低碳时变城配送车辆路径-发车调度集成优化

针对交通拥挤环境下日益增长的城市配送需求，通过分析时序依赖对成本和碳排放的影响，引入车辆在节点等待和离散调度策略，研究基于时序依赖的低碳城市配送车辆路径与离散调度问题。为求解该问题，设计基于遗传算法与局部搜索相结合的混合进化搜索算法对模型求解，用积极的局部搜索机制替代随机的变异操作，并通过可行解构造算法、变概率交叉和多种局部搜索策略来提高算法求解质量和求解效率。通过对比仿真实验对算法和模型的有效性进行了验证。     

Effect of an abrupt change in pulling rate on microstructures of directionally solidified Al2O3-Er3Al5O12 eutectic and off-eutectic composite ceramics

Directionally solidified microstructures of Al₂O₃-Er₃Al₅O₁₂ eutectic and off-eutectic in situ composite ceramics were explored under abrupt-change pulling rate conditions. Corresponding temperature distributions and interface locations were studied. In eutectic composition, fluctuation of eutectic spacing occurred when the pulling rate increased abruptly. A gradually increase or abrupt increase in eutectic spacing was observed when the pulling rate decreased abruptly. In hypoeutectic and hypereutectic compositions, formation of the primary phases were suppressed when the pulling rate increased abruptly from 10?µm/s to 100?µm/s, while primary phases precipitated when the pulling rate decreased abruptly from 100?µm/s to 10?µm/s. The interface altitude decreased after the pulling rate increased abruptly, but increased after the pulling rate decreased abruptly. The liquid composition restriction (around the eutectic composition) at the eutectic interface plays an important role in the suppression of the primary dendrite and coupled eutectic oxides can be obtained in off-eutectic compositions even under higher solidification rate conditions.     

Catalytic Hydrocracking of a Bitumen‐Derived Asphaltene over NiMo/γ‐Al2O3 at Various Temperatures

Hydrocracking of a bitumen‐derived asphaltene over NiMo/γ‐Al₂O₃ was investigated in a microbatch reactor at varying temperatures. The molar kinetics of asphaltene cracking reaction was examined by fitting the experimental data. Below a defined temperature, the molar reaction showed the first‐order kinetic feature while at higher temperatures secondary reactions such as coke formation became significant, causing deviation of the reaction behavior from the proposed first‐order kinetic model. Selectivity analysis proved that dominant products varied from gases to liquids to gases with increasing temperature, shifting the dominant reaction from C–S bonds cleavage to C–C bonds cleavage.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.