrained Markov Decision Process (CMDP) by carefully designing state, action, reward, and cost functions. Subsequently, we propose the Projected Constrained Policy Optimization (PCPO)-based ACC Algorithm SFRL-ACC, which is specifically tailored to solve the CMDP problem. PCPO incorporates safety constraints that further restrict the trust region formed by the Kullback-Leibler (KL) divergence, facilitating DRL policy updates that maximize performance while keeping safety costs within their limit bounds. Finally, we train an SFRL-ACC policy and compare its computation time, traffic efficiency, ride comfort, and safety with state-of-the-art MPC-based ACC control methods. The experimental results prove the superiority of the proposed method in the aforementioned performance aspects.
ABSTRACT
Janus membranes have attracted much attention for switchable oil/water separation because they have opposite wetting behavior on each side. However, it remains a challenge to fabricate Janus membranes with asymmetric wettability from biomass by simple methods. Herein, we prepared a flexible Janus wood (JW) membrane by cutting the natural wood along the longitudinal direction, followed by a facile top-down approach. The hydrophobic lignin was removed from the wood to prepare a highly porous and superhydrophilic wood (SW) with underwater superoleophobicity. Then, one side of the SW was sprayed with a mixture of 1H,1H,2H,2H-perfluorooctyltrichlorosilane/SiO2 nanoparticles to form a superhydrophobic surface that hardly affected the wettability of the other side. The obtained JW membrane maintains its selective wettability in harsh environments owing to its durability and stability. Furthermore, it has a switchable, high separation efficiency of >99% for both oil-in-water and water-in-oil emulsions, which can be attributed to the unique wettability and hierarchical micro/nano structure of the JW membrane. Notably, the three-dimensional interconnected micro/nanochannels (pits and nanopores) of the JW membrane are beneficial to the size-sieving effect during emulsion separation. At the same time, the layered channels (tracheids and vessels) enable multiple separations. JW membrane is sustainable, inexpensive, stable, and easy to manufacture, providing more implications for the innovation of biomass-based Janus separation materials in industrial wastewater treatment.
ABSTRACT
The main objective of this work is to analyse the influence of heat treatment with polydimethylsiloxane on integrated performance of bamboo timber. Bamboo timber was heat treated using polydimethylsiloxane as a medium at 120, 150, 180 and 210 °C for 3 h in this study. Results revealed that the equilibrium moisture content (EMC) and linear swelling ratio of heat-treated bamboo specimens was remarkable decreased with increasing heat treatment temperature. The surface contact angle of water on the bamboo specimens was observed to increase with the increasing heat treatment temperature, indicating the reduction of wettability with water. Additionally, the modulus of rupture (MOR) and modulus of elasticity (MOE) was decreased with the increasing heat treatment temperature and lower than that of untreated specimens. Cellulose crystallinity of bamboo specimens was slightly decreased with the increase of heat treatment temperature. TG-DTG results illustrated a reduction in relative content of hemicellulose, and increase in relative content of lignin and cellulose of bamboo specimens with the increase of heat treatment temperature. Presence of the stretching vibration Si-C in Si-CH3 indicated the bonding of siloxane to bamboo timber by forming covalent bonds. The colour of the heat-treated bamboo timber was even deepened after heat treatment, endowing the bamboo timber with better surface decoration performance.
ABSTRACT
OBJECTIVE: To explore the main sources causing stress among Chinese college students and its distribution. METHODS: A clustered random sampling method was conducted to perform the questionnaire on psychological stress among 2007 students selected from 13 universities. RESULTS: The main sources of psychological stress on college students regarding learning task, college environment, job-seeking, interpersonal relationship and emotional disorders. 49.3% of the population experienced mild level of psychological stress, 8.4% belonged to critical groups who experienced higher levels of stress,while 0.3% experienced severe level of stress. Sophomores and juniors were under more stressful situation than freshmen and senior students, while female students felt more stressful on learning and job-seeking than males. Male students felt more stressful caused by their families, health status, love affairs, social adaptation and frustration than females. Students from countryside were under more stress than those coming from urbans. Students from ordinary universities felt more stressed than those from famous universities and students from western areas were under more stress than those from the coastal areas. CONCLUSION: Stress had become a severe problem influencing the mental health development among college students. The problem needs to be addressed accordingly.