深度学习识别光网络单元故障的设计与应用

为解决依赖装维上门鉴别光网络单元故障带来的不便,可以从机器视觉入手实现自动化故障识别。近年,ImageNet挑战赛的成功推动了物体识别技术的跨越式发展,特别是基于卷积的深度学习技术在视觉识别方面已经达到人类水平,为光网络单元故障的自动识别提供了技术基础。文章对识别光网络单元的工作状态进行了研究,将设备工作状态分为7个场景,提出了利用手机APP采集图片识别故障的解决方案并投入了实际生产;重点阐述了深度学习模块的设计与实现,提出一种通过算法整合的方式综合运用物体检测和图像分类算法,分3阶段逐步求精,解决了图片过滤,光网络单元型号和状态识别等问题,实现了基于计算机视觉自动识别光网络单元故障。从数据上看产品的端到端准确率超过84%,识别速度达到10 FPS,月均提供服务超过1万人次,在减少用户等待的同时节约了人力资源。     

基于多元神经网络融合的分布式资源空间文本分类研究

针对实体产业对科技资源的服务需求,以服务效应作为资源文本分类标准,提出一种基于多元神经网络融合的分布式资源空间文本分类模型。设计了包含词嵌入层、卷积层、双向门控循环单元层、注意力机制层和softmax层的多元神经网络通路;在此基础上采用基于需求—效应—资源分类策略,完成了从定性科技资源需求到定量资源服务效应求解,再到定性科技资源输出的映射变换,重点解决了分布式科技资源局部和全局语义特征形式多样、文本长距离依赖特征显著、重要资源信息难以准确识别的问题,进而从分布式科技资源空间中快速准确地获取效应知识,提升实体产业产品研发效率和创新能力;通过万方专利科技资源数据集验证了所提方法的可行性和有效性,为更加全面地挖掘资源文本特征和按需服务实体产业提供了一种新的思路和手段。     

基于目标级联技术的含风电互联电网机组组合策略

针对含风电互联电网日前安全约束机组组合的规模大、约束复杂、求解困难等问题,提出基于目标级联分析技术的分散协调优化策略。将问题分解为负责区域间边界节点电压相角协调的上层优化问题和以并行方式独立优化各区域发电计划的下层优化问题。下层优化以弃风电量期望和电量不足期望,量化各区域内风电、负荷预测误差,以及常规机组强迫停运等系统运行不确定性所带来的风险,并以罚函数的形式引入目标函数,以综合优化系统可靠性与经济性。2区域12节点系统和IEEE RTS96三区域互联系统算例仿真验证所建模型和算法的有效性。     

Improved district heating network operation by the integration of high-temperature heat pumps

Biomass combined heat and power (CHP) plants connected to district heating networks are a very good opportunity to increase the share of renewable sources into energy systems. Frequently, important consumers are connected to ensure a stable base heat demand throughout the year but they often have higher requirements in terms of temperature (i.e. steam), which involves a high level of temperature in the district heating network during the whole year and high levels of heat losses in the network. This contribution presents the possibility to decrease the level of temperature at which the district heating network operates and to use high-temperature heat pumps connected locally at the consumption point to produce steam when it is required. An investigation of the global design and integration through thermodynamic simulation models is realised for the University of Liège district heating network. This study is intended to determine the heat pump coefficient of performance and, therefore, to assess the balance between the savings in terms of heat losses and the additional heat pump electricity consumption.     

A Bio‐Inspired and Biomass‐Derived Healable Photochromic Material Induced by Hierarchical Structural Design

Utilization of bionics to develop stimuli responsive polymers that can heal damage with excellent restorability is particularly attractive for a sustainable society. Herein, inspired by chameleons, a hierarchical structural design strategy is proposed and illustrated to fabricate a healable photochromic material based on a self‐healable polymeric matrix and a finely dispersed photochromic spirooxazine. The self‐healable polymeric matrix is fabricated via the integration of multiple hydrogen bonds (H bonds) and covalent cross‐links into a biomass‐derived elastomer. The dynamic nature and soft characteristics enable the as‐prepared elastomer superior extensibility as well as self‐healing ability, while the covalent cross‐links can assist the reassociation of ruptured H bonds. The representative elastomer exhibits an extensibility of 2600% and toughness of 42.76 MJ m^?3. Furthermore, it shows good self‐healing ability with complete recovery of scratch as well as restoration against 1900% of elongation and 24.1 MJ m^?3 of toughness after healing at 60 °C for 24 h. This combination of moderate toughness, good self‐healing ability, and smart photochromic property in biomass‐derived materials should largely improve their applicability, reliability, and sustainability in various materials and devices.     

[数据驱动的智能服务]数据驱动的复杂产品智能服务技术与应用

随着传感器、数据采集装置和其他具备感知能力的模块在复杂产品服务运行阶段的应用，复杂产品运维系统的数字化和智能化程度越来越高，具有实时、多源、异构、海量等特性的数据成为提高复杂产品系统可靠和低成本运行的决策依据，数字孪生技术提供了一种有效途径。介绍了数据驱动的复杂产品智能服务研究进展；分析了数据驱动的智能服务基本特征与框架模型；提出了数据驱动的复杂产品智能服务方法，主要包括面向服务的复杂产品建模与仿真方法、数据驱动的服务需求获取与精准分析预测方法、基于数字孪生的设备故障识别与动态性能预测方法、数据驱动的装备视情维修与备件库存联合多目标决策优化方法、基于数字孪生的复杂产品辅助维修技术、多要素协同的复杂装备能效精准分析预测方法、基于数据挖掘的复杂产品运行优化控制方法等；给出了智能服务系统的应用案例。所提出的框架和方法可为现代制造服务的智能化转型升级提供参考。     

Sleep Disorders Reduce Health-Related Quality of Life in Multiple Sclerosis (Nottingham Health Profile Data in Patients with Multiple Sclerosis)

Quality of Life (QoL) is decreased in multiple sclerosis (MS), but studies about the impact of sleep disorders (SD) on health-related quality of Life (HRQoL) are lacking. From our original cohort, a cross-sectional polysomnographic (PSG) study in consecutive MS patients, we retrospectively analysed the previously unpublished data of the Nottingham Health Profile (NHP). Those MS patients suffering from sleep disorders (n = 49) showed significantly lower HRQoL compared to MS patients without sleep disorders (n = 17). Subsequently, we classified the patients into four subgroups: insomnia (n = 17), restless-legs syndrome, periodic limb movement disorder and SD due to leg pain (n = 24), obstructive sleep apnea (n = 8) and patients without sleep disorder (n = 17). OSA and insomnia patients showed significantly higher NHP values and decreased HRQoL not only for the sleep subscale but also for the “energy” and “emotional” area of the NHP. In addition, OSA patients also showed increased NHP values in the “physical abilities” area. Interestingly, we did not find a correlation between the objective PSG parameters and the subjective sleep items of the NHP. However, this study demonstrates that sleep disorders can reduce HRQoL in MS patients and should be considered as an important confounder in all studies investigating HRQoL in MS.     

Using provenance to efficiently improve metadata searching performance in storage systems

In cloud storage systems, more than 50% of requests are metadata operations, and thus the file system metadata search performance has become increasingly important to different users. With the rapid growth of storage system scales in volume, traditional full-size index trees cannot offer high-performance metadata search due to hierarchical indexing bottleneck. In order to alleviate the long latency and improve the quality-of-service (QoS) in cloud storage service, we proposed a novel provenance based metadata-search system, called PROMES. The metadata search in PROMES is split into three phases: (i) leveraging correlation-aware metadata index tree to identify several files as seeds, most of which can satisfy the query requests, (ii) using the seeds to find the remaining query results via relationship graph search, (iii) continuing to refine and rerank the whole search results, and sending the final results to users. PROMES has the salient features of high query accuracy and low latency, due to files’ tight and lightweight indexing in relationship graph coming from provenance’s analysis. Compared with state-of-the-art metadata searching schemes, PROMES demonstrates its efficiency and efficacy in terms of query accuracy and response latency.     

A self‐scalable load injection service

Load testing of applications is an important and costly activity for software provider companies. Classical solutions are very difficult to set up statically, and their cost is prohibitive in terms of both human and hardware resources. Virtualized cloud computing platforms provide new opportunities for stressing an application's scalability, by providing a large range of flexible and less expensive (pay‐per‐use model) computation units. On the basis of these advantages, load testing solutions could be provided on demand in the cloud. This paper describes a Benchmark‐as‐a‐Service solution that automatically scales the load injection platform and facilitates its setup according to load profiles. Our approach is based on: (i) virtualization of the benchmarking platform to create self‐scaling injectors; (ii) online calibration to characterize the injector's capacity and impact on the benched application; and (iii) a provisioning solution to appropriately scale the load injection platform ahead of time. We also report experiments on a benchmark illustrating the benefits of this system in terms of cost and resource reductions. Copyright © 2013 John Wiley & Sons, Ltd.     

A systemic framework and analysis of urban water energy

Energy impacts of urban water systems are substantial, but not typically analysed systemically. We develop a new system boundary framework including a utility, the ‘bulk water supply authority’ (SB1); the ‘urban water system’ including water use (SB2); and the ‘regional water system’ (SB3). We use the framework to review existing models and show that most address only one boundary. We apply the framework to quantify thermal equivalents of water-related energy in SB1 and SB2, and identify that over 96% of water-related energy in South East Queensland (SEQ) is outside SB1 and within SB2. Consideration of energy influenced by water use is paramount to systemic energy efficiency and optimisation in the urban water system. Clear articulation of system boundaries will improve modelling and management of the energy impact of urban water. Systemic modelling will help decision makers answer increasingly integrated and cross-system and sector questions regarding water and energy interactions.