A computer aided design method for car form and its application based on shape parameters

In the early design stage, automotive modeling should both meet the requirements of aesthetics and engineering. Therefore, a vehicle CAD (computer aided design) model that can be easily adjusted by feedbacks is necessary. Based on CE-Bézier surface, this paper presents a set of algorithms for parametric segmentation and fairing surface generation in a car model. This model is defined by a simplified automotive template and relevant control points, shape parameters and segmentation parameters, which can be modified to alter the car form efficiently. With this model and the corresponding adjustment method, more than fifty various vehicle models are established in this research according to different parameters. And two methods for calculating similarity index between car models are constructed, which are suitable for brand design trend analysis and modelling design decisionmaking.     

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.     

除尘器新型褶式滤筒的结构优化及系列化设计

以新型褶式滤筒为研究对象,选取滤筒褶数N_2、褶夹角θ、褶高h、过滤风速v为影响因子,除尘器压力损失为响应值,基于响应曲面法分析影响因子对压力损失的影响,建立滤筒除尘器压力损失的预测模型并得到滤筒褶皱结构最优参数。以滤筒内径D、筒体高度D_1为标准尺寸,依据相关国家标准设计滤筒筒体部分;以锥体高度D_2、锥体上圆直径D_3为系列尺寸,利用尺寸变化法设计锥体部分;通过Access软件建立滤筒产品数据库。结果表明:当θ=5.2°,N_2=50,v=0.01 m/s,h=0.035 m时,除尘器压力损失最低;当D_1=1 000 mm,D=320 mm时,D_2和D_3最佳值分别为600,130 mm,故采用D_2/D_1=0.6,D_3/D=0.4的比值设计相应滤筒锥体系列。