Improving surface-subsurface water budgeting using high resolution satellite imagery applied on a brownfield

The estimation of surface-subsurface water interactions is complex and highly variable in space and time. It is even more complex when it has to be estimated in urban areas, because of the complex patterns of the land-cover in these areas. In this research a modeling approach with integrated remote sensing analysis has been developed for estimating water fluxes in urban environments. The methodology was developed with the aim to simulate fluxes of contaminants from polluted sites. Groundwater pollution in urban environments is linked to patterns of land use and hence it is essential to characterize the land cover in a detail. An object-oriented classification approach applied on high-resolution satellite data has been adopted. To assign the image objects to one of the land-cover classes a multiple layer perceptron approach was adopted (Kappa of 0.86). Groundwater recharge has been simulated using the spatially distributed WetSpass model and the subsurface water flow using MODFLOW in order to identify and budget water fluxes. The developed methodology is applied to a brownfield case site in Vilvoorde, Brussels (Belgium). The obtained land use map has a strong impact on the groundwater recharge, resulting in a high spatial variability. Simulated groundwater fluxes from brownfield to the receiving River Zenne were independently verified by measurements and simulation of groundwater-surface water interaction based on thermal gradients in the river bed. It is concluded that in order to better quantify total fluxes of contaminants from brownfields in the groundwater, remote sensing imagery can be operationally integrated in a modeling procedure.     

Structural health monitoring of a cable-stayed bridge with Bayesian neural networks

In recent years, there has been an increasing interest in permanent observation of the dynamic behaviour of bridges for long-term monitoring purpose. This is due not only to the ageing of a lot of structures, but also for dealing with the increasing complexity of new bridges. The long-term monitoring of bridges produces a huge quantity of data that need to be effectively processed. For this purpose, there has been a growing interest on the application of soft computing methods. In particular, this work deals with the applicability of Bayesian neural networks for the identification of damage of a cable-stayed bridge. The selected structure is a real bridge proposed as benchmark problem by the Asian-Pacific Network of Centers for Research in Smart Structure Technology (ANCRiSST). They shared data coming from the long-term monitoring of the bridge with the structural health monitoring community in order to assess the current progress on damage detection and identification methods with a full-scale example. The data set includes vibration data before and after the bridge was damaged, so they are useful for testing new approaches for damage detection. In the first part of the paper, the Bayesian neural network model is discussed; then in the second part, a Bayesian neural network procedure for damage detection has been tested. The proposed method is able to detect anomalies on the behaviour of the structure, which can be related to the presence of damage. In order to obtain a confirmation of the obtained results, in the last part of the paper, they are compared with those obtained by using a traditional approach for vibration-based structural identification.     

Project cost risk analysis: A Bayesian networks approach for modeling dependencies between cost items

Uncertainty of cost items is an important aspect of complex projects. Cost uncertainty analysis aims to help decision makers to understand and model different factors affecting funding exposure and ultimately estimate the cost of project. The common practice in cost uncertainty analysis includes breaking the project into cost items and probabilistically capturing the uncertainty of each item. Dependencies between these items are important and if not considered properly may influence the accuracy of cost estimation. However these dependencies are seldom examined and there are theoretical and practical obstacles in modeling them.     

采用扩展的贝叶斯人工神经网络选择结构损伤监测模型

对采用规则的动态数据进行结构损伤监测时,模式识别是一个有效的方法,人工神经网络作为匹配模式特征的系统方式广泛应用于模式识别研究中。人工神经网络设计是影响模型识别性能和效率的最基本因素。由Lam等人提出的贝叶斯人工神经网络设计法则为单隐层前馈人工神经网络确定大量隐性神经单元提供了严格的数学手段。本文的第一个目标是对贝叶斯人工神经网络设计法则进行拓展,包括选择隐层中神经单元的传递函数。所提出的法则具有高效的特点,适用于实时人工神经网络设计。目前,许多人工神经网络设计技术需要在训练前已知人工神经网络模型的类型,因此,最基本的问题是自动选择优化的人工神经网络模型类型的技术。由于模型参数和Ritz向量一般用于描述模式的特征,本文的第二个目标是采用模式识别对结构损伤监测中这两个模式特征进行比较。为了清楚判断这两个特征,研究中采用了IASC-ASCE准则。研究结果显示:采用模型参数进行训练的人工神经网络性能略优于采用Ritz向量进行训练的人工神经网络性能。     

Computational framework for risk-based planning of inspections,maintenance and condition monitoring using discrete Bayesian networks

This paper presents a computational framework for risk-based planning of inspections and repairs for deteriorating components. Two distinct types of decision rules are used to model decisions: simple decision rules that depend on constants or observed variables (e.g. inspection outcome), and advanced decision rules that depend on variables found using Bayesian updating (e.g. probability of failure). Two decision models are developed, both relying on dynamic Bayesian networks (dBNs) for deterioration modelling. For simple decision rules, dBNs are used directly for exact assessment of total expected life-cycle costs. For advanced decision rules, simulations are performed to estimate the expected costs, and dBNs are used within the simulations for decision-making. Information from inspections and condition monitoring are included if available. An example in the paper demonstrates the framework and the implemented strategies and decision rules, including various types of condition-based maintenance. The strategies using advanced decision rules lead to reduced costs compared to the simple decision rules when condition monitoring is applied, and the value of condition monitoring is estimated by comparing the lowest costs obtained with and without condition monitoring.     

Triage methodology of bridges for infrastructure management: empirical analysis of road networks in municipalities with declining populations and increasing debts

The population of Japan peaked in 2010 and has since entered a depopulation period. On the other hand, there are many bridges that were constructed in the past, especially during the period of high economic growth. Their deteriorating state is becoming increasingly evident. It is expected that maintenance and management costs of the development and maintenance of urban infrastructure for bridges will increase. It is necessary to respond to the ageing of the national land stock. This study verifies urban infrastructure methodology to develop and maintenance using a road network of a municipality whose population actually decreases. This methodology makes use of the basic data held by the municipality such as the population and the length of the road. More specific, the authors propose a methodology for applying the triage to the decision-making processes involving bridges such as road bridges, similar to how it is applied when providing medical care to those with injuries caused by large-scale disasters. The proposed methodology is useful for municipal bridge management strategy and can be applied to other countries around the world that may face decreasing population and/or rising debt in the future.