On-line SVM在船舶设备故障预测中的应用

船舶设备众多、型号多样、结构复杂,故障预测所需的有效数据偏少,而大规模的在线数据监测又受制于存储空间和计算时间的限制。利用On-line SVM建立了故障预测模型,分析了船舶设备故障预测的流程;并以某船舶主机的燃油系统为例,验证了模型的准确性,认为基于On-line SVM的故障预测精度较高,解决了船舶设备故障预测中的超大样本、非线性以及高维复杂数据问题。     

复合地基上加筋土挡墙力学响应及影响因素分析

为了明确复合地基上加筋土挡墙力学行为,利用非线性分析软件ADINA建立有限元模型,建立了复合地基上的加筋土挡墙力学响应分析模型,将路面荷载与行车荷载共同等效为均布荷载。分析结果表明:复合地基上加筋土挡墙在施工期间的沉降量存在一个临界值,当填筑至某一层位后总沉降量显著下降;每一层加筋土层都会发生不均匀沉降,最上面一层最明显;水平变形最大值发生在面板中下部,随着时间的推移,墙体的变形越来越稳定,稳定后其水平变形形成鼓肚形状。对影响复合地基上加筋土挡墙竖向变形的参数如加筋间距、填土性质、地基刚度等进行了分析。结果表明,在格栅选择、面板设计、地基刚度控制、垫层模量及厚度设计等方面的合理设计可以有效减少挡墙竖向变形;同时还能减少路面的不均匀沉降。该研究对复合地基上加筋土挡墙设计与施工具有重要指导意义。     

Beneficiation of low-grade diasporic bauxite with hydrocyclone

Low-grade diasporic bauxite was treated with hydrocyclone of small cone-angle. The effects of apex diameter, feed pressure and feed concentration on separation indexes were tested, and then the separation process was discussed by hydrokinetics tentatively. The results show that the increase of apex diameter changes the spacial locality of the envelope of zero vertical velocity, resulting in decrease of the ratio of Al2O3/SiO2 in overflow and increase of the recovery of Al2O3 in underflow, while feed pressure and feed concentration have no remarkable effect on the spacial locality of the envelope of zero vertical velocity, however, the separation indexes are improved by the increase of feed pressure, but are worsened by the increase of feed concentration.     

Synergistic catalysis effect of Mn-promoted BaAl2O4 catalysts on catalytic performance for soot combustion

A series of Mn-promoted BaAl₂O₄ catalysts were developed for catalytic soot combustion. These catalysts were characterized using XRD, BET, H₂-TPR, O₂-TPD, and in-situ DRIFTS. The results showed that an optimized combustion catalyst should accommodate barium and manganese with proper balance to promote soot combustion. A synergistic mechanism was suggested to explain the synergistic effect of manganese and barium: NO was trapped mainly as nitrites by barium, while the generated nitrites further transformed to nitrates facilitated by manganese, which finally oxidized soot into CO₂.     

A model for resilient modulus determination of recycled mixes with bitumen emulsion and cement from ITS testing results

Typically, resilient modulus (M_r) of recycled mixes, containing bitumen emulsion and cement, will increase upon curing. Hence, assigning a design M_r for these mixes will be more complex than the case of conventional hot mixes. Furthermore, M_r testing facilities are not generally available in many project sites. Therefore, developing a model that could estimate M_r from ordinary testing methods would be quite appropriate. In this research, upon performing indirect tensile strength test (ITS) and determining M_r of specimens at different testing temperatures (−10, 5 and 25 °C) and curing times (7, 28 and 120 days), two models have been developed to estimate the M_r of recycled mixes with bitumen emulsion and two types of cements (type I and pozzolanic cement). The results showed that increased curing time and cement content and decreased testing temperature led to increased ITS and M_r values. For both tests the effect of temperature was more pronounced than two other parameters. The models were developed by two steps. First the relationship between ITS and M_r at similar testing conditions was determined for each cement type. This was done by a linear relationship. In the second step, the relationship was adjusted to consider the effects of temperature and curing time. Using the final model, M_r of studied mixes could be estimated from ITS testing results at similar or different testing conditions.     

基于通信网络机车分布式系统实时控制的分析与研究

针对基于通信网络的机车控制系统实时性要求及网络传输的可能影响,通过对列车通信网络(TCN)技术特点以及车载分布式控制应用要求的分析,总结了基于网络的实时控制的处理;在分析各个环节的延时成因及影响的基础上,重点对轨道车辆分布式控制系统实时性能进行了分析及研究,得出基于通信网络的实时控制系统必须考虑网络的影响,特别是传输延迟的影响,同时根据应用实践提出了改善基于通信网络的车载分布式控制系统实时性的原理及方法,并进行了测试及验证。     

Integrated optimization of multi-vehicle-type timetabling and scheduling to accommodate periodic passenger flow

A method was developed for integrating the process of multitype bus timetable generation and chains of trips formed by considering multiperiod passenger flow characteristics. First, the cumulative passenger demand curve was fitted and combined with the vehicle trajectory. Second, according to the results, the combined departure interval for multiple vehicle types was determined, and a one-way possible timetable set was established. Third, considering the departure time window, the upward and downward possible timetable sets were connected. A bi-objective mixed integer nonlinear programming model based on a spatiotemporal network was developed through two-way matching. The objective of the model was to minimize the generalized fleet cost (a problem solved by the continuous deficit function of multiple vehicle types) and passenger waiting time. For two-way matching, the computational complexity was reduced according to the postroot jump traversal rule, and the 𝑘-shortest path algorithm was used to solve the bi-objective Pareto-optimal solution set. Finally, the Harbin No. 96 bus line was used as an example to validate the proposed model and algorithm. The optimization reduced the bus purchase cost by 51.28%, energy loss cost by 31.78%, and passenger waiting time by 37.07%, indicating that the proposed model can significantly reduce the costs for bus companies and passengers.     

Unpaired image-to-image translation of structural damage

Condition assessment of civil infrastructure from manual inspections can be time consuming, subjective, and unsafe. Advances in computer vision and Deep Neural Networks (DNNs) provide methods for automating important condition assessment tasks such as damage and context identification. One critical challenge towards the training of robust and generalizable DNNs for damage identification is the difficulty in obtaining large and diverse datasets. To maximally leverage available data, researchers have investigated using synthetic images of damaged structures from Generative Adversarial Networks (GANs) for data augmentation. However, GANs are limited in the diversity of data they can produce as they are only able to interpolate between samples of damaged structures in a dataset. Unpaired image-to-image translation using Cycle Consistent Adversarial Networks (CCAN) provide one means of extending the diversity and control in generated images, but have not been investigated for applications in condition assessment. We present EIGAN, a novel CCAN architecture for generating realistic synthetic images of a damaged structure, given an image of its undamaged state. EIGAN has the capability to translate undamaged images to damaged representations and vice-versa while retaining the geometric structure of the infrastructure (e.g, building shape, layout, color, size etc). We create a new unpaired dataset of damaged and undamaged building images taken after the 2017 Puebla Earthquake. Using this dataset, we demonstrate how EIGAN is able to address shortcomings of three other established CCAN architectures specifically for damage translation with both qualitative and quantitative measures. Additionally, we introduce a new methodology to explore the latent space of EIGAN allowing for some control over the properties of the generated damage (e.g., the damage severity). The results demonstrate that unpaired image-to-image translation of undamaged to damaged structures is an effective means of data augmentation to improve network performance.     

Integration control for traffic corridors considering guidance information

The problem of designing integration traffic strategies for traffic corridors with the use of ramp metering, speed limit, and route guidance is considered in this paper. As an improvement to the previous work, the presented approach has the following five features： 1） modeling traffic flow to analyze traffic characteristics under the influence of variable speed limit, on-ramp metering and guidance information; 2） building a hierarchy model to realize the integration design of traffic control and route guidance in traffic corridors; 3） devising a multi-class analytical dynamic traffic assignment （DTA） model for traffic corridors, where not only the route choice process will be different for each user-class, but also the traffic flow operations are user-class specific because the travel time characteristic for each user-class is considered; 4） predicting route choice probabilities adaptively with real-time traffic conditions and route choice behaviors corresponding to variant users, rather than assuming as pre-determined; and 5） suggesting a numerical solution algorithm of the hierarchy model presented in this paper based on the modified algorithm of iterative optimization assignment （IOA）. Preliminary numerical test demonstrates the potential of the developed model and algorithm for integration corridor control.