数字孪生飞云江流域水利知识平台建设研究

为提高飞云江流域智慧管控风险能力,根据数字孪生流域知识平台建设要求,以知识图谱为技术框架,引入机器深度学习技术,融入流域预报调度业务规则、历史典型场景洪水模式和专家预报经验等知识,通过图模型可视化处理,将知识以图数据模式进行存储,建立流域业务规则库、历史场景库、专家经验库和知识图谱库。利用图计算引擎管理和驱动知识,对流域特点、水利对象关联关系、业务规则等水利知识,进行挖掘提炼、归类组合、智慧管理和集成应用,构建基于水利知识图谱的数字孪生流域知识平台。数字孪生飞云江流域水利知识平台具有智能匹配、智慧推荐、全景推演等特点,可支撑流域防洪“四预”业务,提升流域风险与调度决策全流程数字化、智慧化、精准化水平,为其他水利知识平台建设提供经验借鉴。     

数字孪生甬江流域水资源“四预”应用研究

基于当前数字孪生流域发展背景及宁波市水资源利用特点，为满足宁波市水资源在不同时空下合理分配的需求，以甬江流域水资源管理与调配“四预”流程为切入点，深度融合数字孪生、BIM 建模等现代化信息技术，在建立来水预报分析、需水预测、水资源优化调配、水资源实时分析评价及水资源预警等各类模型的基础上， 构建具有“预报分析—监测预警—调配预演—调度预案—动态评价”功能的水资源管理与调配业务应用系统，以达到及时准确预报、全面精准预警、同步仿真预演、精细数字预案、多维动态评价的目标，最终实现水资源的智能优化调配与管理。     

数字孪生潭江流域先行先试建设与实践

为提高潭江流域水利工程防洪调度能力,开展数字孪生潭江流域建设。数字孪生潭江面向流域防洪调度需求,围绕“四预”核心功能,以22座大中型水库、7座梯级闸陂为精细化调度目标,建设数据底板、模型平台、业务应用等,构建流域L1级数据底板,流域重点区域及工程L2级数据底板,开发六大类水利专业模型,构建具有“四预”功能的预报调度系统平台,实现流域多源监测感知与数据高效能管理,江河水库闸坝集中管理、联合调度、科学决策,最大程度保障流域内防洪（潮）的安全,完善预报监测薄弱环节,提升工程调度反馈时效性,同时为河湖规范化管理提供依据。项目成果在2022年“龙舟水”、台风暴雨防御期间投入实战,助力潭江流域水库、水闸群的联合调度,取得防洪不受淹、水资源不浪费的最佳效益。     

韧性城市视角下的甬江流域数字孪生平台建设

针对甬江流域水灾害防御需求,结合韧性城市理论,以防洪减灾“预报、预警、预演、预案”四预体系为导向,利用数字孪生引擎的强大渲染能力,建设全要素的数字孪生流域时空底座,以水文水动力模型、空间计算技术等为重要基础支撑,围绕综合监测、洪涝预报、洪涝预演、综合调度、协同预案等业务需求构建孪生场景,实现了甬江流域数字孪生平台。实践应用表明,该平台成功抵御了甬江流域超标准洪水,并对未来防洪工程体系优化具有启示意义,对其他流域防洪减灾、城市内涝治理工作具有一定的借鉴意义。     

数字孪生乐安河助力提升小流域防洪决策支撑能力

江西省乐安河流域防汛工作具有小流域防洪的典型特征，针对小流域防洪存在的“四预”体系不完备、决策支持能力不能满足业务需要等问题，开展数字孪生乐安河流域的建设试点。将 WebGIS 引擎和游戏引擎相融合， 结合使用新型水文监测感知体系、BIM + GIS + IoT、多源数据融合等先进技术，搭建视觉真实、数据准确的三维数字孪生场景，构建未来降雨、水文预报、水工程调度、一维/二维演算等多模型耦合的流域防洪智能模拟仿真平台，实现乐安河上游暴雨集中区（婺源）洪水预报全过程的精准化模拟和预报调度一体化，为决策部门提供受灾影响范围这一关键性决策依据研究成果，对构建中小流域（县域）防洪“四预”体系，助力提升小流域（县域）防洪决策支撑能力具有示范性作用。     

数字孪生椒江防洪“四预”应用研究

针对椒江流域山区河流、平原河网、感潮河段、洪泛区均存在的水系及易受台风影响的洪涝格局,根据数字孪生流域的要求,开发了符合数字孪生标准的水利专业模型服务组件,建设了预报调度一体化系统;对模型计算所需的多源数据开发了多源数据融合平台;根据防洪“四预”业务需求开发了知识平台对调度规则、历史洪水的知识推送功能;建立了椒江流域273个子流域112条河流、2112个计算断面、84900个二维计算网格、17个控制单元的流域预报调度一体化模型,系统经过多场次台风暴雨检验,运行效率较高;对全国沿海地区防洪“四预”应用建设具有借鉴意义。     

数字孪生欧阳海灌区关键技术研究和应用

为破解灌区运行管理过程中普遍存在的水资源调配和防洪调度决策过度依赖经验、管理粗放等短板问题，为数字孪生灌区建设积累经验，本项目以欧阳海灌区渠首水库和右总干渠系为研究对象，探索实现水资源调配和防洪调度“四预”功能，通过水动力学模型和三维GIS模型共享网格技术和“需水-配水-调水”模型组合应用技术，搭建欧阳海灌区数据底板、模型库和知识库，形成数字孪生平台，开发水资源配置与调度、抗旱管理及防洪调度等系统，初步在欧阳海灌区实现水资源按需分配和精准调度。另外，该研究成果已在2022年湖南省干旱情况下保障了灌区中晚稻灌溉用水，同时也为2022年6月22日欧阳海水库发生最大入库洪峰的防洪调度提供了智能决策支撑。     

生态流量监管“四预”业务应用探索

为提高重点河湖生态流量动态监管能力，针对各地服务支撑生态流量监管业务系统与数字孪生流域建设提出的“四统一”不相适应，以及生态流量监测预警、达标判别、统计分析、流量预测、成因分析、调度方案预演、预警响应等全过程监管能力不足等问题，本文围绕业务管理需求，提出了生态流量监管总体方案以及“四预”业务应用总体架构，提出了包括数据底板、模型库、知识库等内容的数字孪生平台建设思路以及基于图数据库的生态流量预警知识图谱构建技术，提出了包括监测告警、预测预警、水量调度预演、会商服务等功能的应用系统模块建设思路，梳理了生态流量监管“四预”业务流程，可为当前数字孪生流域建设先行先试和水资源管理与调配系统中的生态流量监管业务“四预”能力建设提供参考和借鉴意义。     

北大港水库数字孪生建设方案与要点探讨

为提升北大港水库工程管理现代化与智慧化水平，结合北大港水库“数字河库”建设现状和水库扩容工程规划，提出北大港水库数字孪生建设方案，搭建数字孪生工程建设总体框架与主要内容，丰富 L2 和 L3 级数据底板， 构建模型库和知识库，实现建设期和运维期的智能应用建设。对安全监测数据底板、工程安全模型等数字孪生建设难点，以及实现“四大安全”与全过程、全要素管理等进行探讨。实现北大港水库流域防洪调度、水资源管理与调配，以及其他各项业务管理的数字化、网络化、智能化水平提升，有效推进水库运营管理数字化转型和智能化升级。     

在建大型水利工程数字孪生平台实践与思考

为整体提升在建水利工程智慧化管理能力，通过数字孪生平台建设，赋能建设期工程施工管理、运行期业务应用。在已建信息化系统的基础上，结合数字孪生水利工程建设要求和目标，构建引江济淮工程数字孪生平台总体架构。围绕数据底板、模型平台、知识平台 3 个方面，搭建真实、全面、准确的水利及水运多领域数据底板，为工程数字化映射、智能化应用提供准确的数据资源；搭建感知、预测、调度、控制、评价功能的模型平台，覆盖中长期、短期、实时多尺度调度需求，以及常规、应急多目标调度场景；搭建以方案库和专家经验库为主的知识平台，将静态、动态知识共同融入“四预”全流程；按照工程建设、运行调度、工程维护等管理业务需求，建设水资源调度、航运调度、工程安全监控等业务系统，为更加合理、有序地推进数字孪生水利工程后续建设提供思路。     

Deep learning-based extraction of construction procedural constraints from construction regulations

Construction procedural constraints are critical in facilitating effective construction procedure checking in practice and for various inspection systems. Nowadays, the manual extraction of construction procedural constraints is costly and time-consuming. The automatic extraction of construction procedural constraint knowledge (e.g., knowledge entities and interlinks/relationships between them) from regulatory documents is a key challenge. Traditionally, natural language processing is implemented using either rule-based or machine learning approaches. Limited efforts on rule-based extraction of construction regulations often rely on pre-defined vocabularies and involve heavy feature engineering. Based on characteristics of the knowledge expression of construction procedural constraints in Chinese regulations, this paper explores a hybrid deep neural network, combining the bidirectional long short-term memory (Bi-LSTM) and the conditional random field (CRF), for the automatic extraction of the qualitative construction procedural constraints. Based on the proposed deep neural network, the recognition and extraction of named entities and relations between them are realized. Unlike existing information extraction research efforts using rule-based methods, the proposed hybrid deep learning approach can be applied without complex handcrafted features engineering. Besides, the long distance dependency relationships between different entities in regulations are considered. The model implementation results demonstrate the good performance of the end-to-end deep neural network in the extraction of construction procedural constraints. This study can be considered as one of the early explorations of knowledge extraction from construction regulations.     

Measure-adaptive state-space construction

Measure-adaptive state-space construction is the process of exploiting symmetry in high-level model and performance measure specifications to automatically construct reduced state-space Markov models that support the evaluation of the performance measure. This paper describes a new reward variable specification technique, which combined with recently developed state-space construction techniques will allow us to build tools capable of measure-adaptive state-space construction. That is, these tools will automatically adapt the size of the state space to constraints derived from the system model and the user-specified reward variables. The work described in this paper extends previous work in two directions. First, standard reward variable definitions are extended to allow symmetry in the reward variable to be identified and exploited. Then, symmetric reward variables are further extended to include the set of path-based reward variables described in earlier work. In addition to the theory, several examples are introduced to demonstrate these new techniques.     

Multi-view kernel construction

In many problem domains data may come from multiple sources (or views), such as video and audio from a camera or text on and links to a web page. These multiple views of the data are often not directly comparable to one another, and thus a principled method for their integration is warranted. In this paper we develop a new algorithm to leverage information from multiple views for unsupervised clustering by constructing a custom kernel. We generate a multipartite graph (with the number of parts given by the number of views) that induces a kernel we then use for spectral clustering. Our algorithm can be seen as a generalization of co-clustering and spectral clustering and a relative of Kernel Canonical Correlation Analysis. We demonstrate the algorithm on four data sets: an illustrative artificial data set, synthetic fMRI data, voxels from an fMRI study, and a collection of web pages. Finally, we compare its performance to common alternatives.     

编译课程体系建设刍议

针对大学计算机专业编译课程教学实际,分析了编译课程在计算机人才培养过程中的重要性;通过对国内外知名高校编译课程设置的梳理以及编译技术最新进展的研究,结合国家自主安全可控计算机生态链建设的需求,提出了构建编译课程体系的初步构想。     

智慧校园建设探究

本文通过对数字校园向智慧校园转型必要性的分析,引入智慧校园的内涵,证明智慧校园是高校教育信息化发展的更高形态;针对智慧校园建设,介绍了物联网技术的三种构建方式：以RFID为媒介、以传感器为媒介、以二维条码为媒介的构建思路;最后从网络框架—移动服务—运行保障三个方面,详细阐述了基于物联网的智慧校园移动服务构建的技术承载与应用融合.     

Labour-intensive civil construction

This paper presents the results of a literature review of the ergonomics of labour-intensive civil construction. The work capacity of Asian and European workers is compared. Metabolic rates and other factors limiting productivity presented in the literature are summarised. Comparison is made with the results of productivity measurements taken in India and Indonesia. The considerable scope and need for further work in this field is outlined.     

Automating dictionary construction

Computer readable dictionaries are produced by the dictionary editor system JISYO, which takes inputs from dictionary data bases produced from type-setting tapes by the DTV (Data Translation and Verification) system of M. Nagao. Topological structuring transforms the dictionaries into thesauri with associative partial ordering by means of which denotations are computed as limits.     

Behavior-based model construction

In this paper, we review behavior-based model construction from a point of view characterized by verification, model checking, and abstraction. It turns out that abstract interpretation is the key to scaling known learning techniques for practical applications, that model checking may serve as a teaching aid in the learning process underlying the model construction, and that there are various synergies with other validation and verification techniques. We will illustrate our discussion by means of a realistic telecommunications scenario, where the underlying system has grown over the last two decades, the available system documentation consists of not much more than user manuals and protocol standards, and the revision cycle times are extremely short. In this situation, behavior-based model construction provides a sound basis, e.g., for test-suite design and maintenance, test organization, and test evaluation.