用参数自整定模型在线检测空气处理机组故障

大型现代建筑大都安装了能源管理与控制系统（EMCS）,EMCS系统储存的大量监控数据为空调系统的在线故障检测与诊断提供了方便。提出了一种利用参数自整定空调部件模型在线检测变风量空气处理机组故障的方法。利用遗传算法优化模型参数使模型预测数据与实测值数据的残差最小,因此空调部件模型有较高的预测精度。若模型预测数据与实测数据的残差超出了预先设定的阈值,就意味着变风量空气处理机组可能存在故障。针对在实际应用时确定故障检测阈值的困难,给出了用统计方法确定阈值的方法。故障检测方法在真实建筑中进行了应用和验证,结果表明该故障检测方法可以结合EMCS系统准确有效的检测变风量空气处理机组故障。     

基于切换的步进电机驱动力矩的研究

在采用切换控制的基础上,分析目前步进电机驱动存在的问题,并提出采用高低压驱动和改进型续流回路来提升步进电机输出转矩的方案,现场实验结果表明此方案输出电流小、力矩大,很好地改善了步进电机的驱动性能。     

基于协作反馈控制算法的车联网行车安全动态强化模型

针对车联网（IoV）环境下,单车的信息采集和处理能力不足以满足时间敏感的行车安全应用需求,需要通过多车协作增强车间信息共享和信道接入能力等问题,提出一种基于协作反馈控制算法的行车安全动态强化模型。首先,提出虚拟车队协作模型,提升交通信息的采集精度,扩大采集范围,建立车间的稳定协作关系,在形成协作虚拟车队的同时降低信道拥塞;然后,实现一个针对消息传输和驾驶控制的联合优化模型,通过异构交通数据的深度融合最大化IoV的安全效用;最后,在对车流量时空变化进行预测的基础上,提出自适应的反馈控制模型实时调整驾驶安全策略。仿真结果表明,所提出的行车安全动态强化模型在各种车流分布模型下,均能够取得良好的性能指标,可以有效支持驾驶辅助控制系统,在保障行车安全的同时降低信道拥塞。     

基于深度学习的Android恶意软件检测:成果与挑战

随着Android应用的广泛使用,Android恶意软件数量迅速增长,对用户的财产、隐私等造成的安全威胁越来越严重。近年来基于深度学习的Android恶意软件检测成为了当前安全领域的研究热点。该文分别从数据采集、应用特征、网络结构、效果检测4个方面,对该研究方向已有的学术成果进行了分析与总结,讨论了它们的局限性与所面临的挑战,并就该方向未来的研究重点进行了展望。     

Markov-Miml: A Markov chain-based multi-instance multi-label learning algorithm

The main aim of this paper is to propose an efficient and novel Markov chain-based multi-instance multi-label (Markov-Miml) learning algorithm to evaluate the importance of a set of labels associated with objects of multiple instances. The algorithm computes ranking of labels to indicate the importance of a set of labels to an object. Our approach is to exploit the relationships between instances and labels of objects. The rank of a class label to an object depends on (i) the affinity metric between the bag of instances of this object and the bag of instances of the other objects, and (ii) the rank of a class label of similar objects. An object, which contains a bag of instances that are highly similar to bags of instances of the other objects with a high rank of a particular class label, receives a high rank of this class label. Experimental results on benchmark data have shown that the proposed algorithm is computationally efficient and effective in label ranking for MIML data. In the comparison, we find that the classification performance of the Markov-Miml algorithm is competitive with those of the three popular MIML algorithms based on boosting, support vector machine, and regularization, but the computational time required by the proposed algorithm is less than those by the other three algorithms.     

基于GPU实现叠前时间偏移走时计算的并行算法

走时计算是叠前时间偏移计算中最耗时的部分,通过分析传统的串行走时算法,发现静态8点插值算法非常适合在GPU上运行。首先利用CUDA技术对静态8点插值算法进行并行化改造,设计静态8点并行插值算法,然后测试其正确性,统计其相对误差情况。实验表明此算法比工业生产上的动态插值算法更准确,最后我们利用体偏作性能测试。试验结果表明,运行在GPU上的静态8点并行插值算法内核性能是运行在CPU上的动态插值算法内核的22．76倍。这说明,静态8点并行插值算法适合进行走时计算,并且可以应用于工业生产上。     

计算机科学与技术专业教学内容和课程体系改革

通过分析高校计算机科学与技术专业的人才培养和教学中存在的问题,探索社会需要、适应学科发展的创新型人才培养模式．对目前该学科中课程体系和教学内容改革进行了研究,提出了相应的改革策略。     

500 m口径球面射电望远镜索网结构形态和受力分析

500m口径球面射电望远镜(Five-hundred-meter Aperture Spherical radio Telescope，FAST)是国家重大科技基础设施项目。口径500m、半径300.4m的球冠形索网是FAST反射面的主体支承结构。通过促动器的主动控制，索网可以在标准球面和不同抛物面之间转换，即索网为可主动变位的结构。针对FAST索网结构设计中由主动变位引起的形态分析和轻量化需求等问题开展研究，提出了目标位形应变补偿法，统一了球面基准态和抛物面态的形态分析方法，解决了多目标位形索网结构的形态分析问题；提出预应力优化方法，将球面基准态最大索力降低了29%；研究了索网球面基准态和抛物面态的受力性能，并与实测结果进行对比，索力吻合较好,50%以上钢索索力相对误差在5%以内。     

Water-borne conductive polyaniline doped by acidic phosphate ester containing polysilsesquioxane precursor

Acidic phosphate ester (APES) bearing polysilsesquioxane precursor was prepared employing the ring-opening reaction of (3-glycidoxypropyl)trimethoxysilane (GPTMS) with acidic phosphate monoester carrying long hydrophilic tail. Doped with APES, polyaniline emeraldine base (PANI) was successfully dissolved or dispersed in water, and a free-standing film with electrical conductivity as high as 0.05 S/cm was available. The obtained film showed water-resistance due to the confinement from inorganic networks of amorphous polysilsesquioxane characterized by ²⁹Si-MAS NMR spectrum. When the conductive film was soaked in water for 14 days, its electrical conductivity showed a little decline at the first stage of 6 days, and a considerably long platform existed at the following stage. However, for the film without polysilsesquioxane network, the electrical conductivity showed a sharp decline, and the film was broken into pieces for only 1 day soaking. Covalently linked with inorganic network of polysilsesquioxane by POC bond, thermal stability of the conductive polyaniline was also improved compared with that of the conductive hybrid film from physical blending.