城市配水管网区域改造聚类技术研究

阐述了模糊C均值(FCM)算法和马尔科夫随机场(MRF)的相关理论知识和基本框架。首先建立了基于模糊C均值的给水管网区域改造算法,它可直接应用MPR-Pipe算法得到的管网管段"重要性"值完成对管网的区域聚类;接着,建立了基于马尔科夫随机场和FCM算法的MRF-FCM区域改造算法,它同时考虑管网的拓扑信息和属性信息对管网区域聚类。根据工程实例进行算法实践,结果表明,两种算法可以得到符合实际工程应用的区域聚类,确定优先改造区域,为管网改造问题提供了切实可行的解决方案。     

供水管网DMA分区及优选分区边界管段方法研究

针对目前城市供水管网进行独立计量分区（DMA）方法不成熟、依赖经验较多的问题,提出了一种新的DMA分区方法。以分区边界管段（BPs）长度和BPs中高流量管段数量最小化为目标,定义了两节点间相似度计算公式,利用谱聚类（SC）算法完成对DMA区域的划分。在满足管网压力限制的条件下,以节点压力标准差之和、综合水龄指数和分区成本作为优化目标,建立BPs上阀门和流量计优化布置模型。使用多目标粒子群（MOPSO）算法求解该模型,得到Pareto最优解集;通过优劣解距离法（TOPSIS）进行多个布置方案的决策。将该方法应用于某实际管网进行DMA分区,结果表明,该方法可以顺利完成管网DMA分区,并在改善分区后管网水力水质性能及降低分区成本等方面起到显著作用。     

应用灰色聚类模型对给水管网水质的综合评价

灰色聚类法是灰色系统理论的一种,它以模糊数学为基础,并在此基础上有所发展、创新。灰色聚类模型的特点是对数据的分辨力高,多个评价因子的综合评价中有独到的优势。给水管网水质是多个因子的综合作用结果,不利于直观判断。因而可借助灰色聚类模型理论,确定实际的各项指标的数值与评价标准的关系,把各个因子定量的监测数据转化成综合性的结论。依靠灰色聚类理论来确定管网水质的归类以此方法来评价给水管网各个监测点的水质情况,确定管网水质的归类,最后用实例验证模型计算值与实际情况的一致性。     

基于节点高程差的DMA边界划分研究

独立计量区域(District Metered Areas,DMAs)作为管网漏损控制的最小管理单元,逐渐成为了漏损主动管理最有效的途径之一.在总结国内外关于供水管网DMA分区研究成果的基础上,文中提出了一种基于节点高程差的DMA边界划分方法,该方法引入管网节点的高程差改进相似矩阵,并使用谱聚类算法求解,改进结果在不影...     

给水系统的测点配置

提出了使给水系统可观的最小测点集的确定方法，本算法依据给水系统可观当且仅当网络中包含一梗满秩生成树。在简明扼要的描述了给水系统的可观性理论之后，对一实际给水系统如何从最初的管道铺设图是到了管网简化图，然后利用并改进图论及数据结构中关于生成树的算法，得到最小测点集进行了详细的描述。若原系统无测点利用本算法可确定出最小测点集，而当原系统中含有测点时，若此时不可观，利用本算法可判断出最大可观树，及在何处应添加测点以使整个网络可观，而原系统的测点被最大程度的利用。最后针对确定测点集常用的例子来验证了算法的有效性和正确性。     

城市给水管网系统所面临的问题及对策

分析了我国供水系统所面临的问题，指出目前采用的管网微观动态水力模型的优越性和局限性。提出了给水管网分区的新概念，即在管网微观动态模型的基础上进行给水管网分区，然后用模型指导管网的运行。阐述了适应我国国情的管网建模和管网分区方法。     

供热管网阻抗辨识观测点优化布置策略

为了提高水力模型校核精度,寻找管网阻抗辨识和管网水力模型构建的最佳观测位置,根据供热管网设计参数计算管道节点压力和流量对阻抗的相对灵敏度,利用谱系聚类算法进行分析,确定一定监测条件下所需采集的数据。以1个供热管网为例,介绍了观测点优化布置策略的实现过程。结果表明,该策略结合已有的阻抗辨识方法可以得到满意的结果。     

给水管网流量监测点优化布置的研究

在摄动分析的基础上建立了给水管网的流量敏感度方程,通过敏感度分析给出了流量监测点的优化布置方法,并通过一小型给水管网算例验证了该方法的有效性和可靠性.结果表明:该方法不仅可以找出管网中流量的最敏感点,还可以根据敏感度排序进行管网分区;按照正常用户流量确定的流量监测点仍能满足非正常情况下(用户流量发生较大变化)的流量监测.     

市政给排水设计中输水方式的选择及管网分区

输水方式的选择和管网分区的确定是当前市政给水工程中十分重要的组成部分，其不仅影响着给水工程是否能够稳定运行，同时对工程造价也有着较大的影响。在城市供水系统中，为了保证供水的持续性和稳定性，必须要对管网的水头损失以及最小服务水头等问题进行详细的分析，才能为输水管网的布置提供必要的参考，以此保证管网的投资控制在合理的范围内，充分发挥其经济效益和社会效益。基于此，本文就针对市政给水工程设计中输水方式的选择以及管网分区方案的相关问题进行简单的探讨。     

天津市供水系统分区计量管理体会

供水系统分区计量不同于一般给水系统分区供水（并联分区或串联分区），而是在供水管网上安装流量计将整个供水系统划分成若干个供水区。天津市是全国范围内较早实行供水系统分区计量的城市，以下是一些工作体域，对各区域分开管理，并为管网管理与营业管理合并进行职责的重组与再造会。     

Clustering of designers based on building information modeling event logs

A network‐enabled event log mining approach is proposed for a deep understanding of the Building Information Modeling (BIM)‐based collaborative design work. It proposes a novel algorithm termed node2vec‐GMM combining a graph embedding algorithm named node2vec and a clustering method named Gaussian mixture model (GMM) to cluster designers within a network into several subgroups, and then makes cluster analysis. Its superiority lies in the efficient feature learning ability to preserve network structure and the powerful clustering ability to tackle uncertainty and visualize results, which can directly return the cluster embedding. As a case study, a directional network with 68 nodes (designers) and 436 ties (design task transmissions) is constructed based on retrieved data from 4GB real BIM event logs. The node2vec learns and projects the network feature representation into a 128‐dimensional vector, which is learned by GMM to discover three possible clusters owning 15, 26, and 27 closely linked designers. Analysis of each cluster is performed from node importance measurement and link prediction to identify information spreading and designers’ roles within clusters. Our new algorithm node2vec‐GMM is proven to better improve clustering quality than other state‐of‐the‐art methods by at least 6.0% Adjusted Rand Index and 13.4% Adjusted Mutual Information. Overall, the designer clustering process provides managers with data‐driven support in both monitoring the whole course of the BIM‐based design and making reliable decisions to increase collaboration opportunities.     

给定测点数的管网测压点优化布置方法

介绍了一种在给定测点数时管网测压点的选取方法,根据图论法以及聚类分析中的算法编制了测压点优化选点程序,并对长江下游某市供水管网测压点进行了优化布置。分析结果表明,测压点能够较好地反映整个管网压力分布情况,该方法具有一定的应用价值。     

Book review

This paper presents a new prioritisation approach to the problem of rehabilitation of water distribution systems. It consists in a algorithm that, based on the resilience index and on the unitary power concepts, selects the most important pipes to be replaced in order to achieve two main objectives: first, to reduce loss of water due to leakage by decreasing and levelling pressures along the entire network; second, to reduce the dissipated energy in the system, making it more efficient and reliable. Additionally, the implemented algorithm finds profitable rehabilitation schemes and allows the identification of the appropriate point at which, according to the economic and hydraulic criteria established by the user, the process of replacing pipes should be stopped. This paper includes three case studies – one hypothetical and two real water distribution systems – in which the algorithm was tested. For these networks hydraulically and economically near-optimal rehabilitation schemes were achieved.     

基于改进遗传算法的给水管网优化设计

针对基于简单遗传算法的给水管网优化设计在供水安全性和经济性方面存在的不足,提出了适于管网优化设计的改进遗传算法。改进遗传算法采用罚函数技术和自适应策略,有效地解决了简单遗传算法管网优化设计中水力性能较差的问题。以典型环状给水管网为例的计算结果表明,改进遗传算法设计方案的经济性和供水安全性都优于简单遗传算法设计方案,充分说明改进遗传算法用于给水管网优化设计具有实用性和有效性。     

Reliability based optimal design of water distribution networks considering life cycle components

Water distribution systems play an important role in supplying water to consumers in a timely and efficient manner. The importance and complexity of such systems lead to extensive research in the area of optimal design of water distribution networks. Traditionally, only system costs are considered in design with few models incorporating environmental impacts. This paper presents a model for designing sustainable water distribution networks by minimising life cycle costs and life cycle CO₂ emissions, while ensuring hydraulic reliability for the life time of the system. The model integrates a multi-objective genetic algorithm with water network simulation software, EPANET. A traditional benchmark water distribution network is used to demonstrate the model. Eight scenarios have been developed to test and validate the model for a variety of objectives with different constraints. Trade-offs between life cycle costs and life cycle emissions, along with hydraulic reliability of the system are illustrated.     

Optimal joint deployment of flow and pressure sensors for leak identification in water distribution networks

ABSTRACT

A multi-objective optimization methodology is proposed herein for accurate identification of leakage in water distribution networks (WDNs) using pressure and flow sensors. We first model leakage at potential nodes using the EPANET software, and then divide WDN into near-homogenous zones using k-means clustering algorithm based on geographic distribution of nodes. Finally, flow and pressure sensors locations are optimized using the NSGA-II algorithm to identify the leakage zone accurately. Novelty of the proposed approach lies in sequential optimization of flow and pressure sensors placement, which helps improve the accuracy of leakage zone identification in WDNs. The objective functions of this study are: 1) maximizing accuracy of identified leakage zone and 2) minimizing number of sensors (and hence operational costs). Simulation results of the Mesopolis WDN corroborate the efficiency and effectiveness of the proposed approach.     

A Customized Particle Swarm Method to Solve Highway Alignment Optimization Problem

Abstract: Optimizing highway alignment requires a versatile set of cost functions and an efficient search method to achieve the best design. Because of numerous highway design considerations, this issue is classified as a constrained problem. Moreover, because of the infinite number of possible solutions for the problem and the continuous search space, highway alignment optimization is a complex problem. In this study, a customized particle swarm optimization algorithm was used to search for a near‐optimal highway alignment, which is a compound of several tangents, consisting of circular (for horizontal design) and parabolic (for vertical alignment) curves. The selected highway alignment should meet the constraints of highway design while minimizing total cost as the objective function. The model uses geographical information system (GIS) maps as an efficient and fast way to calculate right‐of‐way costs, earthwork costs, and any other spatial information and constraints that should be implemented in the design process. The efficiency of the algorithm was verified through a case study using an artificial map as the study region. Finally, we applied the algorithm to a real‐world example and the results were compared with the alignment found by traditional methods.     

Real-time rock mass condition prediction with TBM tunneling big data using a novel rock–machine mutual feedback perception method

Real-time perception of rock mass information is of great importance to efficient tunneling and hazard prevention in tunnel boring machines (TBMs). In this study, a TBM–rock mutual feedback perception method based on data mining (DM) is proposed, which takes 10 tunneling parameters related to surrounding rock conditions as input features. For implementation, first, the database of TBM tunneling parameters was established, in which 10,807 tunneling cycles from the Songhua River water conveyance tunnel were accommodated. Then, the spectral clustering (SC) algorithm based on graph theory was introduced to cluster the TBM tunneling data. According to the clustering results and rock mass boreability index, the rock mass conditions were classified into four classes, and the reasonable distribution intervals of the main tunneling parameters corresponding to each class were presented. Meanwhile, based on the deep neural network (DNN), the real-time prediction model regarding different rock conditions was established. Finally, the rationality and adaptability of the proposed method were validated via analyzing the tunneling specific energy, feature importance, and training dataset size. The proposed TBM–rock mutual feedback perception method enables the automatic identification of rock mass conditions and the dynamic adjustment of tunneling parameters during TBM driving. Furthermore, in terms of the prediction performance, the method can predict the rock mass conditions ahead of the tunnel face in real time more accurately than the traditional machine learning prediction methods.     

Comparison of chlorination and chloramination practices on microbial inactivation efficiencies within a scaled‐up water distribution network using central composite design

Disinfection practices reduce the incidence of water‐borne diseases but may result in formation of disinfection byproducts (DBPs) in raw water that are reported to be carcinogenic. Central composite design (CCD) was employed in the present study for optimization of disinfectant dose and contact time with the rationale to evaluate if an optimal balance could be achieved between minimal DBPs formation and effective microbial inactivation with either free or combined chlorine in treated water within a lab‐scale prototype network to simulate real water distribution network conditions. After a series of experimental runs based upon design of experiments (DoE) by CCD, dose was found to be the most significant factor (P < 0.01) in determining DBPs formation in both disinfectant’s applications. Where, contact time significantly (P < 0.01) affected bacterial inactivation in chlorination experiments, in contrast, dose was effective in chloramination experiments. Thus, it was concluded that the optimal balance may be achieved in the water networks with the help of multifactorial optimization when disinfectant dose was maintained near 3 mg/L as applied chlorine dose in both disinfection cases, while contact time was 62 and 155 min for chlorine and chloramine, respectively.     

Identification of the optimal entry points at District Metered Areas and implementation of pressure management

Nowadays, the implementation of pressure management in District Metered Areas (DMAs) is considered one of the most effective tools for leakage control, particularly in large networks and in systems with deteriorated infrastructures and with high pressure. The goal of the methodology proposed in this paper is to identify the optimal entry points at DMAs, determine the network needs in terms of reinforcement/replacement, and fix both the location and settings of different types of Pressure Reduction Valves (PRVs) for leakage control. This methodology is based on an optimisation model, which is solved by a Simulated Annealing algorithm, and the solutions obtained always fulfil the minimum pressure requirements for the network. The objective function comprises the total cost of the DMAs implementation and the economic benefits that can be achieved by pressure management. Finally, the results for two case studies are presented and discussed.