基于案例推理的土石坝病险智能诊断系统

近年来基于案例推理已受到广泛关注，将基于案例推理技术应用到土石坝病险诊断系统中，为土石坝病险智能化诊断提供了一条新的途径。该文针对土石坝病险诊断的案例特点，设计了案例的集成框架表示和分层模糊检索策略，并提出了诊断系统的实现方案。     

智能土石方调配系统的数据库设计

智能土石方调配系统对工程数据、生产数据和地理空间数据进行数字化，存入数据库服务器，根据工程进度计划，利用动态线性规划算法，生成任意时间跨度的土石方调配方案。由于大型工程数据量巨大，影响土石方调配方案的边界条件众多，且实际施工现场数据处于动态变化之中，因此智能土石方调配系统的数据库设计的好坏，直接关系到整个土石方调配平衡方案的可信度、可操作性和运行质量。通过需求分析，设计了数据库结构，开发了智能土石方调配系统并应用到世界最高的面板坝的土石方调配方案优化分析中，数据库运行状况良好，提高了土石方调配方案的准确性和可操作性。     

混凝土坝非稳态施工过程异常监控与管理研究

为有效管控混凝土坝非稳态施工过程,针对施工过程中施工资源的时变性造成施工计划变更频繁、施工进度难以保证等问题,首先对多域施工资源进行了统一形式化描述,定义了施工任务与施工资源之间的关联约束关系,然后对施工资源异常进行分类定义并建立了单源、多源随机资源异常事件的响应机制与传播算法,开发了可管控施工资源动态变化的施工过程管理原型系统,在某水电站主体工程施工过程中进行原型应用,取得了较好效果。该方法可作为施工仿真系统的有效补充用于水电工程施工过程管理。     

基于Web的心墙堆石坝仿真系统建模与应用研究

介绍了基于Web的心墙堆石坝仿真系统。在仿真系统构成方面,分析了心墙堆石坝仿真系统四个功能模块的功能及其相互关系。仿真系统设计上,重点讨论了土石方平衡模块改进的数学模型、子系统设计和调配计算,完善了模型的约束条件。最后提出了基于SOA架构心墙堆石坝仿真系统的分层实现模式。工程实例分析说明了基于Web的心墙堆石坝仿真系统是有效的、可行的。     

基于多Agent的电力营销决策支持系统的研究

针对传统决策支持系统的局限性以及决策支持问题的复杂性,本文把Agent方法引入到决策支持系统的研究中,提出了一个新型的决策支持系统框架,设计了基于多Agent的电力营销决策支持系统。该模型中的多个Agent通过Agent解释服务通信交流,相互合作,共同完成决策支持任务,充分的发挥了Agent的自主性、反应性、协作性,为电力企业的决策问题的解决提供了一个新的途径。     

Intelligent analysis method of dam material gradation for asphalt-core rock-fill dam based on enhanced Cascade Mask R-CNN and GCNet

Reasonable dam materials’ gradation design for asphalt-core rock-fill dams is one of the main ways to control permeability. It is a challenge to test whether it can meet the requirements of dam construction. The computer vision method provides a new idea for asphalt-core rock-fill dam material gradation testing. However, due to the characteristics of densely overlapping and multi-scale sizes of dam material particles, the traditional image segmentation methods and algorithms cannot achieve accurate segmentation of dam materials’ images, and it is hard to apply the segmentation result to quantify the gradation curve. In this research, the enhanced Cascade Mask R-CNN with ResNet and PAFPN (Path Aggregation Feature Pyramid Networks) is proposed. Multi-scale features extracted by ResNet and feature ensemble can be realized using PAFPN. Data augmentation (DA) and online hard example mining (OHEM) are also applied in segmentation model training. Moreover, the GCNet is proposed to calibrate the gradation curve. The nonlinear relationship between the real gradation and the one based on the segmentation results can be revealed and the model of dam materials’ gradation analysis can be established. In the research, the enhanced Cascade Mask R-CNN can achieve 84.2 mAP, which is higher than that of Cascade Mask R-CNN with 74.9 mAP. The effectiveness of the proposed module and training strategies is proved using ablation experiments. The average error of each level for the gradation calibration using GCNet is 0.55%, 1.87%, 2.22%, 1.18%, and 2.42% respectively. The accuracy can meet the requirements of hydraulic engineering construction, which verifies the effectiveness of the GCNet network for gradation calibration, and the research provides a new method and technology for intelligent gradation testing of the asphalt-core rock-fill dam.     

Knowledge integration using problem spaces: A study in resource-constrained project scheduling

The need to develop schedules for projects with resource constraints and cash flows arises in organizational settings ranging from construction planning to research and development. Given the intractable nature of the problem, a variety of knowledge sources relevant to the project scheduling task have been identified in the Operations Management literature. These include a large number of heuristic procedures that can be used to generate feasible project schedules as well as recent neural network-based approaches that can select appropriate heuristic procedures to apply to a specific instance of the project scheduling problem. While integrated application of these knowledge sources is required to effectively support scheduling, previous work has focussed on developing and implementing them in isolation. The problem space computational model presented in this paper addresses this shortcoming by integrating these various knowledge sources, thus enabling the development of decision support systems for resource constrained project scheduling. More generally, the modeling approach used in this paper can be applied to create systems to assist knowledge intensive tasks that arise in many organizational settings.     

A new methodology for Decisions in Medical Informatics using fuzzy cognitive maps based on fuzzy rule-extraction techniques

In this research work, a novel framework for the construction of augmented Fuzzy Cognitive Maps based on Fuzzy Rule-Extraction methods for decisions in medical informatics is investigated. Specifically, the issue of designing augmented Fuzzy Cognitive Maps combining knowledge from experts and knowledge from data in the form of fuzzy rules generated from rule-based knowledge discovery methods is explored. Fuzzy cognitive maps are knowledge-based techniques which combine elements of fuzzy logic and neural networks and work as artificial cognitive networks. The knowledge extraction methods used in this study extract the available knowledge from data in the form of fuzzy rules and insert them into the FCM, contributing to the development of a dynamic decision support system. The fuzzy rules, which derived by these extraction algorithms (such as fuzzy decision trees, association rule-based methods and neuro-fuzzy methods) are implemented to restructure the FCM model, producing new weights into the FCM model, that initially structured by experts. Concluding, our scope is to present a new methodology through a framework for decision making tasks using the soft computing technique of FCMs based on knowledge extraction methods. A well known medical decision making problem pertaining to the problem of radiotherapy treatment planning selection is presented to illustrate the application of the proposed framework and its functioning.     

基于多图卷积神经网络和注意力机制的学术新星预测方法

从学术新人中发掘出有潜力的学术新星能够为人才引进、项目评审和专家库构建等任务提供决策支持,具有重要的研究意义与应用价值,因此受到学术界的广泛关注。然而现有的学术新星预测方法并没有将学者的合作关系和个体属性信息进行有机结合,导致准确率低下。为解决上述问题,提出了一种基于多图卷积神经网络与注意力机制的学术新星预测方法MGCNA。综合考虑了合作网络与相似网络,基于2种网络使用图卷积神经网络学习作者的特征表示,再利用注意力机制进行信息融合,从而预测潜力较高的学术新星。最后在来自ArnetMiner平台的真实数据集上进行了实验,实验结果表明了MGCNA在预测学术新星任务上的有效性。     

A comparison of two methods for reducing take-off delay at London Heathrow airport

This paper describes recent research into the departure process at London Heathrow, with the primary motivation of reducing the amount of fuel used, improving both the economic and environmental costs. Two proposals are considered here. The first proposal considers the practicality and potential benefits of aiding the controller in improving the take-off sequencing. The second proposal aims to absorb some of the inevitable delay for aircraft at the stands, before the engines are started, but also involves a take-off sequencing aspect. Models for the two take-off sequencing problems are presented in this paper, the second of which includes an additional pushback time (or TSAT) allocation sub-problem which has to be solved subsequently. These models have distinctive differences from the models for the take-off and arrival sequencing problems which are usually considered in the literature, since they take into account necessary constraints imposed due to the control problem (whether a sequence can actually be achieved, and how) in each case. As discussed in this paper, the control problem cannot be ignored by the controllers at Heathrow, and so it cannot be ignored by any realistic system to aid them in their tasks. Comparative take-off sequencing results are presented for the two systems, and the potential benefits from providing decision support to the runway controllers or improved TSAT allocation at the stands are considered. The paper ends with some overall conclusions from the research, showing the large potential benefits of these systems. The TSAT allocation system which is discussed in this paper has been developed for implementation at London Heathrow as one element of a major project which focuses upon collaborative decision making.     

柏叶口水库面板堆石坝变形数值分析

为了解柏叶口面板堆石坝变形规律,通过单元尺寸和曲率因子优化及多步逐级加载模拟大坝施工加载过程,应用COMSOL Multiphysics软件获取大坝竣工期、正常蓄水位、设计及校核洪水位4种工况下的,河床处180、左岸60及右岸245等断面的典型剖面的变形,结合某混凝土面板堆石坝工程,考虑分级加载的情况下,仿真模拟大坝填筑、混凝土面板浇筑过程,分析混凝土面板堆石坝的变形特性。研究结果表明本工程施工速度快对大坝整体变形规律改变不大,可为下一步预警指标的拟定提供参考。     

An integrated expert system/operations research approach for the optimization of natural gas pipeline operations

This paper reports on a project, conducted jointly between SaskEnergy/Transgas and the University of Regina, which aims at developing an integrated decision support system for the optimization of natural gas pipeline operations. In this integrated approach, both expert systems and operations research techniques are used to model the operations of the gas pipelines. The decision support system can perform the tasks of (1) determining the state of the line pack of the pipelines and recommending the control commands to be issued, (2) determining the associated horsepower requirement, and (3) determining the specific compressor unit to be turned on or off. The first two tasks are performed by an expert system, and the third by a fuzzy programming model. The expert system has been developed on G2 and validated using a simulation program.     

Modelling rhetorical legal “logic”—a double syllogism

This paper looks at legal reasoning from the point of view of the work of the lawyer, rather than the law itself. In the case of Common Law systems, this means a more flexible view of how tasks are divided between the humans and the computer system, with an emphasis on decision support rather than complete automation. A process-based model of the lawyer's work is proposed in the form of a double syllogism, which displays an aesthetically pleasing symmetry, but also a significant asymmetry in the role played by perceived precedents. This arises from the use of inductive, rather than deductive, reasoning. The potential complications arising from the issue of the perception of precedents are discussed in depth.The double-syllogism model is then considered in the light of CommonKADS terminology and models. It is suggested that decision support systems using knowledge-based techniques, as required to support lawyers working under Common Law jurisdiction, raise a stronger form of the interaction problem that is well known in knowledge-based systems. This means that such systems are not well catered for in the existing CommonKADS Organisational, Agent, Task and Communication Models. The double-syllogism model is suggested as a supplement to CommonKADS in the development of such systems, at least until a more generic addition is available.     

一种基于交流成本的全球软件任务调度方法*

在全球软件开发中,由于时区、地理位置、文化和语言等各种因素,交流和协作变得非常困难,如果在进行任务调度的时候不考虑交流对整个项目所造成的影响,则有可能使整个项目开发的总成本增加,从而给项目带来很大的风险。通过采用基于交流成本的任务调度方法,在项目初期就考虑交流风险,并对任务进行调度,从而能有效减少该风险对项目可能造成的损失。通过一个示例项目将该方法与传统的基于阶段的方法进行对比,说明了交流成本对整个项目成本的确有很重要的影响,并且使用基于交流成本的任务调度方法能有效降低项目开发的总成本。     

Extraction of decision alternatives in construction management projects: Application and adaptation of NSGA-II and MOPSO

The time-cost trade-off problem is a known bi-objective problem in the field of project management. Recently, a new parameter, the quality of the project has been added to previously considered time and cost parameters. The main specification of the time-cost trade-off problem is discretization of the decision space to limited and accountable decision variables. In this situation the efficiency of the traditional methods decrease and applying of the evolutionary algorithms is necessary. In this paper, two evolutionary algorithms that originally search the decision space in a continuous manner including: (1) multi-objective particle swarm optimization (MOPSO) and (2) nondominated sorting genetic algorithm (NSGA)-II, are considered as the optimization tools to solve two construction project management problems. These problems are both in discrete domain including two or tree objectives, separately. In this regard, some procedures has been suggested and then applied to adopt both algorithms capable in solving the problems in a discrete domain. Results show the advantages and effectiveness of the used procedures in reporting the optimal Pareto for the optimization problems. Moreover, the NSGA-II is more successful in determining optimal alternatives in both time-cost trade-off (TCTO) and time-cost-quality trade-off (TCQTO) problems than the MOPSO algorithm.     

An Internet of Things-enabled BIM platform for modular integrated construction: A case study in Hong Kong

In recent years, Building Information Modelling (BIM) has been acting an important role in the delivery of Modular Integrated Construction (MiC) project. However, the full potential of BIM to MiC project cannot be realized without accurate information collection, timely information exchange, and automatic decision support throughout the project life cycle. In order to fulfil such requirements, this paper aims to develop an Internet of Things-enabled BIM platform (IBIMP) for the MiC project. A real-life project located in Hong Kong were deeply explored for developing the platform. The IBIMP consists of smart construction objects (SCOs) equipped with smart trinity tag (STT) and GPS sensor, smart gateway system, data source management service, location-based service, rule-based progress control service, as well as decision support services for prefabrication production, transportation, and on-site assembly processes. With the combination of advanced Internet of Things (IoT) technology and BIM technology, the barriers that hamper the possible functions of BIM can be overcame. By using application scenarios of a subsided sale flats MiC project in Hong Kong as examples, this study demonstrates how problems encountered by independent stakeholders such as inconvenient data collection, lack of automatic decision support, and incomplete information can be addressed by the IBIMP.     

多项目多任务选择计划模型及其智能决策

针对多项目多任务选择计划及项目流程调度问题,综合考虑项目的权重、承继约束、各项目内部任务的时序约束及各种资源在使用上存在着先后顺序等特点,将项目层、任务层及资源利用统筹考虑,结合多层决策的思想,建立项目、任务、资源统筹兼顾的混合规划模型。依据免疫系统中克隆选择、细胞克隆、记忆细胞获取、亲和突变等机制,设计求解此模型的免疫克隆选择算法。数值实验结果说明了该模型设计的合理性及算法的有效性。     

Scheduling dependent tasks on identical machines using a novel heuristic criterion: A robotic computation example

The problem of schedulingn dependent tasks, with arbitrary processing times, onm identical machines so as to minimize the makespan criterion is considered. Since this problem is NP-hard in the strong sense, it can be solved only suboptimally using heuristic approaches. Two new heuristic algorithms (dispatching rules), namely MVT/MISF and DMVT/MISF algorithms, for this problem are proposed. These algorithms are then used, together with the existing ones CP/MISF and DHLF/MISF, as a dispatching rule base of a new adaptively weighted combinatorial dispatching (AWCD) rule. This combinatorial dispatching rule has a superior behaviour compared to simple dispatching rules. Extended experimentation with these algorithms supports this argument. Here a representative robotic dynamics computation example is included. In addition, some empirical rules are derived and proposed for the selection of a simple dispatching rule (heuristic) if such a selection is required, for each particular input data set. These methods, as well as the existing optimal algorithms for special solvable cases of the considered problem, have been integrated in a decision support system (DSS).     

An implementation of inference in temporal branching time models

Issues concerning the implementation of temporal reasoning (inference) for models based on branching time logic as applied to intelligent decision support systems are considered. The focus is on the construction of a qualitative (interval) and quantitative (metric) branching time model. The inference is reduced to solving the temporal constraint satisfaction problem, and the corresponding procedures (algorithms) are proposed. An example of the practical application of the proposed techniques in a prototype of a real-time intelligent decision support system is described.     

Preference-Based Constrained Optimization with CP-Nets

Many artificial intelligence (AI) tasks, such as product configuration, decision support, and the construction of autonomous agents, involve a process of constrained optimization, that is, optimization of behavior or choices subject to given constraints. In this paper we present an approach for constrained optimization based on a set of hard constraints and a preference ordering represented using a CP-network—a graphical model for representing qualitative preference information. This approach offers both pragmatic and computational advantages. First, it provides a convenient and intuitive tool for specifying the problem, and in particular, the decision maker's preferences. Second, it admits an algorithm for finding the most preferred feasible (Pareto-optimal) outcomes that has the following anytime property: the set of preferred feasible outcomes are enumerated without backtracking. In particular, the first feasible solution generated by this algorithm is Pareto optimal.